# Add marketplace (one time)
claude plugin marketplace add fcakyon/claude-codex-settings

# Install any plugin by name
claude plugin install fable-advisor@claude-settings

In Claude Code desktop, select + beside the prompt, then Plugins and Add plugin.

# Add marketplace (one time)
codex plugin marketplace add fcakyon/claude-codex-settings

# Install any plugin by name
codex plugin add simplify@claude-settings

In the Codex desktop app, open Plugins, find the plugin, and select Install.

# Install any plugin by name
gemini extensions install --path ./plugins/simplify

# Add marketplace (one time)
cursor-agent plugin marketplace add https://github.com/fcakyon/claude-codex-settings

# Start the interactive CLI
cursor-agent

Enter /plugin, open the marketplace, and install the plugin at user or project scope. In the Cursor app, open Customize and select Install.

Run /simplify to review your staged or committed diff across four angles (reuse, simplification, efficiency, altitude) with parallel agents, then apply the cleanups. It reviews changed-code quality, not correctness bugs. It brings Claude Code's built-in /simplify to Codex, Cursor, and Gemini, which don't ship it natively, so all three get the same review and apply flow.

Skills:

• simplify - review the changed diff across four angles and apply the fixes

Hooks:

• guard.py - Require a completed /simplify run before each Claude Code or Codex commit, unless you explicitly ask to skip it for one commit

Before a Write or Edit saves, humanize scans the new text and blocks whatever reads like a machine wrote it, each hit paired with a plain-word swap. It reads Markdown files whole and checks comments and docstrings in code files while skipping source code and recognized code-shaped references:

• 3 marks: the em-dash, section sign, and stray semicolon (the en-dash stays)
• 53 stock words like leverage, seamlessly, vibrant, game-changing, each mapped to a plain swap
• 16 openers and cliches like in conclusion, a testament to, aims to bridge
• 10 pile-up words like crucial or significant, flagged at 3+ uses in one write

Runs on Claude Code and Gemini. Unlike a markdown rule the model can ignore, the hook checks every Write or Edit and blocks each match until it is replaced. The word list draws on Wikipedia's "Signs of AI writing".

Skills (ZIP for claude.ai, ChatGPT, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
humanize	Avoid common AI writing patterns with examples

Hooks:

• humanize.py - blocks matched marks, buzzwords, and cliches before a Write or Edit lands

Ask a Fable 5.1 reviewer to challenge a plan or conclusion before you commit. Claude Code uses the native plugin agent, while Codex, Cursor, and Gemini call the same model through an authenticated Claude Code CLI with claude -p --model claude-fable-5-1.

Agents:

• fable-advisor - Native Claude Code reviewer with recent conversation context

Skills:

• fable-advisor - Routes Claude Code to its native agent and other tools to claude -p

Ask GPT-6 Astra to challenge a plan before you build it, the cross-model check the built-in advisor cannot give you. Claude Code attaches the recent conversation, so "ask the codex advisor" is enough. Codex, Cursor, and Gemini reach the same reviewer. Needs the Codex CLI signed in.

Agents:

• codex-advisor - Sends the recent conversation to GPT-6 Astra and returns the verdict verbatim

Skills:

• codex-advisor - Routes Claude Code to its native agent and other tools to codex exec

Cuts filler and keeps output token use down with the answer or next step first, one-action-per-step lists, concrete time estimates, a single under-two-minute next action, and short teaching notes while coding. Claude Code applies the output style automatically. Codex, Cursor, and Gemini CLI expose the same instructions as an adhd-output-style skill because they do not support plugin output styles.

Output styles:

• ADHD Explanatory - Low-token ADHD formatting plus educational Insight blocks while coding

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
adhd-output-style	Apply the same reply format in Codex, Cursor, and Gemini CLI

When Claude Code auto-summarizes a long session, the default summary routinely drops the highest-signal facts. This plugin tells the summarizer to keep them:

• File paths under investigation so the next turn doesn't re-discover where you were
• Confirmed root causes so you don't re-debug what's already solved
• Open questions, metrics, and IDs that prose summaries usually round away
• Findings from expensive subagent runs that took minutes to gather

Runs on every /compact (manual) and every auto compaction. Claude Code only; Codex, Cursor, and Gemini CLI don't yet expose a comparable summary hook.

