ArcKit: The Enterprise Architecture Governance Harness

Build better enterprise architecture through structured strategy, design, delivery, and assurance workflows.

ArcKit is a toolkit for enterprise architects that transforms architecture governance from scattered documents into a systematic, AI-assisted workflow for:

• 🏛️ Establishing and enforcing architecture principles
• 👥 Analyzing stakeholder drivers, goals, and outcomes
• 🛡️ Risk management (HM Treasury Orange Book)
• 💼 Business case justification (HM Treasury Green Book SOBC)
• 📋 Creating comprehensive requirements documents
• 🗄️ Data modeling with ERD, GDPR compliance, and data governance
• 🔬 Technology research with build vs buy analysis (web search powered)
• ☁️ Azure-specific research using Microsoft Learn MCP for authoritative documentation
• 🗺️ Strategic planning with Wardley Mapping
• 📊 Generating visual architecture diagrams (Mermaid)
• 🤝 Managing vendor RFP and selection processes
• ✅ Conducting formal design reviews (HLD/DLD)
• 🔧 ServiceNow service management design
• 🔗 Maintaining requirements traceability
• 📎 Citation traceability for external documents (inline [DOC-CN] markers with source quotes)

ArcKit produces DRAFT artefacts for qualified people to review, not legal, regulatory, clinical, or security advice. See What ArcKit does not do.

---

Quick Start

Installation

Claude Code (premier experience) — install the ArcKit plugin (requires v2.1.287+):

First, make sure Claude Code is on the latest version:

claude install latest

Then in Claude Code:

/plugin marketplace add tractorjuice/arckit-claude

Then install from the Discover tab, or via CLI. The marketplace ships 17 plugins — install only the overlays you need:

# Core (76 commands — UK Government civilian + generic enterprise)
claude plugin install arckit@arckit-claude

# Core + UAE federal
claude plugin install arckit arckit-uae

# Broad overlay set (UK + UAE + FR + CA + EU + AT + AU + US + UK-NHS + UK-GCloud)
claude plugin install arckit arckit-{uae,fr,ca,eu,at,au,us,uk-nhs,uk-gcloud}

# Enterprise architecture and AI agent governance overlays
claude plugin install arckit arckit-togaf-adm arckit-agent-architecture

The standalone tractorjuice/arckit-claude marketplace hosts all Claude Code plugins: the arckit core plugin, regional overlays, sector overlays, the TOGAF ADM and AI agent architecture overlays, the arckit-fde tooling plugin, and the public-but-proprietary arckit-uk-gcloud supplier overlay. The 14 community plugins (arckit-uae, arckit-fr, arckit-ca, arckit-eu, arckit-at, arckit-au, arckit-au-energy, arckit-us, arckit-uk-finance, arckit-uk-nhs, arckit-uk-gcloud, arckit-togaf-adm, arckit-agent-architecture, arckit-oaa) require the arckit core plugin. arckit-au-energy (sector) additionally requires arckit-au (jurisdiction), which it composes — install with claude plugin install arckit arckit-au arckit-au-energy. arckit-uk-gcloud is a proprietary, Claude Code only supplier-side G-Cloud bid-authoring overlay — it is public for installation and inspection, but not MIT licensed and not distributed to the non-Claude extension formats. One tooling plugin — arckit-fde — is a lean, Claude Code only plugin with one command, /arckit-fde:create, that generates a brandable (white-label) Forward Deploy Engineering consulting website into docs/ (GitHub Pages ready), with UK Public Sector and Generic market presets; no dependencies, not converted to non-Claude formats, no governance doc-types.

The older tractorjuice/arc-kit marketplace remains available for compatibility, but new Claude Code installs should use tractorjuice/arckit-claude. Claude Code is the primary development platform for ArcKit and provides the most complete experience: all official commands, autonomous research agents, automation hooks, bundled MCP servers (AWS Knowledge, Microsoft Learn, Google Developer Knowledge, govreposcrape, uk-tenders), and automatic updates via the marketplace. See Why Claude Code? below.

Why v2.1.287? It adds Claude mods, which ArcKit uses to draw a status line above the prompt: how many projects and artefacts you have, how many are DRAFT, and how many reviews are overdue. It also fixes plugin SessionStart hooks not running in new cloud sessions, which skipped ArcKit's session set-up and version check there.

The floor also carries earlier releases ArcKit depends on:

Models

• v2.1.284 adds Claude Sonnet 5.5 (claude-sonnet-5-5), the default Sonnet model on the Anthropic API, with 1M context; earlier clients cannot select it. Like Opus 5.5 it always thinks and defaults to effort: medium, so ArcKit's effort: max commands run at max on it.
• v2.1.280 adds Claude Opus 5.5 (claude-opus-5-5), the default Opus model. It always thinks, so ArcKit's effort: max commands can no longer be quietly sent as high by a session with thinking off, and the Effective Effort row in each artefact's Build Provenance is accurate.
• v2.1.219 adds Claude Opus 5 (claude-opus-5), with 1M context and fast mode, which earlier clients cannot select (superseded as the default by Opus 5.5).
• v2.1.197 makes Claude Sonnet 5 the default, with native 1M context.

Security and permissions

• v2.1.251 stops the file tools (Read, Write, Edit) following a symlink swapped inside the working directory after the permission check, and makes Grep and Glob honour Read() deny rules through a symlinked search path. That is the same class of bypass the v2.1.222–v2.1.224 fixes closed for Bash, and the class ArcKit's file-protection and secret-file-scanner gates sit in front of.
• v2.1.234 stops Claude Code's MCP diagnostics printing resolved secrets. ArcKit bundles two keyed MCP servers whose ${user_config.*} API keys sit in request headers. On a session with no keys configured those connections fail by design, so ArcKit routinely produces exactly the diagnostics this fixed.
• v2.1.222 stops PreToolUse auto-allow hooks bypassing tool restrictions inside background agent tasks, which became load-bearing when v2.1.232 made subagent spawns background by default.
• v2.1.223 and v2.1.224 close Bash permission-check bypasses, a sandbox denyRead/denyWrite trailing-slash bypass, and a bug where project paths over 200 characters resolved into another project's session directory. v2.1.224 also surfaces sandbox violation details in Bash results.
• v2.1.172 fixes wildcard-domain WebFetch rules (WebFetch(domain:*.gov.uk)) that never matched subdomains on earlier clients. That is the exact shape ArcKit recommends for confining research-agent traffic in OFFICIAL-SENSITIVE deployments.

Effort and thinking

• v2.1.251 sends Opus 5 effort: xhigh/max as high when thinking is off instead of failing, so ArcKit's effort: max commands complete on thinking-off sessions.
• v2.1.221 fixes WebSearch returning a 400 at effort: xhigh/max when thinking is disabled, which silently broke ArcKit's effort: max commands and its three max-effort research agents for anyone running with thinking off.

Plugin loading and agents

• v2.1.246 fixes four plugin-loading bugs that hit ArcKit's exact layout: /reload-plugins counted 0 skills for plugins that define skills under skills/*/SKILL.md, hook error messages showed a literal ${CLAUDE_PLUGIN_ROOT} instead of the resolved path, the plugin cache created duplicate SHA-named directories, and claude plugin update <bare-name> failed.
• v2.1.200 fixes project-scoped plugin loading from git worktrees and claude agents --plugin-dir <dir> visibility, which makes ArcKit's branch and test-repo workflows reliable.
• v2.1.198–v2.1.199 fix background-subagent reliability, parent error propagation and hook stderr visibility, which matter to /arckit:build, reader/writer handoffs and hook diagnosis.

Older fixes: v2.1.156 Opus 4.8 thinking-block fix, v2.1.154 plugin defaultEnabled: false, v2.1.144 session-title and headless Skill tool fixes, v2.1.143 plugin dependency enforcement, v2.1.139 hook args: string[], v2.1.129 monitor layout and prompt-cache fixes, v2.1.121 MCP/provenance hook unlocks, v2.1.118–v2.1.119 release/telemetry unlocks, and the earlier /context, Auto mode, plugin update, MCP leak, retry and subagent working-directory fixes.

Gemini CLI — install the ArcKit extension:

gemini extensions install https://github.com/tractorjuice/arckit-gemini

Zero-config: all 76 official commands, templates, scripts, and bundled MCP servers (AWS Knowledge, Microsoft Learn). Updates via gemini extensions update arckit.

GitHub Copilot (VS Code) — install the ArcKit CLI and scaffold prompt files:

# Install with pip
pip install git+https://github.com/tractorjuice/arc-kit.git

# Scaffold a project with Copilot prompt files
arckit init my-project --ai copilot

Creates .github/prompts/arckit-*.prompt.md (165 prompt files — the 76 official commands plus the community overlays), .github/agents/arckit-*.agent.md (10 custom agents), and .github/copilot-instructions.md (repo-wide context). Invoke commands in Copilot Chat as /arckit-requirements, /arckit-stakeholders, etc.

Codex CLI — install the ArcKit CLI:

# Install with pip
pip install git+https://github.com/tractorjuice/arc-kit.git

# Or with uv
uv tool install arckit-cli --from git+https://github.com/tractorjuice/arc-kit.git

# Or run without installing
uvx --from git+https://github.com/tractorjuice/arc-kit.git arckit init my-project

Mistral Vibe CLI — link the ArcKit extension:

# Clone the standalone extension repository
git clone https://github.com/tractorjuice/arckit-vibe.git
cd arckit-vibe

# Create extensions directory and link
mkdir -p ~/.vibe/extensions/
ln -s $(pwd) ~/.vibe/extensions/arckit

Zero-config: 76 official commands as skills, 10 specialized agents, all templates, and bundled MCP servers (AWS Knowledge, Microsoft Learn, Google Developer Knowledge, GovRepoScrape).

Kimi Code CLI — start kimi, then install the ArcKit plugin from the prompt:

/plugins install https://github.com/tractorjuice/arckit-kimi.git

Every ArcKit command ships as an Agent Skill, invoked with /skill:arckit-<command> (for example /skill:arckit-requirements). The kimi.plugin.json manifest carries all six bundled MCP servers and auto-loads the architecture-workflow skill at session start.

Latest Release: v6.18.2

OKF Interoperability

ArcKit can exchange Markdown knowledge bundles using an Open Knowledge Format-shaped frontmatter layer:

• /arckit:export-okf copies ArcKit ARC-*.md artifacts into an OKF bundle with portable type, title, resource, tags, timestamp, and arckit metadata.
• /arckit:import-okf scans an OKF bundle, writes .arckit/tmp/okf-import-report.json, and materializes safe imports as RSCH review notes by default.
• Native ArcKit files remain unchanged unless you explicitly enable source frontmatter stamping with ARCKIT_OKF_FRONTMATTER=1 or .arckit/config.json containing { "okfFrontmatter": true }.

Platform Support

Windows users: The Claude Code plugin, Gemini CLI extension, GitHub Copilot prompt files, Mistral Vibe extension, and Kimi Code CLI extension work natively on all platforms. For Codex CLI / OpenCode CLI on native Windows (without WSL), some commands containing inline bash snippets may require Git Bash or WSL2. We recommend WSL2 for the best experience.

Initialize a Project

Claude Code: No initialization needed — the plugin provides everything.

Mistral Vibe: No initialization needed — the extension provides everything.

