Pre-commit/ship code review: Codex default; optional Claude or Pi.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Auto Review
Run the bundled structured review helper as a closeout check. This is code review, not Guardian `auto_review` approval routing.
Codex review is the default when no engine is set. It uses `gpt-5.6-sol` with `high` reasoning by default, then retries once with `gpt-5.6-terra` only when the account cannot access Sol. Claude review is optional and uses `claude-fable-5` by default.
For user-visible behavior, pair autoreview with `behavior-validator`. Autoreview is source-aware and judges the change bundle; behavior validation is source-blind and judges the running product or tool against a behavior contract. A clean autoreview is not proof that a UI, CLI, API, or generated artifact works from the user's perspective.
Use when:
- user asks for Codex review / Claude review / Pi review / autoreview / second-model review
- after non-trivial code edits, before final/commit/ship
- reviewing a local branch or PR branch after fixes
…
The line at the top of this page pins the label git:20260812.c83047b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (34964 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
amd/gaia · 1,593 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_24cvj2vxefxkrs2w
GET https://markdownregistry.com/api/v1/resolve?ref=amd/gaia/autoreview
GET https://markdownregistry.com/api/v1/blob/add4c8e1540c90808456d064316c19c676b7f8743f35f5b8f532550fc1a1dbaa
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
amd/gaia · .claude/skills/adding-eval-scorecard/SKILL.md · Adopt the per-agent eval scorecard for a GAIA hub agent: write the harness→payload adapter, run the eval to produce a…
amd/gaia · .claude/skills/agent-hub-release/SKILL.md · Cut or wire the frozen-binary + npm release of an agent GAIA itself ships (the email/flagship CI pipeline: freeze ->…
amd/gaia · .claude/skills/analyzing-claude-sessions/SKILL.md · Analyze your own local Claude Code session transcripts to find what you actually use the agent for, how effective it…
amd/gaia · .claude/skills/benchmarking-the-agent/SKILL.md · Measure the flagship GAIA agent against Claude Code and across models — quality, truthfulness, steps, tokens, time and…
amd/gaia · .claude/skills/driving-the-tui/SKILL.md · Use when testing or validating the GAIA TUI (tui/) by actually running it — driving screens, clicking and scrolling…
amd/gaia · .claude/skills/gaia-build-agent/SKILL.md · Build a new GAIA agent with the SDK end-to-end: scaffold the package, write the Agent subclass, register @tool…
amd/gaia · .claude/skills/gaia-technical-presentation/SKILL.md · Generate a TECHNICAL slide presentation (engineering audience) from a source document as self-contained HTML that…
amd/gaia · .claude/skills/gaia-tui-manual/SKILL.md · The GAIA terminal UI (gaia-tui) — how to build it, launch it with a real pty, drive it through the loopback control…
amd/gaia · .claude/skills/github-issue-response/SKILL.md · Respond to a GitHub issue, PR comment, discussion reply, or review on amd/gaia. Use when writing any reply that will be…
vincentkoc/tokenjuice · .agents/skills/autoreview/SKILL.md · Auto Review closeout. Codex review is the default when no engine is set and is the recommended reviewer.
simonrowland/goal-flight · autoreview/SKILL.md · Run a structured code review (Codex default, Claude optional) as a closeout check on a local or PR branch before commit…