Hooks:

• precompact_priorities.sh - Priority-preservation instructions for the compaction summarizer

Adds the two missing pieces Claude Code's telemetry needs to power a usage dashboard:

• Sticky session ID per project: resumed conversations stay one session, not dozens
• Categorized rejection reasons (profanity, wrong target, scope drift, retry, and more): chart why Claude pushes back

Per-device data is already in Claude Code's built-in OpenTelemetry stream. Pairs naturally with openobserve-skills for the dashboard side.

Hooks:

• session_start_chat_id.py - SessionStart hook that emits a sticky per-project chat_id
• user_prompt_reject_feedback.py - UserPromptSubmit hook that categorizes tool-rejection reasons

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/anthropic-office-skills --skill '*'

Official office document skills from anthropics/skills.

Skill	Description	Install
pdf	PDF processing (read, merge, split, create, OCR, forms)
pptx	PowerPoint presentation building and editing
xlsx	Excel spreadsheet processing with formulas
docx	Word document creation and editing

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/openai-office-skills --skill '*'

Office document skills for creating and editing PDFs, Word documents, slide decks, and spreadsheets.

Skill	Description	Install
pdf	PDF generation and extraction with visual review
slides	Slide deck creation with PptxGenJS
spreadsheet	Spreadsheet processing with formulas and formatting
doc	Word document creation and editing

Python coding guidelines grounded in authoritative sources: PEP 8, PEP 20 (Zen of Python), Google Python Style Guide, and Brett Slatkin's "Effective Python" (3rd ed.). Covers code integration, idiomatic patterns, YAGNI anti-abstraction rules, Google-style docstrings, and 18 before/after code examples.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
python-guidelines	Core rules, self-tests, and reference index

Reference files:

• zen-of-python.md - Full PEP 20 with annotations
• google-style-guide.md - Curated sections with source URLs
• idiomatic-patterns.md - 18 patterns with before/after code
• effective-python-tips.md - Key tips from 3rd edition

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/react-skills --skill '*'

React and frontend best practices from vercel-labs/agent-skills.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
composition-patterns	React composition patterns: compound components, render props, context
react-best-practices	64 React/Next.js performance rules from Vercel Engineering
react-native-skills	35+ React Native/Expo rules for performance and animations
react-view-transitions	View Transition API for page/route animations
web-design-guidelines	UI review against 16 web interface guideline categories

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/agent-browser --skill '*'

Browser automation via CLI instead of MCP. 93% less context usage than Playwright MCP by using snapshot + element refs instead of full DOM tree dumps. From vercel-labs/agent-browser.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
agent-browser	Browser automation: navigation, forms, clicking, screenshots, auth, sessions
electron	Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion)
derive-client	Build a direct API client from a site's recorded browser traffic
dogfood	Explore a web app to find bugs and UX issues
webmcp-gen	Expose a page's workflows as WebMCP tools

CLI Tool: agent-browser - install via npm i -g agent-browser && agent-browser install

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/frontend-design-skills --skill '*'

Frontend design and writing skills from anthropics/claude-plugins-official, openai/plugins, and vercel-labs/writing-guidelines.

Skill	Description	Install
openai-frontend-design	Composition-first design: restrained layout, image-led hierarchy, tasteful motion
anthropic-frontend-design	Bold aesthetic direction, distinctive typography, anti-generic AI aesthetics
writing-guidelines	Review interface copy and text for clear, consistent writing

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/mongodb-skills --skill '*'

Official MongoDB agent skills for schema design, query tuning, Atlas Search, and connections. From mongodb/agent-skills.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
mongodb-atlas-stream-processing	Atlas stream processing patterns
mongodb-connection	Connection management
mongodb-mcp-setup	MCP server setup
mongodb-natural-language-querying	Natural language to queries
mongodb-query-optimizer	Query performance tuning
mongodb-schema-design	Schema design patterns
mongodb-search-and-ai	Atlas Search and AI integration

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/supabase-skills --skill '*'

Supabase skills covering Postgres query/schema best practices from supabase/agent-skills, JavaScript SDK usage from supabase/supabase-js, and CLI workflows from supabase/cli.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
supabase-postgres-best-practices	Postgres performance and schema design across 8 categories
supabase-js	JavaScript SDK for auth, database, storage, realtime, edge functions
supabase-cli	CLI for local dev, migrations, edge functions, project management
supabase	Supabase security, RLS, CLI, and schema change workflow

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/stripe-skills --skill '*'