Kimi Code CLI:

# Create a new architecture governance project
arckit init payment-modernization --ai kimi

# Or initialize in current directory
arckit init . --ai kimi

GitHub Copilot (VS Code):

# Create a new architecture governance project
arckit init payment-modernization --ai copilot

# Or initialize in current directory
arckit init . --ai copilot

OpenCode CLI:

# Create a new architecture governance project
arckit init payment-modernization --ai opencode

# Or initialize in current directory
arckit init . --ai opencode

Codex CLI:

# Create a new architecture governance project
arckit init payment-modernization --ai codex

# Minimal install (skip docs and guides)
arckit init payment-modernization --ai codex --minimal

# Or initialize in current directory
arckit init . --ai codex

Start Using ArcKit

# GitHub Copilot (VS Code)
cd payment-modernization && code .
# In Copilot Chat, use ArcKit commands:
/arckit-principles Create principles for a financial services company
/arckit-requirements Build a payment processing system...

# Codex CLI
cd payment-modernization
codex
# Inside your AI assistant, use ArcKit commands:
/arckit:principles Create principles for a financial services company
/arckit:requirements Build a payment processing system...
/arckit:sow Generate RFP for vendor selection

# Mistral Vibe CLI
cd payment-modernization
vibe
# Use ArcKit skills:
/arckit-principles Create principles for a financial services company
/arckit-requirements Build a payment processing system...
/arckit-sow Generate RFP for vendor selection

# Or use specialized agents:
vibe --agent arckit-research "Research cloud providers"

# Kimi Code CLI
cd payment-modernization
kimi
# Use ArcKit skills:
/skill:arckit-principles Create principles for a financial services company
/skill:arckit-requirements Build a payment processing system...
/skill:arckit-sow Generate RFP for vendor selection

Upgrading

Claude Code plugin: Updates are automatic via the marketplace — no action needed.

Gemini CLI extension: Updates via gemini extensions update arckit.

GitHub Copilot: Re-run arckit init --here --ai copilot to update prompt files, agents, and instructions.

Mistral Vibe: Pull the latest standalone extension repo: cd ~/.vibe/extensions/arckit && git pull.

Kimi Code CLI: Re-run the install command from the kimi prompt to pick up the latest release: /plugins install https://github.com/tractorjuice/arckit-kimi.git.

Codex CLI:

# Step 1: Upgrade the CLI tool
pip install --upgrade git+https://github.com/tractorjuice/arc-kit.git
# Or with uv:
uv tool install --force arckit-cli --from git+https://github.com/tractorjuice/arc-kit.git

# Step 2: Update your existing project (re-run init in place)
cd /path/to/your-existing-project
arckit init --here --ai codex

This updates commands, templates, scripts, and agents while preserving your project data (projects/) and custom templates (.arckit/templates-custom/).

If upgrading from v0.x, you may also need to migrate legacy filenames — see the upgrading guide for full details.

---

Explore Example Outputs

Public demonstration repositories showcase complete ArcKit deliverables:

• NHS Appointment Booking — arckit-test-project-v7-nhs-appointment: Digital health platform with NHS Spine integration and GDPR safeguards.
• M365 GCC-H Migration — arckit-test-project-v1-m365: Government cloud migration with compliance mapping and change management.
• HMRC Tax Assistant — arckit-test-project-v2-hmrc-chatbot: Conversational AI service covering PII protection and bilingual support.
• Windows 11 Deployment — arckit-test-project-v3-windows11: Enterprise OS rollout with policy migration and security baselines.
• Patent Application System — arckit-test-project-v6-patent-system: Intellectual property workflow automation using GOV.UK Pay and Notify.
• ONS Data Platform — arckit-test-project-v8-ons-data-platform: Official statistics analytics environment with Five Safes governance.
• Cabinet Office GenAI Platform — arckit-test-project-v9-cabinet-office-genai: Cross-government GenAI platform with responsible AI guardrails.
• UK Government Training Marketplace — arckit-test-project-v10-training-marketplace: AI training procurement platform with multi-sided marketplace design.
• National Highways Data Architecture — arckit-test-project-v11-national-highways-data: Strategic road network data platform modernization.
• Scottish Courts GenAI — arckit-test-project-v14-scottish-courts: Scottish Courts and Tribunals Service GenAI strategy with comprehensive MLOps and FinOps.
• Doctors Appointment System — arckit-test-project-v16-doctors-appointment: Online appointment booking system with NHS integration.
• UK Fuel Price Transparency — arckit-test-project-v17-fuel-prices: UK Government fuel price transparency service with real-time pricing data.
• Smart Meter Consumer App — arckit-test-project-v18-smart-meter: UK Smart Meter data consumer mobile app with DCC/SMIP integration.
• UK Government API Aggregator — arckit-test-project-v19-gov-api-aggregator: Unified access to 240+ UK Government APIs across 34+ departments.

---

What it costs (plugin footprint)

Token cost of installing the arckit core plugin in a Claude Code session, captured from claude plugin details arckit on v2.1.143+:

• Always-on per session: ~10,042 tokens — added to every session's system context, covering the 73 command-skills + 5 utility skills (architecture-workflow, arckit-build, mermaid-syntax, plantuml-syntax, wardley-mapping) + 29 agent descriptors. Hooks (9 events) and MCP servers (6) are harness-resolved at runtime and not counted.
• On-invoke: ~250 to ~60K tokens per command — paid only when a specific skill or agent fires. Most commands are in the 5–10K range.

On-invoke cost by command

Costs are estimates from the Claude Code tokenizer and may differ from actual usage. Use this table to budget research-heavy multi-command sessions.

Trimming the footprint

• The five utility skills already use paths: globs to scope their always-on cost to relevant projects (mermaid-syntax only loads under *.mmd, wardley-mapping under WARD artefacts, etc.). The 73 command-skills are listed but not described in detail in the always-on context — the full prompt only loads on invocation.
• Community overlays (arckit-uae, arckit-fr, arckit-nl, arckit-ca, arckit-eu, arckit-at, arckit-au, arckit-au-energy, arckit-us, arckit-uk-finance, arckit-uk-nhs) are independent plugins — install only the jurisdictions / sectors you need. Each adds its own always-on baseline. arckit-uk-finance, arckit-uk-nhs, and arckit-au-energy are sector overlays (arckit-au-energy layers the energy sector on the arckit-au jurisdiction baseline); the rest are jurisdiction-based.
• Heavy commands (jsp-936, analyze, diagram, backlog) are on-invoke only; the always-on cost is unaffected by which heavy commands exist.

To measure your own session footprint, run /context all (Claude Code v2.1.139+) for per-skill token estimates against your active model.

---

Why ArcKit?

Problem: Architecture Governance is Broken

Traditional enterprise architecture suffers from:

• ❌ Scattered documents across tools (Word, Confluence, PowerPoint)
• ❌ Inconsistent governance enforcement
• ❌ Manual vendor evaluation with bias
• ❌ Lost traceability between requirements and design
• ❌ Stale documentation that doesn't match reality

Solution: Structured, AI-Assisted Governance

ArcKit provides:

• ✅ Template-Driven Quality: Comprehensive templates ensure nothing is forgotten
• ✅ Systematic Workflows: Clear processes from requirements → procurement → design review
• ✅ AI Assistance: Let AI handle document generation, you focus on decisions
• ✅ Enforced Traceability: Automatic gap detection and coverage analysis
• ✅ Version Control: Git-based workflow for all architecture artifacts

---

What ArcKit does not do

ArcKit generates DRAFT artefacts for qualified people to review. It is not legal, regulatory, clinical, or security advice, and no output it produces is a submission, a certification, an accreditation, or a compliance decision. Every artefact carries Status: DRAFT until a named accountable person signs it off, and that is the point at which responsibility for the content transfers to your organisation.

Concretely, and regardless of how complete an artefact looks:

• A /arckit:dpia output is not a completed DPIA. UK GDPR Article 35 places the assessment on the controller, and Article 36 requires prior consultation with the ICO where high residual risk remains. ArcKit drafts the document. The controller and the Data Protection Officer own it, and only they can conclude it.
• /arckit:secure and /arckit:mod-secure do not produce an assurance decision. NCSC CAF outcomes, Cyber Essentials certification, and MOD Secure by Design assurance are all judged by named accountable individuals and, where relevant, by certification bodies. A generated assessment is input to that judgement, never a substitute for it.
• /arckit:atrs and /arckit:ai-playbook do not make an algorithmic tool lawful, fair, or transparent. An ATRS record is published by the department after its own internal clearance, and the UK Government AI Playbook principles are obligations on the deploying organisation.
• The EU overlay does not perform conformity assessment. It drafts documentation referencing the AI Act, NIS2, DORA, CRA, DSA and the Data Act. It is not a notified-body activity, it does not determine your risk classification, and it does not track amendments or implementing acts as they are made.
• /arckit:jsp-936 and the NHS clinical safety commands are not assurance either. Defence AI assurance requires the accountable authority; DCB0129 and DCB0160 require a suitably registered Clinical Safety Officer.
• No output is a procurement decision. Research, scoring, and evaluation commands rank options against stated criteria. The Senior Responsible Owner and the procurement officer decide, under whatever framework rules apply to them.

Two limits apply to everything above:

1. Citations reflect the moment they were fetched. Commands cite sources at fetch time and record the URL, but legislation, standards, framework agreements, and vendor pricing all change. A citation that resolved when the artefact was generated may not describe the current text.
2. Generated content can be wrong. Output is produced by a language model, and research commands extract from third-party web pages that may themselves be inaccurate or written to mislead. ArcKit isolates that extraction behind schema validation and keeps scoring deterministic, which reduces the blast radius but does not make the underlying facts true.

Who must review what

Before any ArcKit artefact is relied on, published, or submitted:

• Data protection artefacts (DPIA, records of processing): Data Protection Officer
• Security and assurance artefacts: CISO, or the assessing authority for the relevant regime
• Clinical safety artefacts: a registered Clinical Safety Officer
• Business cases and procurement artefacts: Senior Responsible Owner and procurement or commercial lead
• Anything referencing a regulation, in any jurisdiction: qualified legal counsel for that jurisdiction

The community overlays each carry their own, narrower version of this warning. This section applies to all of ArcKit, including the officially-maintained core commands.

---

UK Government Compliance

ArcKit includes dedicated commands for UK public sector delivery:

• /arckit:tcop — Assess all 13 Technology Code of Practice points across delivery phases.
• /arckit:ai-playbook — Produce responsible AI assessments aligned to the UK Government AI Playbook and ATRS.
• /arckit:secure — Generate Secure by Design artefacts covering NCSC CAF, Cyber Essentials, and UK GDPR controls.
• /arckit:mod-secure — Map MOD Secure by Design requirements (JSP 440, IAMM, clearance pathways).
• /arckit:jsp-936 — Deliver JSP 936 AI assurance packs for defence AI systems.

See the demo repositories for end-to-end examples, especially arckit-test-project-v7-nhs-appointment (civilian services) and arckit-test-project-v9-cabinet-office-genai (AI governance).

---

EU, French, Dutch & Austrian Regulatory Compliance (Community)

⚠️ Community-contributed. EU and French commands are domain-maintained by @thomas-jardinet, Austrian commands by @gtonic. The 27 commands below cover EU regulations (GDPR, NIS2, AI Act, DORA, CRA, DSA, Data Act, Cloud Sovereignty Framework), French government standards (SecNumCloud, ANSSI, EBIOS, CNIL, DINUM, etc.), Dutch government standards (Rijksbreed cloudbeleid, VIRBI 2025, BIO2, cloud exit), and Austrian government standards (DSG, NISG 2026, BVergG 2018, BaFG / WZG accessibility). They are not part of the officially-maintained baseline — output should be reviewed by qualified DPO / CISO / Vergabejurist / legal counsel before reliance, and citations may lag current source text. Each command surfaces with a [COMMUNITY] prefix in /help listings and renders a warning banner before generating.

