Review code changes, branches, or PRs against requirements and repository standards. Select general review or security-focused differential review according to the requested task and risk.
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
Recover the requested review scope, verified baseline, requirements, and affected code. Preserve the distinction between a review and implementation work.
Read [host integration](../.shared/host-integration.md) once for the imported review procedures.
| Review task | Read |
|---|---|
| Check requirement coverage, scope, repository standards, and maintainability | [General review](references/general/guide.md) |
| Review security-sensitive changes, regressions in protection, or concrete attack paths | [Security-focused differential review](references/security/guide.md) |
Use the security procedure when the user requests that analysis or the changed trust boundary makes it necessary. An ordinary low-risk review does not require a complete security audit. Keep evidence for requirement failures and security findings distinct.
The security procedure retains its methodology, adversarial analysis, reporting checklist, patterns, and assets. Use report templates as evidence checklists and follow the user's requested output format.
…
The line at the top of this page pins the label git:20261029.276ae81, 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.
GET https://markdownregistry.com/api/v1/artifacts/art_r7jarel6lusnbpf7
GET https://markdownregistry.com/api/v1/resolve?ref=dayfinggg/openai-codex-agent-skills/code-review
GET https://markdownregistry.com/api/v1/blob/154929883d325fb0804e6fe68c11714b479f235e6de51c7d63fcfa9358a8d70a
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.
dayfinggg/openai-codex-agent-skills · codex/skills/api-contract-change/SKILL.md · Implement or modify HTTP API contracts with validation, errors, authorization, and client-compatibility checks. Use for…
dayfinggg/openai-codex-agent-skills · codex/skills/backend-security-change/SKILL.md · Secure changed backend boundaries while preserving access policy and accepted events. Use for authentication…
dayfinggg/openai-codex-agent-skills · codex/skills/ci-failure-diagnosis/SKILL.md · Diagnose failed CI jobs from the exact commit, primary error, environment, and reproduction. Use for failed pipelines…
dayfinggg/openai-codex-agent-skills · codex/skills/codebase-design/SKILL.md · Design or improve a module interface, dependency seam, or test boundary for the requested change without speculative…
dayfinggg/openai-codex-agent-skills · codex/skills/database-migration-rollout/SKILL.md · Plan and validate schema migrations with lock, data, application-compatibility, rollout, and restoration checks. Use…
dayfinggg/openai-codex-agent-skills · codex/skills/database-query-diagnosis/SKILL.md · Diagnose slow SQL, lock waits, or connection exhaustion using actual queries, plans, and workload evidence. Use for…
dayfinggg/openai-codex-agent-skills · codex/skills/deployment-verification/SKILL.md · Prepare or verify an application release with artifact identity, configuration, migrations, readiness, and restoration…
dayfinggg/openai-codex-agent-skills · codex/skills/diagnosing-bugs/SKILL.md · Diagnose a difficult reproducible bug or performance regression through a feedback loop, competing hypotheses, and…
dayfinggg/openai-codex-agent-skills · codex/skills/docker/SKILL.md · Containerize an application, write or optimize Dockerfiles and image builds, or configure and diagnose Docker Compose…
dayfinggg/openai-codex-agent-skills · codex/skills/documentation-writing/SKILL.md · Write and maintain project documentation. Use when creating or updating README files, guides, API references, runbooks…
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…