Official Stripe agent skills for payment integration: API selection, Connect platform setup, billing/subscriptions, Treasury, and SDK upgrades. From stripe/ai.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
stripe-best-practices	Payments, billing, Connect, Treasury integration best practices
stripe-projects	Stripe Projects CLI setup and stack provisioning
upgrade-stripe	Stripe API version and SDK upgrade guide
connect-recommend	Choose a Stripe Connect setup for marketplaces and platforms
connect-required-verification-information	Connected account verification and KYC requirements
metronome	Usage-based billing with Metronome
stripe-apps	Build and review Stripe Apps
stripe-docs	Look up Stripe docs and API reference

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/polar-skills --skill '*'

Official Polar agent skills for billing system, Stripe integration, subscription lifecycle, and local dev with Docker. From polarsource/polar.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
polar-billing	Polar billing system, Stripe integration, subscriptions, benefit provisioning
polar-local-environment	Polar local development environment with Docker

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/livekit-skills --skill '*'

Voice AI agent development with the LiveKit Agents SDK, from design and live testing to simulations and production. Works with LiveKit Cloud or a self-hosted server, and looks up current docs with the lk CLI when no docs server is connected. Based on livekit/agent-skills, patched so the Cloud-only parts also cover self-hosting.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
building-livekit-agents	Structure voice agents: latency, context size, handoffs and tasks
debugging-livekit-agents	Drive a local conversation with the agent and read its tool calls
operating-livekit-agents	Deploy, roll back, and keep a live agent fast and stable
reading-livekit-docs	Look up current LiveKit APIs, CLI flags, and changelogs
running-livekit-simulations	Run whole-conversation simulations before shipping
testing-livekit-agents	Write turn-level agent tests with pytest or Vitest
writing-livekit-scenarios	Write and maintain the scenarios simulations run

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/cloudflare-skills --skill '*'

Choose the Cloudflare services your project needs, then load the relevant specialist skill. From cloudflare/skills.

• Includes Workers, Wrangler, Durable Objects, Agents SDK, Sandbox, and Turnstile guidance.
• Covers Next.js deployment, email, Zero Trust, migrations, and web performance.
• Keeps detailed references inside each skill so they are read only when needed.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
cloudflare-deploy	Cloudflare platform: compute, storage, AI, networking, security
agents-sdk	Build applications with the Agents SDK
basin	Stream, catalog, and query analytics data in R2
cloudflare-email-service	Configure email sending and routing
cloudflare-one	Configure Zero Trust and SASE
cloudflare-one-migrations	Plan migrations to Cloudflare One
durable-objects	Build persistent state and coordination
k2	Build durable logs with K2 Streams
nextjs-on-cloudflare	Deploy Next.js with vinext
sandbox-migrate-to-next	Migrate Sandbox stable to preview
sandbox-next	Build with the Sandbox preview SDK
sandbox-stable	Maintain stable Sandbox applications
turnstile-spin	Set up and verify Turnstile
web-perf	Audit loading and interaction performance
workers-best-practices	Write and review production Workers
wrangler	Configure and operate the Wrangler CLI

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/web-performance-skills --skill '*'

Audit web page performance using Chrome DevTools MCP. Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. From cloudflare/skills.

Bundles the chrome-devtools MCP server (no API key needed).

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
web-performance-optimization	Core Web Vitals, Lighthouse, render-blocking, accessibility audits

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/openobserve-skills --skill '*'

Programmatic access to OpenObserve (Cloud or self-hosted) via the documented REST API. Covers:

• Auth and search: HTTP Basic auth, the search/SQL endpoint with microsecond timestamps
• Streams and dashboards: stream listing/schema, dashboard CRUD, the v8 panel JSON schema
• Known pitfalls: the customQuery re-aggregation bug that doubles table rows when fields.y carries an aggregationFunction

Built for AI agents: uses curl only, no SDK or CLI dependency. Pairs naturally with claude-telemetry-hooks for Claude Code usage dashboards. Reference docs are mirrored from openobserve/openobserve-docs.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
openobserve-api	Search SQL, streams, dashboards, panel schema, ingestion endpoints, common pitfalls

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/hetzner-skills --skill '*'

Hetzner Cloud infrastructure management via the hcloud CLI. Decision trees for compute, networking, storage, DNS, and common deploy workflows. Reference docs extracted from hetznercloud/cli.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
hetzner-deploy	Servers, networks, firewalls, load balancers, DNS, volumes, storage

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/dokploy-skills --skill '*'

Dokploy Cloud and self-hosted dashboard workflows from Dokploy/website, plus a compact CLI command index generated from Dokploy/cli.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
dokploy-deploy	Dokploy Cloud, self-hosted dashboard, Docker Compose, databases, domains, remote servers, CLI index

Best-of bundle from anthropics/claude-plugins-official. Cherry-picks skills, agents, and commands from multiple upstream plugins.