EU regulations (member-state-neutral baselines, applicable across EU/EEA):

• /arckit:eu-rgpd — GDPR (EU 2016/679) compliance assessment — legal basis, data subject rights, transfers, DPIA screening, breach notification
• /arckit:eu-nis2 — NIS2 Directive — operators of essential / important entities, Article 21 measures, incident reporting timelines
• /arckit:eu-ai-act — EU AI Act (Regulation 2024/1689) — risk classification (prohibited / high-risk / GPAI), conformity routes
• /arckit:eu-dora — Digital Operational Resilience Act (EU 2022/2554) — financial sector ICT risk, TLPT, third-party register
• /arckit:eu-cra — Cyber Resilience Act (Regulation 2024/2847) — products with digital elements, SBOM, VDP, CE marking
• /arckit:eu-cloud-sovereignty — EU Cloud Sovereignty Framework (v1.2.1) — eight weighted sovereignty objectives, SEAL-0 to SEAL-4 assurance levels, minimum-SEAL tender gate
• /arckit:eu-dsa — Digital Services Act (Regulation 2022/2065) — intermediaries, platforms, VLOPs, ARCOM
• /arckit:eu-data-act — Data Act (Regulation 2023/2854) — connected products, B2B FRAND, cloud switching, Article 27

French government (apply on top of the EU baseline for French deployments):

• /arckit:fr-secnumcloud — SecNumCloud 3.2 qualification (sovereign cloud, OIV/OSE, extraterritorial risk)
• /arckit:fr-dinum — DINUM standards: RGI, RGAA, RGESN, RGS, doctrine cloud de l'État, FranceConnect, DSFR
• /arckit:fr-marche-public — French public procurement (code de la commande publique, UGAP, sovereignty clauses)
• /arckit:fr-rgpd — CNIL-specific GDPR layer (cookies Délibération 2020-091, HDS, age 15, DPO registration)
• /arckit:fr-ebios — EBIOS Risk Manager — 5-workshop study (VM/ER/SR/CO/SS/SO/MS IDs, MITRE ATT&CK, homologation)
• /arckit:fr-anssi — ANSSI Guide d'hygiène informatique (42 measures) + cloud security recommendations
• /arckit:fr-anssi-carto — ANSSI SI cartography across business / application / system / network levels
• /arckit:fr-dr — Diffusion Restreinte handling under II 901 / SGDSN / ANSSI
• /arckit:fr-algorithme-public — Public algorithm transparency notice (Article L311-3-1 CRPA, Loi République Numérique)
• /arckit:fr-pssi — Information System Security Policy (PSSI) per ANSSI / RGS
• /arckit:fr-code-reuse — Public code reuse assessment (code.gouv.fr, SILL, EUPL) — build-vs-reuse decision matrix

Dutch government (apply on top of the EU baseline for Netherlands central-government deployments — domain-maintained by @umag):

• /arckit:nl-cloud — Rijksbreed cloudbeleid 2026 compliance (materieel cloudgebruik, exit plan, CISO Rijk notification, EEA residency, staatsgeheim / TBB eligibility)
• /arckit:nl-tbb — Te Beschermen Belangen and VIRBI 2025 rubricering (BIV scoring across five kernbelangen, one-way TBB↔rubricering inference)
• /arckit:nl-bio — BIO2 conformance (OBDO, on NEN-EN-ISO/IEC 27001:2023 and 27002:2022)
• /arckit:nl-exit — Cloud exit plan under Rijksbreed cloudbeleid clause 3.2 (planned exit and disruptive interruption, annual review)

Austrian government (apply on top of the EU baseline for Austrian deployments — domain-maintained by @gtonic):

• /arckit:at-dsgvo — Austrian DSG layer on GDPR (§§12–13 image processing, ELGA/GTelG health, §96a ArbVG employee monitoring, age 14 consent, DSB enforcement)
• /arckit:at-nisg — Austrian NISG 2026 (NIS2 transposition, BGBl. I Nr. 94/2025, in force 1 Oct 2026) — Essential/Important designation, Cybersicherheitsbehörde registration, CSIRT reporting (CERT.at / GovCERT), KSÖ, AT sectoral authorities
• /arckit:at-bvergg — Bundesvergabegesetz 2018 procurement — Oberschwellen/Unterschwellen, ANKÖ publication, Bestbieterprinzip, BVwG review
• /arckit:at-barrierefreiheit — Digital accessibility across both transposition tracks — BaFG (European Accessibility Act, private sector) and WZG (public sector), EN 301 549 / WCAG 2.1 AA, Barrierefreiheitserklärung, SMS and FFG

These layer cleanly on the existing baseline — fr-rgpd / at-dsgvo extend eu-rgpd, fr-pssi / at-nisg reference eu-nis2, and fr-secnumcloud integrates with arckit.research and arckit.evaluate for procurement workflows. Austrian commands carry [NEEDS VERIFICATION] markers where a point is genuinely open rather than unreviewed — implementing ordinances not yet issued under the NISG 2026, Länder scope, current guidance versions, and recent DSB case law. nl-cloud and nl-tbb play the same role for Dutch deployments, with nl-cloud keying its public-cloud eligibility off the rubricering determined by nl-tbb.

---

Canada Federal Overlay (12 commands)

Federal Canadian regulatory baseline as a [COMMUNITY] overlay — covering FITAA (Bill C-70 2024), federal privacy and access (Privacy Act, ATI Act), Treasury Board Directive on Automated Decision-Making, Charter rights design review, ITSG-33 + Standard on Security Categorization, Security of Information Act handling, GC Cloud sovereign residency, GC Digital Standards conformance, Official Languages Act, federal procurement (PSPC + PSAB), and First Nations OCAP® data sovereignty.

Help wanted: looking for a Canadian federal enterprise architect to co-maintain this overlay. Open an issue or DM @tractorjuice.

---

UAE Federal Overlay (Community-contributed)

⚠️ Community-contributed overlay. The 12 commands below cover UAE federal regulatory and digital-government instruments and ship as a community-contributed overlay (not part of the officially-maintained baseline of 68). They are anchored on the UAE Cabinet decree of 23 April 2026 mandating that 50% of federal services run on agentic AI by April 2028, and on the federal data, identity, AI governance, and procurement frameworks the decree references. The overlay is currently solo-maintained by @tractorjuice; a UAE domain co-maintainer is being recruited before the overlay can be re-evaluated for official-baseline promotion. Six citations are flagged [NEEDS VERIFICATION] pending Executive Regulations and authority confirmations — see docs/guides/uae-overlay-maintenance.md. Output should be reviewed by qualified UAE federal compliance counsel before reliance.

Set governance_framework: UAE Federal and classification_scheme: UAE Smart Data in plugin userConfig to switch the Document Control header into UAE Smart Data classification rendering across every artefact.

Federal data and security:

• /arckit:uae-classification — UAE Smart Data Classification Register (Open / Shared / Confidential / Secret / Top Secret) with handling rules and declassification schedule
• /arckit:uae-pdpl — Federal Decree-Law No. 45 of 2021 (PDPL) compliance assessment — DPIA, lawful-basis register, data-subject-rights procedure, cross-border transfer log
• /arckit:uae-ias — UAE Cybersecurity Council Information Assurance Standard v2 — Statement of Applicability against 188 controls (60 management M1–M6, 128 technical T1–T9), priority-tiered P1–P4
• /arckit:uae-cloud-residency — National Cloud Security Policy v2 sovereign cloud assessment — per-classification residency, approved CSPs (Core42 / G42, Microsoft UAE North/Central, TDRA FedNet, e& Sovereign Launchpad on AWS), shared-responsibility matrix, exit/portability plan

Federal identity:

• /arckit:uae-uaepass — UAE Pass integration design (OIDC/OAuth flow, claim mapping, Basic vs Verified profile selection, Service Provider onboarding, e-signature audit trail)

Cabinet instruments:

• /arckit:uae-zero-bureaucracy — Service Catalogue review under the UAE Code for Government Services and Zero Bureaucracy programme
• /arckit:uae-digital-records — Digital Records Plan under the UAE Government Services Digital Records Policy (source-of-truth register per service, retention schedule, official-source designation)
• /arckit:uae-data-sharing — Data Sharing Agreement under the UAE Government Services Data Sharing Policy ("collect once, use securely") with PDPL lawful basis per share
• /arckit:uae-priorities-alignment — National Priorities Alignment Statement under the UAE Federal Government Guide — reuse-vs-build, capability-reuse register (UAE Pass, FedNet), strategy alignment to NIS 2031 / AI 2031 / We the UAE 2031

AI governance:

• /arckit:uae-ai-charter — UAE Charter for the Development and Use of AI compliance assessment (12 principles)
• /arckit:uae-ai-autonomy-tier — Three-tier AI autonomy posture (Tier 1 internal-productivity, Tier 2 investor-facing-with-approval, Tier 3 regulated/financial) with per-tier guard-rails, approval gates, audit obligations, tier-promotion criteria

Procurement:

• /arckit:uae-procurement — Federal procurement strategy under Federal Decree-Law No. 11 of 2023 — ITT/RFP packs against MoF Digital Procurement Platform templates, In-Country Value (ICV) plan, evaluation report structure, contract register

The commands chain together in a canonical order from principles → uae-classification → uae-pdpl → uae-ias → uae-cloud-residency → uae-uaepass → uae-zero-bureaucracy → uae-digital-records → uae-data-sharing → uae-ai-charter → uae-ai-autonomy-tier → uae-priorities-alignment → uae-procurement → sobc → wardley → framework. Full guide: docs/guides/uae-overlay.md.

---

UK NHS Clinical Safety Overlay (Community-contributed)

⚠️ Community-contributed overlay — first sector-specific overlay in ArcKit. The 4 commands below cover NHS clinical safety (DCB0129 manufacturer + DCB0160 deployer), NHS DTAC procurement assurance, and UK MDR 2002 + EU MDR 2017/745 software-as-medical-device classification. Adopts Dr Marcus Baw's SAFETY.md spec for DCB0129/0160 file naming and YAML-frontmatter hazard log. Output is not clinical, legal, or regulatory advice — MUST be reviewed by a qualified Clinical Safety Officer (CSO with appropriate GMC / NMC / HCPC / GPhC registration) and, for MDR classification, by a qualified Regulatory Affairs specialist before reliance.

