ARS-Codex

Languages: English · 简体中文 · 繁體中文 · 日本語

ARS-Codex is the Codex-native sibling of Academic Research Skills (ARS) for Claude Code. It is a separate Codex distribution with its own plugin identity, packaging, versioning, and runtime adapter.

This repository vendors the ARS workflow content as a single Codex skill:

skills/academic-research-suite/
  SKILL.md
  manifest.json
  agents/openai.yaml
  codex/
    full-runtime-manifest.json
    agents/
    hooks/
    scripts/
  ars/
    deep-research/
    academic-paper/
    academic-paper-reviewer/
    academic-pipeline/
    experiment-agent/
    commands/
    hooks/
    docs/
    tests/
    shared/

The original Claude Code ARS checkout is not modified. Upstream content is copied from fresh GitHub clones and adapted through the Codex router in skills/academic-research-suite/SKILL.md.

Relationship to Claude Code ARS

This repository is ARS-Codex. For the original Claude Code ARS distribution, use Imbad0202/academic-research-skills.

Use the Claude Code repo when you want the native Claude Code skill layout, Claude-specific agent-team behavior, or the original ARS development history. Use this repo when you want the Codex-native single-suite skill.

Versioning

This ARS-Codex package is version 0.1.28. The repo-root VERSION file, skills/academic-research-suite/SKILL.md metadata version, and skills/academic-research-suite/manifest.json adapter_version track the Codex package version independently of the vendored ARS suite. Vendored upstream versions are recorded by commit in manifest.source_repositories[].

Package-level changes are summarized in CHANGELOG.md.

The vendored ARS source currently tracks upstream main after the signed v3.21.1 release at Imbad0202/academic-research-skills@94436237913091d4739870159d241660527e8338 (2026-09-02; upstream suite metadata remains 3.21.1). This post-release snapshot adds Chinese-aware title matching and balanced CJK wrapper handling, declares the Markdown parser dependency used by surface-form checks, makes a missing PyYAML dependency fail visibly, and carries the September harness-retirement audit plus documentation corrections. The v3.21.1 research-workflow, inquiry-ledger, promotion-bakeoff, review-criteria, and consent boundaries remain unchanged. Nested upstream .github/ workflows and root agents/ mirrors are preserved for traceability and self-tests, but are not repo-level CI or Codex entrypoints; Claude/plugin loader files under .claude/ and .claude-plugin/ remain intentionally excluded.

Install ARS-Codex Plugin

Add the GitHub marketplace and install ARS-Codex with Codex CLI:

codex plugin marketplace add Imbad0202/academic-research-skills-codex --ref main
codex plugin add ars-codex@ars-codex

To update a plugin install later:

codex plugin marketplace upgrade ars-codex
codex plugin add ars-codex@ars-codex

In Codex Desktop, you can alternatively add the repository from Plugins and then install ARS-Codex:

Marketplace source: https://github.com/Imbad0202/academic-research-skills-codex.git
Branch/ref: main
Plugin: ars-codex

The plugin root is plugins/ars-codex/. Its skills/ directory contains a materialized copy of academic-research-suite, not a symlink. This keeps Codex Desktop installs portable on Windows, where plugin caches may materialize symlinks as plain text files and skip bundled skill registration.

Open a new Codex conversation after installation, then invoke $academic-research-suite or describe an academic research task that matches the bundled workflow.

Direct Skill Install Or Update

As an alternative to the plugin, install the skill directly from this repo path. Use --method git so public and credentialed GitHub access both work consistently:

python3 "$HOME/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py" \
  --repo Imbad0202/academic-research-skills-codex \
  --ref main \
  --path skills/academic-research-suite \
  --method git

On macOS and many Linux systems, Python 3 is exposed as python3 rather than python. If your system only has a python command and it is Python 3, use python in the commands instead.

To update an existing install:

rm -rf "$HOME/.codex/skills/academic-research-suite"
python3 "$HOME/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py" \
  --repo Imbad0202/academic-research-skills-codex \
  --ref main \
  --path skills/academic-research-suite \
  --method git

Open a new Codex conversation after installation. Existing Codex sessions may keep their old skill cache; you do not need to close unrelated Claude or Codex sessions.

Verify with /skills: you should see one ARS-Codex entry, academic-research-suite or ARS-Codex. You should not see separate academic-paper, academic-pipeline, deep-research, or academic-paper-reviewer skills from this package. If you do, reinstall with the update command above and open a new Codex conversation.

Codex Docs

• Codex setup covers installation, ars-* aliases, optional tools, Material Passport adapters, and unsupported Claude plugin features.
• Codex architecture explains the logical ARS pipeline with the Codex runtime overlay.
• Optional full-runtime adapter documents the disabled-by-default planner, Codex agent-team templates, and hook pack.