Skills:

• claude-md-improver - Audit and improve CLAUDE.md files across a codebase
• skill-creator - Create, improve, and benchmark Agent Skills with eval testing

Agents:

• code-architect - Architecture design from codebase patterns
• code-explorer - Deep codebase exploration and analysis
• code-reviewer - Code quality and review

Commands:

• /feature-dev - Guided feature development workflow
• /revise-claude-md - Capture session learnings into CLAUDE.md

Hooks:

• Stop (prompt) - Suggest CLAUDE.md updates after significant code changes
• SessionEnd (prompt) - Remind to capture learnings when session ends

Actively maintained plugin development toolkit from anthropics/claude-plugins-official. 7 skills, 3 agents, and guided plugin creation.

Skills: hook-development, mcp-integration, plugin-structure, plugin-settings, command-development, agent-development, skill-development

Agents: agent-creator, plugin-validator, skill-reviewer

Commands: /create-plugin - Guided plugin workflow

Academic research toolkit from fcakyon/phd-skills. Experiment design, literature review, paper writing, citation verification, and reviewer defense for PhD workflows.

Skills:

• dataset-curation - Dataset preparation and annotation guidelines
• experiment-design - Experiment setup and ablation planning
• latex-setup - LaTeX project configuration
• literature-research - Literature search and review
• paper-verification - Citation and claim verification
• paper-writing - Academic paper drafting
• research-publishing - Submission and publishing workflow
• reviewer-defense - Reviewer response preparation

Agents:

• experiment-analyzer - Analyze experiment results and suggest next steps
• paper-auditor - Audit paper for consistency and completeness

Commands:

• /factcheck - Verify citations and claims
• /fortify - Strengthen paper against reviewer critiques
• /gaps - Find gaps in literature coverage
• /setup - Configure phd-skills
• /xray - Deep analysis of a paper

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/github-dev --skill '*'

Git and GitHub automation. Run the setup skill after install.

Agents:

• commit-creator - Intelligent commit workflow
• pr-creator - Pull request creation
• pr-reviewer - Code review agent
• pr-comment-resolver - PR comment resolution

Skills:

• commit-staged - Commit staged changes and write the message
• create-pr - Create a pull request from the full branch diff
• review-pr - Review a pull request for bugs and regressions
• resolve-pr-comments - Address unresolved PR review comments
• update-pr-summary - Update the PR title and description
• clean-gone-branches - Clean local branches deleted from remote
• setup - Configure GitHub CLI

Hooks:

• git_commit_confirm.py - Confirmation before git commit
• gh_pr_create_confirm.py - Confirmation before gh pr create
• block_ai_attribution.py - Block AI attribution lines in commits and PRs
• block_commit_type.py - Block commit types outside the allowed set

Ultralytics Platform API flows and YOLO26 training know-how, plus auto-formatting hooks for Python, JavaScript, Markdown, and Bash and a guard that blocks force-push and rebase.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
ultralytics-platform	Platform API: uploads, training, hosted inference, Moondream and AI annotation
yolo-training	YOLO26 training diagnosis: read the curves, pick the knob

Hooks:

• format_python_docstrings.py - Google-style docstring formatter
• python_code_quality.py - Python code quality with ruff
• prettier_formatting.py - JavaScript/TypeScript/CSS/JSON
• markdown_formatting.py - Markdown formatting
• bash_formatting.py - Bash script formatting
• block_force_push.py - Block force-push and rebase

Install ruff and prettier first (setup).

Official colors, Archivo typography, logo and naming rules, tone of voice, and per-format defaults from ultralytics.com/brand for PDF/PPTX/Canva decks, DOCX documents, marketing email HTML, social posts, and web designs.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
ultralytics-branding	Brand colors, fonts, logo, naming, tone, format defaults

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/azure-tools --skill '*'

40+ Azure services with Azure CLI authentication. Run /azure-tools:setup after install.

Skills:

• azure-usage - Best practices for Azure
• setup - Troubleshooting guide

Commands:

• /azure-tools:setup - Configure Azure MCP

MCP: .mcp.json | microsoft/mcp/Azure.Mcp.Server

Commands for syncing CLAUDE.md and permissions allowlist from repository, plus context refresh for long conversations.