Clinical safety (DCB0129 + DCB0160):

• /arckit:uk-nhs-dcb0129 — NHS DCB0129 manufacturer Clinical Safety Case + Hazard Log. Produces a 3-file set in projects/{NNN}/clinical-safety/: SAFETY.md (front-door anchor), SAFETY-CASE.md (GSN-inspired safety argument), HAZARD-LOG.md (YAML-frontmatter hazard array + rendered Markdown table; 6 starter hazards covering wrong-patient, stale data, audit, authorisation, alert delivery, write integrity)
• /arckit:uk-nhs-dcb0160 — NHS DCB0160 deployer Clinical Safety Case + Deployment Hazard Log. Produces a 3-file deployer-side set in projects/{NNN}/clinical-safety/deployment/; 10 starter deployment hazards covering training, workflow integration, BC, parallel running, migration, local configuration, terminology, RBAC, incident reporting

Procurement and regulation:

• /arckit:uk-nhs-dtac — NHS Digital Technology Assessment Criteria v3 — 5 sections (Clinical Safety, Data Protection, Technical Assurance, Interoperability, Usability + Accessibility) plus AI annex. Cross-references DCB0129/0160, DPIA, ATRS, Secure by Design
• /arckit:uk-mdr-classification — UK MDR 2002 (as amended) + EU MDR 2017/745 software-as-medical-device (SaMD) and AI-as-medical-device (AIaMD) classification. UKCA / UKNI / CE marking pathway, Windsor Framework NI handling, conformity-assessment route, MHRA SaMD/AIaMD Programme alignment, ISO 14971 / IEC 62304 / ISO 13485 standards mapping, post-market obligations

The commands compose with — not replace — the UK government baseline (tcop, secure, dpia, atrs, risk, service-assessment). Recipe: uk-nhs-clinical-safety (44 targets across the clinical-safety waves). Proposed domain co-maintainer: Dr Marcus Baw (@pacharanero) — clinical informatician at RCPCH, openEHR, NHS England.

The DCB0129/0160 outputs deliberately do not carry the ARC- prefix — they follow Marcus's SAFETY.md spec convention so they remain readable by clinicians, MHRA reviewers, and procurement teams who do not use ArcKit. Other artefacts cross-reference them by relative path. Full design log: docs/superpowers/specs/2026-05-19-uk-nhs-overlay-design.md.

---

USA Federal Civilian Overlay (10 commands)

⚠️ Community-contributed overlay. The 10 commands below cover US federal civilian compliance instruments (FedRAMP authorization, FISMA / NIST 800-53 Rev 5, CISA Zero Trust Maturity Model, OMB M-19-17 ICAM, NIST AI RMF + OMB M-24-10/M-25-21 AI assurance, E-Government Act §208 PIA, EO 14028 SBOM self-attestation). They ship as the arckit-us community-contributed overlay (not part of the officially-maintained baseline of 72). EO 14110 was revoked January 2025; the live AI mandates are OMB M-24-10 + M-25-21. FedRAMP completed the Rev 5 transition in 2024. The overlay is currently solo-maintained by @tractorjuice; a US federal-civilian domain co-maintainer is being recruited (CISO / SAOP / FedRAMP PMO / CAIO backgrounds welcome) before the overlay can be re-evaluated for official-baseline promotion. Output should be reviewed by qualified US federal counsel before reliance.

In scope (v1): federal civilian agencies and the vendors that sell to them.

Out of scope (sibling overlays for the future): federal defense (CMMC / RMF / DISA STIGs), state regimes (StateRAMP / TX-RAMP / CJIS / IRS Pub 1075 / CCPA), sector-specific (HIPAA / GLBA / SOX / FERPA / PCI DSS), Section 508 accessibility (deferred to v5.2).

Recipe: us-federal (5 waves — baseline → controls → posture → ai → authorization).

Install: claude plugin install arckit arckit-us. See docs/guides/us-federal-overlay.md for the USA Federal Civilian overlay maintenance guide and citation register.

---

UK Finance Payments Overlay (4 commands) — First Sector Overlay

EXPERIMENTAL sector overlay. The 4 commands below cover UK regulated payment system operators scaling operations under PSD2 SCA-RTS, CASS V, FCA Consumer Duty, and CREST protocols. They ship as the arckit-uk-finance community-contributed overlay — the first sector-specific overlay (distinct from the 8 jurisdictional overlays). Output requires review by qualified UK FS regulatory counsel, MLRO, and SMF holders before implementation.

Payments architecture and compliance:

• /arckit:uk-nhs-dcb0129 — TBD
• /arckit:uk-nhs-dcb0160 — TBD
• /arckit:uk-nhs-dtac — TBD
• /arckit:uk-mdr-classification — TBD

Recipe: uk-fs-payments (multi-wave payment system modernization).

Install: claude plugin install arckit arckit-uk-finance. Help wanted: recruiting a UK financial services domain co-maintainer (CISO / Compliance / Head of Architecture background welcome) to transition to official-baseline status.

---

UK G-Cloud Supplier Bid-Authoring Overlay (15 commands) — Proprietary

PROPRIETARY, Claude Code only. The 15 commands below are a supplier-side overlay for authoring UK G-Cloud 15 (RM1557.15) Digital Marketplace bids, run by the Government Commercial Agency (GCA, formerly CCS): supplier profile, social value, lot questions, the Procurement Act 2023 supplier declaration, service design, a Service Definition Document for each of the five lots (1a, 1b, 2a, 2b, 3), pricing, security evidence, competitor benchmarking, submission review, and a final submission pack. Unlike every other ArcKit plugin, arckit-uk-gcloud ships under a proprietary licence (not MIT) and is not distributed to the non-Claude extension formats (Codex / Gemini / OpenCode / Copilot) — it runs on Claude Code only. It is the 4th sector-specific overlay (after arckit-uk-finance, arckit-uk-nhs, arckit-au-energy) and requires the arckit core plugin.

Supplier-wide (once per bid):

• /arckit:supplier-profile — Supplier profile: company, CDP and PPON, contacts, certifications, insurance (SUPP)
• /arckit:social-value — Social value commitments, Social Value Contact and operational readiness, 10% pass/fail on every lot (SOCV)
• /arckit:lot-questions — Lot questions per lot group: conditions of participation, scored Lot 1a/1b quality answers, Lot 2 and Lot 3 mandatory award criteria (LOTQ)
• /arckit:declaration — Procurement Act 2023 supplier declaration (DECL)

Per service:

• /arckit:service-design — Service design, lot choice and value proposition (SVCD)
• /arckit:sdd-lot1a — Service Definition Document, Lot 1a IaaS and PaaS (SDD)
• /arckit:sdd-lot1b — Service Definition Document, Lot 1b IaaS and PaaS above OFFICIAL (SDD)
• /arckit:sdd-lot2a — Service Definition Document, Lot 2a Infrastructure Software as a Service (SDD)
• /arckit:sdd-lot2b — Service Definition Document, Lot 2b Software as a Service (SDD)
• /arckit:sdd-lot3 — Service Definition Document, Lot 3 Cloud Support, with the DDaT role levels that deliver it (SDD)
• /arckit:pricing — Pricing by lot: 1a/1b price formula, 2a/2b discount bands; for Lot 3, the supplier's one DDaT rate card, shared by every Lot 3 service (PRIC, RATE)
• /arckit:security — Security evidence: certifications by lot and the NCSC Cloud Security Principles (SECA)
• /arckit:gcloud-competitors — G-Cloud competitor benchmark (GCMP)
• /arckit:review — G-Cloud submission review and gap analysis (GCRV)
• /arckit:submission-pack — Assemble the final G-Cloud submission pack

Recommended order: supplier-profile → social-value → service-design → the lot's SDD command → pricing and security → lot-questions → declaration → review → submission-pack. The lot questions come after the SDDs because their award criteria repeat each service's answers.

Skills: gcloud-framework (G-Cloud 15 question set, limits and evaluation), cloud-security, ddat-rate-card (Lot 3 job families, roles and levels; replaces sfia-skills). Recipe: uk-gcloud-submission (end-to-end bid assembly). G-Cloud 14 is no longer supported: /arckit:sdd-lot1 is replaced by sdd-lot1a and sdd-lot1b, and /arckit:sdd-lot2 by sdd-lot2a and sdd-lot2b.

Install: claude plugin install arckit arckit-uk-gcloud. Proprietary — see the licence-exception note at the foot of this README. Ported from the standalone gcloud-kit plugin.

---

TOGAF ADM Overlay (arckit-togaf-adm) [COMMUNITY]

Enterprise Architecture Development Method — 9 commands covering the full ADM cycle.

Install: claude plugin install arckit arckit-togaf-adm Recipe: togaf-adm-full — full ADM cycle via build recipe

---

O-AA Overlay (arckit-oaa) [COMMUNITY]

Open Agile Architecture (O-AA, standard C208) — agile enterprise architecture for product-driven, sprint-based delivery. A standalone overlay alongside arckit-togaf-adm; the two are complementary, not competitors — see the O-AA vs TOGAF ADM decision guide.

Handoff chain: agile-strategy → product-architecture → oaa-adm-lite → agile-security → agile-governance.

Install: claude plugin install arckit arckit-oaa Recipe: oaa-full — strategy → product → ADM Lite → security → governance

---

Using TOGAF ADM and O-AA Together

The two overlays are complementary, not competitors. Each depends only on the arckit core (=6.18.2 pin) — neither depends on the other. O-AA maps the ADM cycle to 2–4 week sprints; arckit-togaf-adm keeps the full document-centric ADM. Decision guide: O-AA vs TOGAF ADM.

Install for pattern A (one plugin per CLI invocation; community plugins install disabled):

claude plugin install arckit
claude plugin install arckit-togaf-adm && claude plugin enable arckit-togaf-adm
claude plugin install arckit-oaa && claude plugin enable arckit-oaa

Running both in the same project:

• No collisions: separate namespaces (/arckit-togaf-adm: vs /arckit-oaa:) and doc-type codes; one core install satisfies both =6.18.2 pins.
• Shared project-local schemas keep artefacts consistent across overlays: vision.yaml (ADM Preliminary ↔ O-AA Lite), implementation-strategy.yaml (Transition ↔ implementation waves), change-request.yaml + compliance-evidence.json (architecture-change ↔ agile-governance).
• Order: run the TOGAF baseline first, then let O-AA sprints execute it at sprint velocity. O-AA commands do not read TOGAF outputs, so the reverse order works mechanically — you just lose the "sprints execute the baseline" benefit.

---

AI Agent Architecture Overlay (arckit-agent-architecture) [COMMUNITY]

Governance, design, and security for autonomous AI agent programs — 6 commands.