Usage

Invoke the suite explicitly with $academic-research-suite (singular), then describe the research task and provide any source files, notes, draft text, reviewer comments, or output constraints.

Use $academic-research-suite to help me plan a systematic literature review on
AI adoption in higher education quality assurance.

The Codex adapter routes the request to one of five ARS workflows:

Claude-Style Aliases

Claude Code v3.7 installs /ars-* slash commands. Codex does not have the same plugin command registry, so this package emulates the command intent inside the single $academic-research-suite skill. Use either form:

Use $academic-research-suite: ars-plan my paper on AI governance in universities.

or, when your Codex client passes slash-prefixed text through as a normal user message:

/ars-plan my paper on AI governance in universities.

If slash input is intercepted by the client, use the plain alias form:

ars-plan my paper on AI governance in universities.

Working Pattern

For best results, start with the workflow goal and the current state of your materials:

Use $academic-research-suite.

Goal: write a journal article.
Current materials: I have a literature matrix and rough findings, but no outline.
Output needed now: paper architecture and missing-evidence checklist.
Constraints: English, APA 7, higher education policy audience.

If you only have a paper topic or broad research direction and do not yet have a clear research question, the Codex router should start with ARS Socratic scoping:

Use $academic-research-suite.

I want to write a paper on AI adoption in higher education quality assurance.
I do not yet have a clear research question.
Please use SCR / Socratic dialogue to help me narrow the question first; do not write an outline yet.

Expected route: deep-research socratic mode first. ARS should ask narrowing questions and should not produce an outline or draft until the research question has converged.

For review tasks, provide the manuscript or a path to the manuscript, plus the review mode you want:

Use $academic-research-suite to review this paper.
Mode: full review.
Focus: methodology, contribution, citation integrity, and likely desk-reject risks.
Output: reviewer reports plus editorial decision letter.

For staged pipelines, ask for a checkpoint instead of asking Codex to run the entire process silently:

Use $academic-research-suite to start an academic-pipeline run.
Begin with Stage 0 intake and stop after producing the pipeline dashboard.

Smoke Tests

In a new Codex conversation:

/skills

Expected: one ARS entry only.

Then test Socratic routing:

Use $academic-research-suite.
I want to write a paper on AI adoption in higher education quality assurance.
I do not yet have a clear research question.

Expected: route to deep-research socratic mode and ask narrowing questions.

CLI smoke test:

codex exec --ephemeral --sandbox read-only \
  -C /path/to/academic-research-skills-codex \
  'Use $academic-research-suite. Router smoke test only. User request to classify: I want to write a paper on AI adoption in higher education quality assurance, but I do not yet have a clear research question. According to the academic-research-suite router, classify the workflow and mode.'

Maintainer quality gates:

python3 skills/academic-research-suite/codex/scripts/ars_codex_quality_gates.py all --json

Expected: every reported gate has "ok": true.

Non-Blocking Codex Warnings

These Codex messages do not mean ARS failed to install:

• [features].codex_hooks is deprecated — update your Codex config when convenient; ARS-Codex does not require hooks for normal use.
• hooks need review before they can run — review those hooks separately if you use them. ARS-Codex treats vendored Claude hooks as traceability metadata and does not require them.

Codex Adapter Behavior

ARS was originally written for Claude Code. In this Codex package:

• The vendored agents/*.md files are used as role and phase prompts.
• The Codex-only codex/ directory contains an optional full-runtime adapter profile. It is disabled by default and does not change normal inline routing.
• The vendored commands/ars-*.md files are prompt recipes only. Codex does not register them as slash commands.
• The vendored hooks/hooks.json file is preserved for upstream traceability only. Codex does not install Claude Code hooks from this package.
• Codex does not automatically spawn background agents unless you explicitly ask for delegated or parallel agent work.
• Web/source verification uses Codex browsing and must cite sources when current or external facts matter.
• Cross-model verification is disabled by default. When explicitly requested in this Codex package, follow the vendored provider setup in ars/shared/cross_model_verification.md, identify the provider/model/content class first, and obtain explicit user consent before any external upload. External reviewers are called through configured provider APIs, not simulated through the active Codex model.
• ARS_MODEL_TIERING is unset by default. The Codex adapter preserves the upstream judgment/execution classification but applies economy or quality-boost only when the runtime supports an explicit per-dispatch model override; otherwise it reports a no-op and keeps the active model.
• Protected top-level agent tools: allowlists remain least-privilege role boundaries. A dispatched checkpoint owner does not gain Bash or network transport; the dispatching Codex context owns any explicitly consented cross-model call.
• A [CROSS-MODEL-HANDOFF v1] block is a transport request, not a deliverable. The dispatcher validates it, sends only its payload, applies the mechanical result routing, and returns judgment work to the original owner.
• In reviewer full mode, an explicitly configured and consented cross-model run swaps the existing Reviewer 2 seat; it never adds a sixth reviewer. Re-review applies the separate Priority-1 judge pass and records provenance. Single-family execution and provider fallback are disclosed.
• ARS_CACHE_STALE_ADVISORY_DAYS controls the advisory-only cache-age threshold, while ARS_CACHE_REVALIDATE=1 opts into live bibliographic re-validation. These settings apply when the programmatic citation gate is run; stale rows alone never fail an integrity gate.
• Locally read PDFs run the structural pdf_read_preflight.py by default before page anchors are trusted. FAIL and UNAVAILABLE remain distinct, and a missing parser or sidecar is never treated as PASS. The v3.20 sandboxed content classifier is an explicit opt-in advisory and cannot override this structural preflight.
• ars-mark-read requires a user-declared read_scope for every new mark. Explicit unknown and legacy scope-less records remain coverage_unknown; partial coverage stays visible and Codex never infers full-text reading.
• Revision rounds use the v3.20 evidence-bound, non-ranking roadmap and explicit author-adjudication contract. They also preserve the v3.19-introduced claim-strength ladder and deterministic numeric, citation, marker, and protected-term conservation checks as advisory-first guards.
• The upstream v3.18 SessionStart update checker is vendored but not installed or executed as a Codex hook. Plugin users update with codex plugin marketplace upgrade ars-codex followed by codex plugin add ars-codex@ars-codex; direct skill installs still update by reinstalling or pulling this repository.
• Upstream references to a "fresh Claude Code session" mean a new Codex conversation in this package; Material Passport reset semantics still apply.
• If a citation, source, statistic, or journal policy cannot be verified, Codex should mark it as unverified rather than invent support.

ARS post-v3.21.1 Main Parity

This package aims for the same user-facing workflow content as upstream ARS post-v3.21.1 main at 94436237913091d4739870159d241660527e8338 where Codex has an equivalent concept. Upstream suite metadata remains 3.21.1.

Bibliographic network behavior is intentionally explicit at the Codex adapter boundary:

Optional External Cross-Model Reviewer API

For reviewer calibration or cross-model devil's advocate checks, configure one of the provider tuples documented in ars/shared/cross_model_verification.md, then ask for cross-model verification explicitly in the prompt. For example:

export OPENAI_API_KEY="<your-openai-api-key>"
export ARS_CROSS_MODEL="gpt-5.5"

Without both a configured provider and explicit user consent for the content class being sent, ARS-Codex falls back to single-runtime review and reports that cross-model verification was unavailable.

Support And Sponsorship

If ARS-Codex helps your research workflow, you can support maintenance through Buy Me a Coffee.

Security

Do not open public issues for vulnerabilities. Follow SECURITY.md for private reporting, and see the release readiness and security report for the latest local validation summary.

File Layout For Advanced Use

The entry point is:

skills/academic-research-suite/SKILL.md

Workflow content is under:

skills/academic-research-suite/ars/<workflow>/

Shared schemas, compliance rules, and cross-workflow contracts are under:

skills/academic-research-suite/ars/shared/

When debugging or updating the package, preserve these paths. Many ARS workflow files cross-reference shared/, scripts/, examples/, and other workflow directories.

Update Policy

Updates sync selected upstream ARS content into skills/academic-research-suite/ars/. Do not mirror the Claude Code repo blindly; exclude Claude/plugin loader files such as .claude/, .claude-plugin/, source .gitignore, and symlink-only alias directories that are not needed in Codex. Nested upstream .github/ workflows may be retained as inactive traceability and self-test fixtures.

Inactive Upstream Scripts

Some upstream maintenance scripts are vendored but intentionally inactive in this Codex package because they require non-vendored Claude Code inputs such as .claude/CLAUDE.md. See inactive_upstream_scripts in skills/academic-research-suite/manifest.json before wiring any upstream script into Codex CI.

Contributors And Acknowledgements

Cheng-I Wu - Maintainer of the ARS suite and this Codex sibling distribution.

Codex - Assisted with the Codex adapter packaging, router-policy hardening, test fixes, and release-readiness review under maintainer direction.

vinschger - Reported beginner installation friction around python vs python3, which led to clearer setup instructions for macOS and other environments.

Joker2377 - Helped answer community installation questions and clarify beginner setup steps in issue discussions.

Vendored upstream ARS contributors are acknowledged in skills/academic-research-suite/ars/README.md.