Use when the user explicitly requests a code review of a module, branch, change, or pull request -- "revisa este código", "haz code review de esto", "review this PR", "review this branch".
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
# Code Review
Code review examines a bounded code snapshot and returns evidence-backed findings
that another person can assess and act on. It is read-only by default: the result is
a report, not a corrected tree, published comment, or merge decision.
Use this technique for an explicitly requested review. Normal coding applies
`code-standards` before generation and during verification without automatically
dispatching reviewers. Risk discovered during coding can justify proposing a review;
it does not silently authorize one or enlarge the assignment. For a Gaia agent or
skill's conformance to its type and implementation, continue with the specialized
`gaia-audit` technique, retaining its name and ownership.
## Process
### 1. Fix the question and snapshot
The coordinator agrees the objective, included paths, exclusions, and available
evidence with the requester. Record repository identity and immutable revisions,
not just a branch label or PR number:
- **Module:** identify paths and the exact snapshot to inspect. Use that same
revision as base and head when there is no change comparison; label it `snapshot`.
…
The line at the top of this page pins the label git:20260925.3549fb0, 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 (10499 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
metraton/gaia · 4 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_w6ngd2tqcfeo7g7v
GET https://markdownregistry.com/api/v1/resolve?ref=metraton/gaia/code-review
GET https://markdownregistry.com/api/v1/blob/88406c62c0a73f89e70b14a13c08cca998392216f96664c4cf0906e68bf6ff00
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.
metraton/gaia · skills/agent-creation/SKILL.md · Use when creating a new specialist agent for Gaia, or reviewing whether an existing agent follows the correct…
metraton/gaia · skills/blog-writing/SKILL.md · Use when writing, drafting, or publishing a blog article for metraton.github.io -- "escribe un post para el blog"…
metraton/gaia · skills/brief-spec/SKILL.md · Use when the user wants to capture a feature as a brief or spec before planning it -- "arma un brief para esto"…
metraton/gaia · skills/code-standards/SKILL.md · Use when writing, modifying, reviewing, or refactoring code — any language or stack, application, infrastructure, or…
metraton/gaia · skills/diagram-builder/SKILL.md · Use when the user wants to build, extend or narrate a diagram deck -- an architecture map, a timeline, a process flow…
metraton/gaia · skills/dispatch/SKILL.md · Use when the orchestrator is about to dispatch a specialist turn that writes to a repository, runs alongside other…
agno-agi/agno · cookbook/02_agents/16_skills/sample_skills/code-review/SKILL.md · Code review assistance with linting, style checking, and best practices
kyegomez/swarms · examples/single_agent/capabilities/skills/multiple_skill_dirs/team_skills/code-review/SKILL.md · Review Python code for bugs, missing tests and security issues using the team's shared standards
basicmachines-co/basic-memory · .agents/skills/code-review/SKILL.md · Use when reviewing Basic Machines code for house style, architecture risk, pre-merge hardening, or whether a change…
nteract/semiotic · .github/skills/code-review/SKILL.md · Review Semiotic pull requests for behavioral bugs, regressions, contract drift, and missing evidence. Use for GitHub…