Install: claude plugin install arckit arckit-agent-architecture Recipe: agent-architecture — full agent architecture lifecycle via build recipe

Combined Recipe: togaf-agent-full

For organisations adopting both enterprise architecture and AI agent governance:

claude agent recipes/togaf-agent-full.yaml

---

The ArcKit Workflow

ArcKit guides you through the enterprise architecture lifecycle:

Phase 0: Project Planning

/arckit:plan → Create project plan with timeline, phases, and gates

Visualize your entire project delivery:

• GDS Agile Delivery phases (Discovery → Alpha → Beta → Live)
• Mermaid Gantt chart with timeline, dependencies, and milestones
• Workflow diagram showing gates and decision points
• Tailored timeline based on project complexity
• Integration of all ArcKit commands into schedule
• Gate approval criteria for governance

Phase 1: Establish Governance

/arckit:principles → Create enterprise architecture principles

Define your organisation's architecture standards:

• Cloud strategy (AWS/Azure/GCP)
• Security frameworks (Zero Trust, compliance)
• Technology standards
• FinOps and cost governance

Phase 2: Stakeholder Analysis

/arckit:stakeholders → Analyze stakeholder drivers, goals, and outcomes

Do this BEFORE business case to understand who cares about the project and why:

• Identify all stakeholders (internal and external)
• Document underlying drivers (strategic, operational, financial, compliance, risk, personal)
• Map drivers to SMART goals
• Map goals to measurable outcomes
• Create Stakeholder → Driver → Goal → Outcome traceability
• Identify conflicts and synergies
• Define engagement and communication strategies

Phase 3: Risk Assessment

/arckit:risk → Create comprehensive risk register (Orange Book)

Do this BEFORE business case to identify and assess risks systematically:

• Follow HM Treasury Orange Book 2023 framework
• Identify risks across 6 categories (Strategic, Operational, Financial, Compliance, Reputational, Technology)
• Assess inherent risk (before controls) and residual risk (after controls)
• Apply 4Ts response framework (Tolerate, Treat, Transfer, Terminate)
• Link every risk to stakeholder from RACI matrix
• Monitor risk appetite compliance
• Feed into SOBC Management Case Part E

Phase 4: Business Case Justification

/arckit:sobc → Create Strategic Outline Business Case (SOBC)

Do this BEFORE requirements to justify investment and secure approval:

• Use HM Treasury Green Book 5-case model (Strategic, Economic, Commercial, Financial, Management)
• Analyze strategic options (Do Nothing, Minimal, Balanced, Comprehensive)
• Map benefits to stakeholder goals (complete traceability)
• Provide high-level cost estimates (Rough Order of Magnitude)
• Economic appraisal (ROI range, payback period)
• Procurement and funding strategy
• Governance and risk management (uses risk register)
• Enable go/no-go decision BEFORE detailed requirements work

Phase 5: Define Requirements

/arckit:requirements → Document comprehensive requirements

Create detailed requirements informed by stakeholder goals (if SOBC approved):

• Business requirements with rationale
• Functional requirements with acceptance criteria
• Non-functional requirements (performance, security, scalability, compliance)
• Integration requirements (upstream/downstream systems)
• Data requirements (DR-xxx)
• Success criteria and KPIs

Phase 5.3: Platform Strategy Design (Optional - for Multi-Sided Platforms)

/arckit:platform-design → Design multi-sided platform strategy using Platform Design Toolkit

Use this phase when designing ecosystem-based platforms (Government as a Platform, marketplaces, data platforms):

• Ecosystem Canvas: Map supply side, demand side, supporting entities with relationship diagrams
• Entity-Role Portraits: Deep dive into 3-5 key entities (context, pressures, goals, gains)
• Motivations Matrix: Identify synergies and conflicts across entities with mitigation strategies
• Transactions Board: Design 10-20 transactions with cost reduction analysis (search, information, negotiation, coordination, enforcement)
• Learning Engine Canvas: 5+ services that help participants improve (data, feedback loops, network effects)
• Platform Experience Canvas: Journey maps with business model and unit economics
• MVP Canvas: Liquidity bootstrapping strategy to solve chicken-and-egg problem
• Platform Design Canvas: Synthesize all 8 canvases into cohesive platform strategy
• UK Government Context: Aligns with Government as a Platform (GaaP), TCoP Point 8 (share/reuse), Digital Marketplace

Use Cases: NHS appointment booking, local authority data marketplaces, training procurement platforms, citizen services portals

Phase 5.5: Data Modeling

/arckit:data-model → Create comprehensive data model with ERD

Create data model based on Data Requirements (DR-xxx):

• Visual Entity-Relationship Diagram (ERD) using Mermaid
• Detailed entity catalog with attributes, types, validation rules
• PII identification and GDPR/DPA 2018 compliance
• Data governance matrix (business owners, stewards, custodians)
• CRUD matrix showing component access patterns
• Data integration mapping (upstream sources, downstream consumers)
• Data quality framework with measurable metrics
• Requirements traceability (DR-xxx → Entity → Attribute)

Phase 5.7: Data Protection Impact Assessment

/arckit:dpia → Generate DPIA for UK GDPR Article 35 compliance

MANDATORY for high-risk processing - assess privacy risks before technology selection:

• ICO 9-criteria automated screening (sensitive data, large scale, vulnerable subjects, AI/ML, etc.)
• Auto-populated from data model (entities, PII, special category data, lawful basis)
• Risk assessment focused on impact on individuals (privacy harm, discrimination)
• Data subject rights implementation checklist (SAR, deletion, portability)
• Children's data assessment (age verification, parental consent)
• AI/ML algorithmic processing assessment (bias, explainability, human oversight)
• ICO prior consultation flagging for high residual risks
• International transfer safeguards (SCCs, BCRs, adequacy decisions)
• Bidirectional links to risk register (DPIA-xxx risk IDs)
• Links mitigations to Secure by Design security controls

Phase 5.8: Data Source Discovery

/arckit:datascout → Discover external data sources

Discover and evaluate external data sources to fulfil project data requirements:

• Data needs extraction from DR/FR/INT/NFR requirements
• UK Government open data portals (data.gov.uk, ONS, NHS Digital, Companies House, OS Data Hub)
• Commercial API providers and data marketplaces
• Free/freemium APIs and open source datasets
• Weighted evaluation scoring (Requirements Fit, Data Quality, License & Cost, API Quality, Compliance, Reliability)
• Gap analysis for unmet data needs
• Data model impact assessment (new entities, attributes, sync strategy)
• Requirements traceability (every DR-xxx mapped to a source or flagged as gap)
• TCoP Point 10 compliance (Make Better Use of Data)

Phase 6: Technology Research

/arckit:research → Research technology, services, and products

Research available solutions to meet requirements with build vs buy analysis:

• Dynamic category detection from requirements (authentication, payments, databases, etc.)
• Commercial SaaS options with pricing, reviews, and ratings (WebSearch)
• Open source alternatives with GitHub stats and community maturity
• UK Government GOV.UK platforms (One Login, Pay, Notify, Forms)
• Digital Marketplace suppliers (G-Cloud, DOS)
• Total Cost of Ownership (TCO) comparison (3-year)
• Build vs Buy vs Adopt recommendations
• Vendor shortlisting for deeper evaluation
• Integration with Wardley mapping (evolution positioning)
• Feeds into SOBC Economic Case (cost data, options analysis)

Phase 6.5: Grants & Funding Research

/arckit:grants → Research UK government grants, charitable funding, and accelerator programmes

Identify and evaluate funding opportunities with eligibility scoring:

• UK Innovate UK grants and R&D funding (e.g. Smart Grants, KTP, SBRI)
• UK Research and Innovation (UKRI) funding calls
• Charitable foundations and philanthropic funding (e.g. National Lottery Heritage Fund, Wellcome Trust)
• Accelerator and incubator programmes (e.g. DCMS, DSIT-backed cohorts)
• EU Horizon Europe successor funding open to UK entities
• Eligibility scoring matrix against project requirements and stakeholder profile
• Application timeline, deadlines, and award values
• Strategic fit assessment (alignment with project goals and public sector context)
• Outputs a structured GRNT funding opportunity register

Phase 7: Strategic Planning with Wardley Mapping

/arckit:wardley → Create strategic Wardley Maps

Visualize strategic positioning with:

• Component evolution analysis (Genesis → Custom → Product → Commodity)
• Build vs Buy decision framework
• Vendor comparison and procurement strategy
• UK Government Digital Marketplace mapping
• Evolution predictions and strategic gameplay

Phase 7.5: Strategic Roadmap

/arckit:roadmap → Create multi-year architecture roadmap

Create strategic roadmap for multi-year transformation programs:

• Multi-year timeline: 3-5 year roadmap with Mermaid Gantt chart aligned to financial years (FY 2024/25, etc.)
• Strategic themes: Cloud migration, data modernization, security & compliance, DevOps transformation
• Capability evolution: Maturity progression from L1 (Initial) to L5 (Optimized) over time
• Investment planning: CAPEX/OPEX budget by financial year, ROI projections, benefits realization
• Governance framework: ARB monthly, Programme Board monthly, Steering Committee quarterly
• Service Standard gates: Alpha/Beta/Live assessment milestones (UK Government)
• Dependencies: Mermaid flowchart showing initiative sequencing and critical path
• Success metrics: Cloud adoption %, technical debt reduction, deployment frequency, time to market
• Traceability: Links roadmap themes to stakeholder drivers, architecture principles, requirements
• UK Government specifics: Spending Review alignment, TCoP compliance timeline, NCSC CAF progression

Use this when: You have a multi-year transformation program with multiple initiatives running in parallel. Roadmaps are strategic (multi-year, multi-initiative, executive communication) vs project plans which are tactical (single initiative, detailed tasks, team execution).

Roadmap feeds into: /arckit:plan for detailed phase execution, /arckit:sobc for investment business case, /arckit:backlog for prioritized user stories, /arckit:strategy for executive-level synthesis.

Phase 7.6: Architecture Strategy Synthesis

/arckit:strategy → Synthesise strategic artifacts into executive-level Architecture Strategy

Create a comprehensive Architecture Strategy document that synthesises multiple strategic artifacts into a single coherent narrative:

• Strategic vision: 2-3 paragraphs articulating the transformation vision and success definition
• Strategic drivers: Summarised from stakeholder analysis with external drivers (regulatory, market, technology)
• Guiding principles: Key principles with strategic implications, compliance summary
• Current state assessment: Technology landscape, capability maturity baseline (L1-L5), technical debt, SWOT
• Target state vision: Future architecture, capability maturity targets, architecture vision diagram
• Technology evolution: Build vs buy decisions, technology radar (Adopt/Trial/Assess/Hold) from Wardley maps
• Strategic themes: 3-5 investment themes with objectives, initiatives, success criteria, principles alignment
• Delivery roadmap summary: Timeline, phases, milestones from roadmap artifact
• Investment summary: CAPEX/OPEX, NPV, IRR, payback period, benefits realisation from SOBC
• Strategic risks: Top risks with heat map, assumptions, constraints from risk register
• Success metrics: KPIs with baselines and year-over-year targets
• Governance model: Forums, decision rights, review cadence
• Traceability: Driver → Goal → Outcome → Theme → Principle → KPI chain

Use this when: You have multiple strategic artifacts (principles, stakeholders, wardley, roadmap, sobc) and need to create a single executive-level document that synthesises them into a coherent strategy. Ideal for Strategy Board presentations, executive briefings, or stakeholder communication.

Unique requirement: This is the only ArcKit command with TWO mandatory inputs (principles AND stakeholders). Strategy cannot be created without understanding both the decision framework and the stakeholder drivers.

Strategy feeds into: /arckit:requirements for detailed requirements, /arckit:roadmap for expanded timeline, /arckit:plan for project delivery.

Phase 7.7: Architecture Decision Records

/arckit:adr → Document architectural decisions

Create Architecture Decision Records (ADRs) following MADR v4.0 format enhanced with UK Government requirements:

• Decision metadata: Sequential numbering (ADR-001, ADR-002), status (Proposed/Accepted/Superseded), escalation level (Team/Cross-team/Department/Cross-government)
• Stakeholder RACI: Deciders (accountable), Consulted (SMEs, two-way), Informed (one-way communication)
• Context and problem statement: Why this decision is needed, business/technical/regulatory drivers
• Decision drivers: Technical forces (performance, security, scalability), business forces (cost, time), compliance forces (GDS Service Standard, TCoP, NCSC, UK GDPR)
• Options analysis: Minimum 2-3 options plus "Do Nothing" baseline, each with pros/cons, cost (CAPEX/OPEX/TCO), GDS Service Standard impact, Wardley evolution stage
• Y-Statement: Structured justification - "In the context of X, facing Y, we decided for Z to achieve A, accepting B"
• Consequences: Positive (benefits, capabilities), Negative (trade-offs, technical debt), Neutral (training, infrastructure), Risks and mitigations
• Validation: How implementation will be verified (design reviews, code reviews, testing, monitoring)
• Traceability: Links to requirements, principles, stakeholders, research, Wardley maps, diagrams, risk register
• UK Government specifics: Escalation levels (Team → Cross-team → Department → Cross-government), governance forums (ARB, TDA, Programme Board), Service Standard/TCoP compliance documentation

Use this when: Making significant architectural decisions that affect system structure, quality attributes, or behavior - technology choices (databases, frameworks, cloud services), integration patterns, security approaches, deployment strategies, data management.