Commands:

• /load-claude-md - Refresh context with CLAUDE.md instructions
• /sync-claude-md - Sync CLAUDE.md from GitHub
• /sync-allowlist - Sync permissions allowlist

Hooks:

• sync_marketplace_to_plugins.py - Syncs marketplace.json to plugin.json

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/gcloud-tools --skill '*'

Logs, metrics, and traces. Run /gcloud-tools:setup after install.

Skills:

• gcloud-usage - Best practices for GCloud Logs/Metrics/Traces
• setup - Troubleshooting guide

Commands:

• /gcloud-tools:setup - Configure GCloud MCP

MCP: .mcp.json | google-cloud/observability-mcp

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/paper-search-tools --skill '*'

Search papers, look up DOIs, download PDFs, and follow citations with Paper Search CLI. Run /paper-search-tools:setup after install. Requires uv and Python 3.10+; no Docker or MCP server.

Skills:

• paper-search-usage - Best practices for paper search
• setup - Troubleshooting guide

Commands:

• /paper-search-tools:setup - Install and verify Paper Search CLI

CLI: fcakyon/paper-search-cli

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/tavily-tools --skill '*'

Web search and content extraction. Run /tavily-tools:setup after install.

Skills:

• tavily-usage - Best practices for Tavily Search
• setup - Troubleshooting guide

Commands:

• /tavily-tools:setup - Configure Tavily MCP

Hooks:

• webfetch_to_tavily_extract.py - Redirect WebFetch to Tavily extract
• websearch_to_tavily_search.py - Redirect WebSearch to Tavily search
• tavily_extract_to_advanced.py - Upgrade Tavily extract depth

MCP: .mcp.json | tavily-ai/tavily-mcp

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/overleaf-skills --skill '*'

Pull reviewer comments from an Overleaf project, locate each in your local git-tracked *.tex files, and apply edits you review. Run setup once to paste your Overleaf session cookie; sessions slide ~5 days idle. Pairs naturally with github-dev for the commit step.

Skills:

• setup - Capture and refresh the Overleaf session cookie
• review-overleaf - Fetch unresolved review threads and apply edits to local .tex files

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/seo-skills --skill '*'

SEO workflows from vercel-labs/marketing-team-eve-template. Audit pages in evidence order, plan programmatic page sets, add valid JSON-LD, and improve hierarchy and internal linking. The schema skill includes a dependency-free Node validator for local JSON-LD checks.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
seo-audit	Prioritized technical, on-page, content, and credibility audit
programmatic-seo	Plan template-driven page sets without thin content
schema	Add and validate JSON-LD structured data
site-architecture	Plan hierarchy, navigation, URLs, and internal links

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/openship-skills --skill '*'

Deploy applications to your own OpenShip instance with guidance drawn from its official documentation and source code.

• Use native CLI commands first, with API calls for missing functionality.
• Design small openship.json files for builds, services, domains, and storage.
• Verify the active deployment and public URL after deployment.
• Keep server upgrades, backups, and restoration separate from application deploys.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
openship-deploy	Deploy and operate self-hosted OpenShip through the CLI
openship-config	Design and validate openship.json

References are tied to one upstream release. The two skills work together and can also be downloaded separately.

Skills CLI

npx skills add https://github.com/fcakyon/claude-codex-settings/tree/main/plugins/test-audit --skill '*'

The test review playbook from openclaw/openclaw, adapted to work in any repository.

• Before a new test lands, it must name the bug it catches and why existing tests miss it.
• Finds tests that copy source, mock the behavior they assert, or repeat a stronger test.
• Deletes test-only exports and dead code once their last test is gone.
• A campaign mode prunes a whole subsystem's tests with a per-test ledger and a final review for lost coverage.