ADR feeds into: /arckit:diagram (architecture diagrams reflect decisions), /arckit:hld-review and /arckit:dld-review (reviews verify decisions implemented), /arckit:traceability (decisions are key traceability artifacts).

Phase 8: Vendor Procurement (if needed)

/arckit:sow → Generate Statement of Work (RFP)

Create RFP-ready documents with:

• Scope of work and deliverables
• Technical requirements
• Vendor qualifications
• Evaluation criteria
• Contract terms

/arckit:dos → Digital Outcomes and Specialists (DOS) procurement 🇬🇧

For UK public sector organizations needing custom development:

• Generate DOS-compliant procurement documentation
• Extract requirements from project artifacts (BR/FR/NFR/INT/DR)
• Essential vs desirable skills from requirements
• Success criteria (technology-agnostic)
• Evaluation framework (40% Technical, 30% Team, 20% Quality, 10% Value)
• Audit-ready documentation for Digital Marketplace

/arckit:gcloud-search → G-Cloud service search with live marketplace search 🇬🇧

For UK public sector organizations needing off-the-shelf cloud services:

• Generate G-Cloud requirements document
• Live Digital Marketplace search using WebSearch
• Find actual services with suppliers, prices, features, links
• Service comparison table with recommendations
• Shortlist top 3-5 matching services
• Links to Digital Marketplace guidance (gov.uk)

/arckit:gcloud-clarify → G-Cloud service validation and gap analysis 🇬🇧

Validate G-Cloud services and generate supplier clarification questions:

• Systematic gap analysis (MUST/SHOULD requirements vs service descriptions)
• Detect gaps: ✅ Confirmed, ⚠️ Ambiguous, ❌ Not mentioned
• Generate prioritised questions (🔴 Critical / 🟠 High / 🔵 Medium / 🟢 Low)
• Risk assessment matrix for each service
• Email templates for supplier engagement
• Evidence requirements specification
• Next steps checklist

/arckit:evaluate → Create vendor evaluation framework

Set up systematic scoring:

• Technical evaluation criteria (100 points)
• Cost evaluation methodology
• Reference check templates
• Decision matrix

/arckit:evaluate (compare mode) → Compare vendor proposals

Side-by-side analysis of:

• Technical approaches
• Cost breakdowns
• Risk assessments
• Value propositions

Phase 9: Design Review

/arckit:hld-review → Review High-Level Design

Validate designs against:

• Architecture principles compliance
• Requirements coverage
• Security and compliance
• Scalability and resilience
• Operational readiness

/arckit:dld-review → Review Detailed Design

Implementation-ready validation:

• Component specifications
• API contracts (OpenAPI)
• Database schemas
• Security implementation
• Test strategy

Phase 10: Sprint Planning

/arckit:backlog → Generate prioritised product backlog

Transform requirements into sprint-ready user stories:

• Convert requirements (BR/FR/NFR/INT/DR) to GDS-format user stories
• Multi-factor prioritization (MoSCoW + risk + value + dependencies)
• Organise into sprint plan with capacity balancing
• Generate traceability matrix (requirements → stories → sprints)
• Export to Jira/Azure DevOps (CSV) or custom tools (JSON)
• Time savings: 75%+ (4-6 weeks → 3-5 days)

When to run: After HLD approval, before Sprint 1 (Alpha → Beta transition)

Phase 10.5: Backlog Export

/arckit:trello → Export product backlog to Trello

Push your backlog directly to Trello for sprint execution:

• Create Trello board with sprint-based lists (Product Backlog + per-sprint + In Progress + Done)
• Cards with priority labels, story points, and acceptance criteria checklists
• Colour-coded labels by MoSCoW priority and requirement type
• Rate-limit-aware Trello API integration
• Requires TRELLO_API_KEY and TRELLO_TOKEN environment variables

When to run: After /arckit:backlog generates the product backlog (requires JSON export)

Phase 11: ServiceNow Service Management Design

/arckit:servicenow → Generate ServiceNow service design

Bridge architecture to operations:

• CMDB design (derived from architecture diagrams)
• SLA definitions (derived from NFRs)
• Incident management design
• Change management plan
• Monitoring and alerting plan
• Service transition plan

Phase 12: Traceability

/arckit:traceability → Generate traceability matrix

Ensure complete coverage:

• Requirements → Design mapping
• Design → Test mapping
• Gap analysis and orphan detection
• Change impact tracking

Phase 13: Quality Assurance

/arckit:analyze → Comprehensive governance quality analysis

Periodically assess governance quality across all artifacts:

• Architecture principles compliance
• Requirements coverage and traceability
• Stakeholder alignment verification
• Risk management completeness
• Design review quality
• Documentation completeness and quality
• Gap identification and recommendations

When to use: Run periodically (before milestones, design reviews, or procurement decisions) to identify gaps and ensure governance standards are maintained.

Phase 14: Compliance Assessment (UK Government)

For UK Government and public sector projects:

/arckit:service-assessment → GDS Service Standard assessment preparation

Prepare for mandatory GDS Service Standard assessments:

• Analyze evidence against all 14 Service Standard points
• Identify gaps for alpha, beta, or live assessments
• Generate RAG (Red/Amber/Green) ratings and overall readiness score
• Provide actionable recommendations with priorities and timelines
• Include assessment day preparation guidance
• Map ArcKit artifacts to Service Standard evidence requirements

Run at end of Discovery (for alpha prep), mid-Beta (for beta prep), or before Live to ensure readiness.

/arckit:tcop → Technology Code of Practice assessment

Assess compliance with all 13 TCoP points:

• Point 1: Define user needs
• Point 2: Make things accessible
• Point 3: Be open and use open source
• Point 4: Make use of open standards
• Point 5: Use cloud first
• Point 6: Make things secure
• Point 7: Make privacy integral
• Point 8: Share, reuse and collaborate
• Point 9: Integrate and adapt technology
• Point 10: Make better use of data
• Point 11: Define your purchasing strategy
• Point 12: Meet the Digital Spend Controls
• Point 13: Define your responsible AI use

/arckit:secure → UK Government Secure by Design assessment

Security compliance assessment:

• NCSC Cloud Security Principles
• NCSC Cyber Assessment Framework (CAF)
• Cyber Essentials / Cyber Essentials Plus
• UK GDPR and DPA 2018 compliance
• Security architecture review
• Threat modeling

/arckit:ai-playbook → UK Government AI Playbook compliance (for AI systems)

Responsible AI assessment:

• AI ethics principles
• Transparency and explainability
• Fairness and bias mitigation
• Data governance for AI
• Human oversight mechanisms
• Impact assessment

/arckit:atrs → Algorithmic Transparency Recording Standard

Generate ATRS record for algorithmic decision-making:

• Algorithm details and logic
• Purpose and use case
• Data sources and data quality
• Performance metrics and monitoring
• Impact assessment and mitigation

For MOD Projects:

/arckit:mod-secure → MOD Secure by Design assessment

MOD-specific security compliance:

• JSP 440 (Defence Project & Programme Management)
• Information Assurance Maturity Model (IAMM)
• MOD Security clearances and vetting
• STRAP classification handling
• Security Operating Procedures (SyOPs)
• Supplier attestation requirements

/arckit:jsp-936 → MOD JSP 936 AI Assurance Documentation

For defence projects using AI/ML systems:

• JSP 936 (Dependable Artificial Intelligence in Defence)
• 5 Ethical Principles (Human-Centricity, Responsibility, Understanding, Bias & Harm Mitigation, Reliability)
• 5 Risk Classification Levels (Critical to Minor)
• 8 AI Lifecycle Phases (Planning to Quality Assurance)
• Approval pathways (2PUS/Ministerial → Defence-Level → TLB-Level)
• RAISOs and Ethics Manager governance
• Human-AI teaming strategy and continuous monitoring

Phase 14.5: Compliance Assessment (EU and French Government)

ArcKit includes commands for EU regulatory compliance and French public sector governance. These commands are applicable to organisations operating in the EU or under French jurisdiction — whether public sector or private.

EU Regulations

/arckit:eu-rgpd → GDPR compliance assessment (Regulation 2016/679)

Assess personal data processing obligations:

• Legal basis determination (consent, contract, legitimate interest, legal obligation)
• Data subject rights implementation (access, erasure, portability, objection)
• CNIL registration and DPO obligations (France)
• Cross-border transfer safeguards (SCCs, BCRs, adequacy decisions)
• Integration with DPIA (/arckit:dpia) for high-risk processing

/arckit:eu-ai-act → EU AI Act compliance (Regulation 2024/1689)

Assess AI system obligations under the EU's risk-based AI framework:

• Risk classification (unacceptable / high-risk / limited-risk / minimal)
• High-risk system obligations: conformity assessment, CE marking, EUDB registration
• GPAI model obligations for providers of general-purpose AI
• Human oversight, transparency, and fundamental rights impact assessment
• Prohibited practices (social scoring, real-time biometric surveillance)

/arckit:eu-nis2 → NIS2 Directive compliance (Directive 2022/2555)

Assess cybersecurity obligations for essential and important entities:

• Sector classification (Annex I Essential vs Annex II Important)
• OIV/OSE designation under French transposition (LPM/LCEN)
• Governance, risk management, and incident reporting obligations
• Supply chain security and vulnerability disclosure
• ANSSI notification timeline (24h → 72h → 30-day final report)

/arckit:eu-dora → DORA compliance (Regulation 2022/2554) for financial entities

Digital Operational Resilience Act obligations for banks, insurers, and investment firms:

• ICT risk management framework (5 pillars)
• Major ICT-related incident classification and reporting (4h → 72h → monthly final)
• TLPT (Threat-Led Penetration Testing) requirements for significant institutions
• Third-party ICT provider management and critical provider designation
• Contractual requirements for ICT service agreements

/arckit:eu-cra → Cyber Resilience Act compliance (Regulation 2024/2847)

Mandatory cybersecurity requirements for products with digital elements (hardware + software):

• Product classification (Default / Important Class I / Critical Class II)
• 12 Annex I Part I security-by-design requirements
• SBOM in SPDX or CycloneDX format (mandatory)
• Vulnerability Disclosure Policy and 24h ENISA reporting
• Conformity assessment route (internal control vs notified body)
• Full application deadline: 11 December 2027

/arckit:eu-dsa → EU Digital Services Act compliance (Regulation 2022/2065)

Tiered obligations for online intermediary services:

• Provider classification (mere conduit / hosting / platform / VLOP / VLOSE)
• VLOP/VLOSE designation threshold: 45M monthly active EU users
• Content moderation, recommender system transparency, advertising obligations
• ARCOM as French Digital Services Coordinator (DSC)
• Systemic risk assessment and independent audit for VLOPs

/arckit:eu-data-act → EU Data Act compliance (Regulation 2023/2854)

Data sharing obligations for connected products and cloud providers:

• Role determination: manufacturer / data holder / DAPS / public sector body
• User data access rights (Chapter II) and B2B sharing (Chapter III)
• Cloud switching obligations (Chapter VI) — egress fee elimination by September 2027
• International data transfer restrictions (Article 27)
• Application date: 12 September 2025

French Public Sector Governance

/arckit:fr-rgpd → French GDPR compliance with CNIL-specific requirements

Extends EU GDPR with French context:

• CNIL enforcement priorities and sector-specific guidelines
• French DPO registration and CNIL prior consultation obligations
• Biometric data processing under French law (CNIL authorisation required)

/arckit:fr-ebios → EBIOS Risk Manager methodology (ANSSI 2018)

French standard risk analysis for IS homologation:

• 5-workshop structure (Framework, Risk Sources, Strategic Scenarios, Operational Scenarios, Risk Treatment)
• OIV/OSE/public sector IS homologation evidence
• Attack path modelling and feared events
• Integration with PSSI and SecNumCloud qualification

/arckit:fr-anssi → ANSSI 42 Cybersecurity Hygiene Measures assessment

Assess compliance with ANSSI's foundational hygiene guide:

• 7 themes: administration, authentication, updates, monitoring, backups, network, workstations
• Cloud security recommendations (ANSSI cloud qualification matrix)
• Gap analysis with prioritised remediation (P1–P3)
• Integration with EBIOS and PSSI

/arckit:fr-anssi-carto → ANSSI SI Cartography (4-level IS mapping)

Generate structured IS cartography following ANSSI's 4-level methodology:

• Level 1: Business processes and core missions
• Level 2: Application and data mapping
• Level 3: Server, database, and system inventory
• Level 4: Network topology, firewall rules, interconnections
• Attack surface summary and sensitive flow identification

/arckit:fr-secnumcloud → SecNumCloud qualification assessment

Assess cloud provider and customer obligations under ANSSI's SecNumCloud referential:

• Visa vs qualification distinction (only full qualification satisfies OIV/ministerial use)
• IS homologation prerequisites for SecNumCloud deployment
• SecNumCloud-compatible architecture requirements
• Procurement clauses for public-cloud contracts

/arckit:fr-dinum → DINUM digital doctrine assessment

Assess compliance with French digital government doctrine:

• RGI (Référentiel Général d'Interopérabilité) — interoperability standards
• RGAA (Référentiel Général d'Amélioration de l'Accessibilité) — accessibility
• Doctrine cloud (cloud native, cloud first, SecNumCloud for sensitive data)
• SILL (Socle Interministériel de Logiciels Libres) — recommended open source stack

/arckit:fr-marche-public → French public procurement (Code de la Commande Publique)

Generate procurement documentation compliant with French public contract law:

• Marché public thresholds and procedures (below/above EU thresholds)
• CCAP, CCTP, RC documentation templates
• ANSSI-qualified provider requirements (PASSI, PRIS, PDIS)
• Achat public durable obligations (environmental and social clauses)

/arckit:fr-pssi → PSSI (Politique de Sécurité des Systèmes d'Information)

Generate IS security policy for French public sector entities:

• 9-section structure approved by the Highest Authority (AA)
• 7 security domains (network, workstations, applications, IS management, physical, personnel, continuity)
• RSSI, DPO, DSI, and FSSI roles
• Review cycle and integration with EBIOS and homologation

/arckit:fr-dr → Diffusion Restreinte (DR) handling compliance

Assess document and IS handling requirements under the DR administrative classification:

• II 901/SGDSN rules for DR document lifecycle
• Electronic storage, transmission, and physical handling obligations
• IS homologation for DR-processing systems
• Scope explicitly bounded: DR only — IGI 1300 (Secret or Très Secret) is out of scope

/arckit:fr-algorithme-public → French Public Algorithm Transparency Notice

Generate mandatory transparency notice under CRPA Art. L311-3-1:

• Scope determination: which automated decisions are covered
• Plain-language description per algorithm, parameters, and weights
• Human oversight mechanisms and appeal rights
• GDPR Art. 22 intersection (automated individual decisions)
• EU AI Act flagging for ML-based systems
• More legally binding than the UK ATRS equivalent

/arckit:fr-code-reuse → French Public Code Reuse Assessment (Circulaire 2021-1524)

Assess code reuse obligations before building or procuring:

• code.gouv.fr search (French public code catalogue)
• SILL (Socle Interministériel de Logiciels Libres) — ministerially recommended open source
• EU public code alternatives (Joinup, European Commission repositories)
• Licence compatibility matrix (EUPL-1.2 recommended for public code publication)
• Decision matrix: reuse / fork / SILL adoption / procure / build
• Circulaire 2021 publication obligation: modified public code must be released back

---

Phase 15: Project Story & Reporting

/arckit:story → Generate comprehensive project story

Create narrative historical record with complete timeline analysis:

• Timeline Analysis: 4 visualization types (Gantt chart, linear flowchart, detailed table, phase duration pie chart)
• Timeline Metrics: Project duration, velocity, phase analysis, critical path identification
• Complete Timeline: All events from git log or file modification dates with days-from-start
• 8 Narrative Chapters: Foundation → Business Case → Requirements → Research → Procurement → Design → Delivery → Compliance
• Traceability Demonstration: End-to-end chains with Mermaid diagrams showing stakeholder → goals → requirements → stories → sprints
• Governance Achievements: Showcase compliance (TCoP, Service Standard, NCSC CAF), risk management, decision rationale
• Strategic Context: Wardley Map insights, build vs buy decisions, vendor selection rationale
• Lessons Learned: Pacing analysis, timeline deviations, recommendations for future projects
• Comprehensive Appendices: Artifact register, chronological activity log, DSM, command reference, glossary

When to use: At project milestones or completion to create shareable story for stakeholders, leadership, or portfolio reporting. Perfect for demonstrating systematic governance and ArcKit workflow value.

/arckit:presentation → Generate MARP slide deck from project artifacts

Create presentation slides from existing architecture artifacts:

• MARP Format: Markdown-based slides with --- separators — exports to PDF, PPTX, or HTML
• Focus Modes: Executive (board-level), Technical (architecture detail), Stakeholder (benefits-focused), Procurement (RFP briefings)
• Artifact-Driven: Reads all available project artifacts and extracts key content into slides
• Mermaid Diagrams: Gantt charts, C4 diagrams, pie charts, and quadrant charts embedded natively
• Configurable: Choose slide count (6-8, 10-12, 15-20) and MARP theme (default, gaia, uncover)
• Doc type code: PRES

When to use: Before governance boards, stakeholder briefings, gate reviews, or quarterly portfolio presentations. Run after creating most project artifacts for the richest slide deck.

Phase 16: Documentation Publishing

/arckit:pages → Generate documentation site

Publish all project documentation as an interactive website:

• Static Site Generation: Generates docs/index.html and docs/manifest.json — deployable to any static host (GitHub Pages, Netlify, Vercel, S3, etc.)
• Mermaid Diagram Rendering: All architecture diagrams render inline with mermaid.js
• Project Navigation: Sidebar with collapsible project tree, document categories, and version badges — documents with multiple versions show an inline dropdown selector
• GOV.UK Styling: Professional government design system styling
• Document Index: Manifest.json provides programmatic access to all artifacts
• LLM Discovery: Generates docs/llms.txt (llmstxt.org format) so LLM agents and crawlers can index every artifact, guide, and project. Hand-curated docs/llms.txt files (without the ArcKit generation marker) are preserved on re-runs

When to use: When you want to share project documentation with stakeholders via a professional web interface, or to create a portfolio view of all architecture artifacts.

---

Supported AI Assistants

Platform Support: ArcKit is developed and tested on Linux. Windows has limited support — hooks (session init, project context, filename validation, MCP auto-allow) require bash and jq which are not available on stock Windows. For the best experience on Windows, use a devcontainer or WSL2.

Why Claude Code?

Claude Code is the primary development platform for ArcKit and provides capabilities not available in other formats:

Agents run research-heavy commands (market research, data source discovery, cloud service evaluation) in isolated context windows, keeping the main conversation clean and enabling dozens of WebSearch/WebFetch/MCP calls without context bloat.

Hooks provide automated governance: filenames are auto-corrected to ArcKit conventions, project context is injected into every prompt so commands know what artifacts exist, MCP tools are auto-approved, and generated outputs like Wardley Maps are validated for mathematical consistency before being finalized.

Gemini CLI provides a strong experience with all commands and MCP servers but lacks agent delegation and hooks. GitHub Copilot provides all 76 official commands as prompt files and 10 custom agents but lacks hooks and MCP servers. Codex CLI and OpenCode CLI provide core command functionality but require manual setup and arckit init scaffolding.

Why Commands, Not Skills

Claude Code automatically exposes ArcKit commands as skills (they appear in the skills list and can be matched by natural language). ArcKit intentionally uses slash commands rather than standalone skills because:

• Deliberate invocation required — Every command generates a heavyweight governance document (requirements spec, risk register, DPIA, etc.). Auto-triggering from conversational intent would waste significant time and tokens.
• Dependency ordering — Commands follow a deliberate sequence (principles → stakeholders → requirements → data-model → etc.). Skills that auto-trigger could run out of order.
• User input via $ARGUMENTS — Most commands accept context from the user (project name, scope, constraints). The command system handles this with $ARGUMENTS substitution.
• Best of both worlds — Since Claude Code exposes commands as skills automatically, users get explicit /arckit:requirements invocation AND natural language matching when Claude recognises intent — no restructuring needed.

Using with GitHub Copilot

For GitHub Copilot users in VS Code, ArcKit commands are delivered as prompt files and custom agents:

# Install and create project (3 steps, zero config)
pip install git+https://github.com/tractorjuice/arc-kit.git
arckit init my-project --ai copilot
cd my-project && code .

# Then use ArcKit commands in Copilot Chat
/arckit-principles Create principles for financial services
/arckit-stakeholders Analyze stakeholders for cloud migration
/arckit-requirements Create comprehensive requirements

This creates .github/prompts/arckit-*.prompt.md, .github/agents/arckit-*.agent.md (10 custom agents), and .github/copilot-instructions.md (repo-wide context).

Using with Codex CLI

For OpenAI Codex CLI users, ArcKit commands are delivered as skills and auto-discovered:

# Install and create project (3 steps, zero config)
pip install git+https://github.com/tractorjuice/arc-kit.git
arckit init my-project --ai codex
cd my-project && codex

# Then use ArcKit skills
$arckit-principles Create principles for financial services
$arckit-stakeholders Analyze stakeholders for cloud migration
$arckit-requirements Create comprehensive requirements

See .codex/README.md for full Codex CLI setup and usage.