Skills (ZIP for claude.ai, Claude Code, Cursor, Codex, VS Code):

Skill	Description	ZIP
test-audit	Gate new tests and prune low-value or duplicate ones

Configuration in .claude/settings.json:

• Model: Opus 5.5 with medium effort
• Environment: bash working directory, telemetry disabled, MCP output limits
• Permissions: bash commands, git operations, MCP tools
• Auto mode: auto permission mode with a custom autoMode classifier block in .claude/settings.json - see the auto mode config reference for what each rule section does, and run claude auto-mode defaults to print the current built-in block and allow rules
• Advisor: the built-in advisor tool uses Fable 5.1. For a review outside the Claude family, use codex-advisor
• Plugins: codex-advisor is enabled in both Claude Code and Codex. Claude Code also enables intelligent-compact. Standalone fable-advisor stays enabled only in Codex

Configuration in .claude/settings-zai.json using Z.ai GLM models via Anthropic-compatible API:

• Main model: GLM-5.3 with 1M context (dialogue, planning, coding, complex reasoning)
• Fast model: GLM-5.3-Flash (file search, syntax checking)
• Cost savings: much cheaper than frontier Claude models
• API key: Get from z.ai/model-api

For Codex CLI, see the recipe at .codex/config-zai.toml. Z.ai serves a Responses endpoint at /api/v1, so no local proxy is needed.

Run Claude Code with Kimi K3 via Anthropic-compatible API - source:

• Model: kimi-k3[1m] - native vision, thinking mode, 1M context
• Fast models: kimi-k2.7-code (sonnet), kimi-k2.6 (haiku) - cheaper 256K tiers
• API key: Get from platform.moonshot.ai

export ANTHROPIC_BASE_URL=https://api.moonshot.ai/anthropic
export ANTHROPIC_AUTH_TOKEN="your-moonshot-api-key"
export ANTHROPIC_MODEL="kimi-k3[1m]"
export ANTHROPIC_DEFAULT_OPUS_MODEL="kimi-k3[1m]"
export ANTHROPIC_DEFAULT_SONNET_MODEL="kimi-k2.7-code"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="kimi-k2.6"
export ANTHROPIC_DEFAULT_FABLE_MODEL="kimi-k3[1m]"
export CLAUDE_CODE_SUBAGENT_MODEL="kimi-k3[1m]"
export ENABLE_TOOL_SEARCH=false

Or use the settings file: .claude/settings-kimi.json

For Codex CLI, use Kimi K3 through the local Responses proxy in .codex/config-kimi.toml. The recipe uses Kimi Code model ID k3. Use k3-256k in both the proxy command and config when 256K context is enough.

Run Claude Code with MiniMax M3 via Anthropic-compatible API - source:

• Model: MiniMax-M3[1m] - 1M context window (512K guaranteed minimum, [1m] unlocks the full window)
• Fast model: MiniMax-M2.7-highspeed - high-throughput variant
• API key: Get from minimax.io

export ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic
export ANTHROPIC_AUTH_TOKEN="your-minimax-api-key"
export ANTHROPIC_MODEL=MiniMax-M3[1m]
export ANTHROPIC_DEFAULT_OPUS_MODEL=MiniMax-M3[1m]
export ANTHROPIC_DEFAULT_SONNET_MODEL=MiniMax-M3[1m]
export ANTHROPIC_DEFAULT_HAIKU_MODEL=MiniMax-M2.7-highspeed
export CLAUDE_CODE_AUTO_COMPACT_WINDOW=400000
export ENABLE_TOOL_SEARCH=false

Or use the settings file: .claude/settings-minimax.json

For Codex CLI, see the recipe at .codex/config-minimax.toml. Note that Codex requires a local Responses API proxy since MiniMax only exposes chat completions.

Configuration in ~/.codex/config.toml:

• Model: gpt-6.1-sol with model_reasoning_effort set to "medium"
• Sandbox: workspace-write with network access enabled
• Auto mode: the "Approve for me" option under /approvals, set by approvals_reviewer = "auto_review". A reviewer subagent judges each escalation against the [auto_review] policy block in .codex/config.toml instead of stopping to ask you, so it trades tokens for far fewer prompts. The policy mirrors the autoMode block in .claude/settings.json
• Plugins: a curated set enabled from this marketplace (simplify, github-dev, python-skills, and more)

Settings in .vscode/settings.json:

• GitHub Copilot: Custom instructions for automated commit messages and PR descriptions
• Python: Ruff formatting with auto-save and format-on-save enabled
• Terminal: Cross-platform compatibility configurations
• Thinking display: point claudeCode.claudeProcessWrapper at a small wrapper that forces --thinking-display summarized, so thinking tokens still show in the extension (works around 2.1.111+ dropping the flag)

#!/bin/bash
# Workaround for VS Code Claude Code extension 2.1.111+ not passing
# --thinking-display to the binary on Opus 4.7 (API default changed
# to "omitted", so thinking blocks arrive empty).
exec "$@" --thinking-display summarized