Project Structure

ArcKit creates this structure:

payment-modernization/
├── .arckit/
│   ├── scripts/
│   │   └── bash/                          # Automation scripts
│   ├── templates/                         # Default templates (refreshed by arckit init)
│   └── templates-custom/                  # Your customizations (preserved across updates)
├── projects/
│   ├── 000-global/
│   │   └── ARC-000-PRIN-v1.0.md          # Global principles
│   └── 001-payment-gateway/
│       ├── ARC-001-STKE-v1.0.md           # Stakeholder analysis
│       ├── ARC-001-RISK-v1.0.md           # Risk register (Orange Book)
│       ├── ARC-001-SOBC-v1.0.md           # Strategic Outline Business Case
│       ├── ARC-001-REQ-v1.0.md            # Comprehensive requirements
│       ├── ARC-001-DATA-v1.0.md           # Data model with ERD, GDPR compliance
│       ├── wardley-maps/                   # Strategic Wardley Maps
│       │   ├── ARC-001-WARD-001-v1.0.md   # Current architecture positioning
│       │   ├── ARC-001-WARD-002-v1.0.md   # Target architecture vision
│       │   ├── ARC-001-WARD-003-v1.0.md   # Gap analysis
│       │   └── ARC-001-WARD-004-v1.0.md   # Build vs buy decisions
│       ├── ARC-001-SOW-v1.0.md            # Statement of Work (RFP)
│       ├── ARC-001-EVAL-v1.0.md           # Vendor evaluation framework
│       ├── vendors/
│       │   ├── acme-corp/
│       │   │   ├── proposal.pdf
│       │   │   ├── scoring.md
│       │   │   ├── hld-v1.md
│       │   │   └── reviews/
│       │   │       └── hld-v1-review.md
│       │   ├── beta-systems/
│       │   │   └── ...
│       │   └── comparison.md
│       ├── ARC-001-SNOW-v1.0.md           # Service management design
│       ├── ARC-001-TRAC-v1.0.md           # Traceability matrix
│       └── final/
│           ├── selected-vendor.md
│           ├── approved-hld.md
│           └── dld/
├── .agents/skills/                        # Codex CLI skills (auto-discovered)
├── .codex/
│   ├── agents/                            # Agent configs
│   └── config.toml                        # MCP servers + agent roles
├── .github/
│   ├── prompts/arckit-*.prompt.md         # GitHub Copilot prompt files (70 official + community overlays)
│   ├── agents/arckit-*.agent.md           # GitHub Copilot custom agents (10 agents)
│   └── copilot-instructions.md            # Repo-wide Copilot context
└── .opencode/commands/                    # OpenCode CLI commands

---

Template Customization

Customize ArcKit templates without modifying defaults:

# Inside your AI assistant
/arckit:customize requirements   # Copy requirements template for editing
/arckit:customize all            # Copy all templates
/arckit:customize list           # See available templates

How it works:

• Default templates live in .arckit/templates/ (refreshed by arckit init)
• Your customizations go in .arckit/templates-custom/ (preserved across updates)
• Commands automatically check for custom templates first, falling back to defaults

Common customizations:

• Add organization-specific document control fields
• Include mandatory compliance sections (ISO 27001, PCI-DSS)
• Add department-specific approval workflows
• Customize UK Government classification banners

---

Complete Command Reference

Core ArcKit commands with maturity status and example outputs from public test repositories.

Status Legend

Example Repositories

Foundation

Interoperability

Strategic Context

Requirements & Data

Research & Strategy

Cloud Research (MCP)

These commands use Model Context Protocol (MCP) servers to access authoritative cloud provider documentation in real-time. The Claude Code plugin bundles both MCP servers automatically. Gemini and Codex users need to install them separately.

Data Source Discovery

Note: The Google Developer Knowledge MCP requires an API key (GOOGLE_API_KEY environment variable). See the GCP Research guide for setup instructions.

Procurement Market Intelligence

Note: /arckit:tenders and /arckit:competitors both use the bundled uk-tenders MCP server (keyless, deferred) via the shared arckit-tenders-reader subagent. Data: ~677,000 UK contracting processes across FTS, Contracts Finder, Public Contracts Scotland, Sell2Wales, and eTendersNI; nightly refresh; best-effort availability (no formal SLA). /arckit:tenders outputs a TNDR artefact (market-wide benchmarks, incumbency, concentration). /arckit:competitors outputs a CMPT artefact (rival-supplier landscape, market-share ranking, head-to-head).

Government Code Discovery

These commands use the govreposcrape MCP server to search 24,500+ UK government repositories. The Claude Code plugin bundles the MCP server automatically. No API key required.

Procurement

Design & Architecture

Operations

Quality & Governance

UK Government

UK MOD

Documentation & Publishing

---

Wardley Mapping for Strategic Architecture

ArcKit uses Wardley Maps to expose the strategic position of every component before you commit to a solution. The /arckit:wardley command produces ready-to-visualise maps that:

• Trace user needs through the supporting value chain so gaps and duplicated effort are obvious.
• Plot evolution from Genesis → Commodity to reveal when to build, buy, reuse, or retire capabilities.
• Feed procurement, vendor evaluation, and design reviews with shared situational awareness.

Maps are emitted in the Open Wardley Map format — paste them straight into https://create.wardleymaps.ai for a visual view. Full example outputs live in the public demos such as arckit-test-project-v3-windows11 (enterprise OS rollout strategy) and arckit-test-project-v14-scottish-courts (GenAI platform strategy).

---

Architecture Diagrams with Mermaid

ArcKit generates visual architecture diagrams using Mermaid for clear technical communication.

What are Architecture Diagrams?

Architecture diagrams visualize system structure, interactions, and deployment for:

• Technical Communication: Share architecture with stakeholders
• Design Documentation: Document current and future state
• Vendor Evaluation: Compare vendor technical approaches
• UK Government Compliance: Visualize Cloud First, GOV.UK services, PII handling

Diagram Types

ArcKit supports 6 essential diagram types based on the C4 Model and enterprise architecture best practices:

Use /arckit:diagram directly, or supply an explicit type such as context, container, sequence, or dataflow. Outputs bundle component inventories with Wardley evolution tags, built-in GOV.UK compliance scaffolding (Notify, Pay, Design System), Cloud First network patterns, GDPR annotations, and traceability back to requirements and tests. For full examples, browse the diagram folders in arckit-test-project-v3-windows11 and arckit-test-project-v14-scottish-courts.

ServiceNow Service Management Design

ArcKit turns architecture artefacts into an operations-ready ServiceNow pack. The /arckit:servicenow command builds:

• CMDB hierarchies, SLAs, and change risk straight from requirements, diagrams, and Wardley Maps.
• ITIL-aligned runbooks covering incident, change, monitoring, and transition activities.
• UK government extras such as GDS Service Standard, Technology Code of Practice, and GOV.UK Pay/Notify dependencies when relevant.

For full outputs, explore the public demos (for example arckit-test-project-v3-windows11) where the generated ServiceNow design files and checklists are published end-to-end.

---

Documentation

Key references live in docs/ and top-level guides:

• Quick tour: docs/index.html mirrors the public landing page.
• Lifecycle visuals: WORKFLOW-DIAGRAMS.md and DEPENDENCY-MATRIX.md cover command flow and relationships.
• Core guides: docs/guides/principles.md, docs/guides/requirements.md, docs/guides/procurement.md, docs/guides/design-review.md.
• Traceability: docs/guides/traceability.md documents end-to-end coverage patterns.
• DDaT Role Guides: docs/guides/roles/ — 18 guides mapping ArcKit commands to UK Government DDaT Capability Framework roles (Enterprise Architect, Solution Architect, Product Manager, etc.).

---

Comparison to Other Tools

Every tool here now has AI features. Sparx has Kernaro AI and an MCP server, Ardoq relaunched as AI-first in May 2026, LeanIX ships an AI assistant and an MCP server, and Confluence has Atlassian Rovo. The difference is what the AI works on. The EA platforms apply it to the application inventory: what exists and how it connects. ArcKit applies it to the governance evidence: the documents an assessment, a design authority or a procurement asks for. They work well together, since ArcKit can read an export from your EA repository as source material.

---

Requirements

• Python 3.11+
• Git (optional but recommended)
• AI Coding Agent: Claude Code v2.1.287+ (via plugin), Gemini CLI (via extension), OpenCode CLI (via CLI), or OpenAI Codex CLI (via CLI)
• uv for package management: Install uv

---

Installation from Source

# Clone the repository
git clone https://github.com/tractorjuice/arc-kit.git
cd arc-kit

# Install in development mode
pip install -e .

# Run the CLI
arckit init my-project

---

Documentation

Full guidance lives in docs/ and the static site.

• Quick tour: docs/index.html (mirrors the public landing page).
• Core guides: docs/guides/principles.md, docs/guides/requirements.md, docs/guides/procurement.md, docs/guides/design-review.md.
• Reference packs: WORKFLOW-DIAGRAMS.md and DEPENDENCY-MATRIX.md cover lifecycle visualisations and the command dependency matrix.
• Traceability: docs/guides/traceability.md documents end-to-end requirements coverage.

Relationship to Spec Kit

ArcKit is inspired by Spec Kit but targets a different audience:

---

Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

Areas we need help:

• Integration with enterprise tools (Jira, Azure DevOps)
• Additional AI agent support
• Template improvements based on real-world usage
• Documentation and examples
• ServiceNow API integration for automated CI creation

---

Tips

Continuous Governance Monitoring

Use the /loop command to run health checks on a recurring interval during long architecture sessions:

/loop 30m /arckit:health SEVERITY=HIGH

This runs /arckit:health every 30 minutes, surfacing stale research, forgotten ADRs, and unresolved review conditions as they appear.

---

Troubleshooting

Token Limit Error

If you see: API Error: Claude's response exceeded the 32000 output token maximum

The Problem: ArcKit generates large documents that can exceed Claude's 32K token output limit.

⚠️ IMPORTANT: Your Claude subscription plan determines the maximum tokens:

• 🔴 Free/Pro plans: 32K max (cannot be increased)
• ✅ Team/Enterprise plans: Can increase to 64K via environment variable

Solutions:

1. For Team/Enterprise plans - Increase token limit:

   export CLAUDE_CODE_MAX_OUTPUT_TOKENS=64000
   

2. For ALL plans (including Free/Pro) - Use Write tool strategy:

   User: /arckit:requirements but write directly to file using Write tool, show me only a summary
   

   This tells Claude to use the Write tool to create the file (doesn't count toward output tokens) and only show you a summary.

Which commands are affected?

• 🔴 HIGH RISK: /arckit:sobc, /arckit:requirements, /arckit:data-model, /arckit:sow
• 🟢 MITIGATED (agent): /arckit:research, /arckit:datascout, /arckit:tenders, /arckit:competitors, /arckit:aws-research, /arckit:azure-research, /arckit:gcp-research, /arckit:gov-reuse, /arckit:gov-code-search, /arckit:gov-landscape, /arckit:grants — run as autonomous agents in separate context windows
• 🟡 MEDIUM RISK: /arckit:risk, /arckit:evaluate, /arckit:principles

See full guide: docs/TOKEN-LIMITS.md

Common Issues

Command not found: Ensure commands are available

# For Codex, check if skills directory exists
ls .agents/skills/arckit-principles/SKILL.md

# For Claude Code, install the ArcKit core plugin:
# /plugin marketplace add tractorjuice/arckit-claude

# For Gemini CLI, install the ArcKit extension:
# gemini extensions install https://github.com/tractorjuice/arckit-gemini

# For GitHub Copilot, check if prompt files exist
ls .github/prompts/arckit-*.prompt.md

# For OpenCode CLI, check if commands directory exists
ls .opencode/commands/

Template not found: Ensure you've run /arckit:principles first

# Check if templates exist
ls templates/

Project creation fails: Ensure you have an ArcKit repository initialized

# Initialize if needed
arckit init .

---

Support

• Issues: GitHub Issues
• Releases: GitHub Releases
• Latest Version: v6.18.2

---

License

MIT License - see LICENSE for details.

Exception: the plugins/arckit-uk-gcloud/ overlay is proprietary (not MIT) — see plugins/arckit-uk-gcloud/LICENSE.

---

Acknowledgements

ArcKit is inspired by the methodology and patterns from Spec Kit, adapted for enterprise architecture governance workflows.

---

Built with ❤️ for enterprise architects who want systematic, AI-assisted governance.