Review code changes with security, correctness, and style checklist. Use for PR review, diff review, or /code-review.
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
## When to use
- User shares a diff, file path, or asks for review before merge
- After implementing a feature, when they want a second pass
## Steps
1. Gather context: `git_diff` (staged or range), or `read_file` / `read_file_range` for named paths.
2. Summarize **intent** of the change in 2–3 sentences before nitpicks.
3. Walk this checklist:
### Correctness
- Logic matches stated requirements; edge cases (null, empty, errors)
- No obvious race or async mistakes
- API contracts and types consistent
### Security
- Input validation on external data
- No SQL/command injection; paths resolved safely
- Secrets not logged or committed
### Style & maintainability
- Matches project conventions (naming, structure)
- Functions focused; duplication avoided
- Tests updated when behavior changes
4. Prioritize findings: **blocker** → **should fix** → **nit**
5. Suggest concrete fixes (snippet or file/line), not vague "consider refactoring"
## Output format
```markdown
## Summary
…
## Blockers
- …
## Suggestions
- …
## Nits
- …
```
## Tools
`git_diff`, `read_file`, `read_file_range`, `search_in_file`, `list_directory`
The line at the top of this page pins the label git:20261007.306e7f0, 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_jn3nrbedytftnmri
GET https://markdownregistry.com/api/v1/resolve?ref=henrigrimm/minnow/code-review
GET https://markdownregistry.com/api/v1/blob/a59cc81ead882b8a71b1eb4a347a5f64704882f2b09c3cf78023723c774665b2
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.
henrigrimm/minnow · .claude/skills/minnow-plan/SKILL.md · Write an implementation plan in Minnow's orchestrator board schema — front matter with todos, waves, and tasks carrying…
henrigrimm/minnow · .cursor/skills/fix-ci/SKILL.md · Investigates GitHub Actions CI failures for the latest commit on the current branch, fixes scoped issues using…
henrigrimm/minnow · .cursor/skills/orchestrate-plan/SKILL.md · Runs multi-phase plans by delegating each phase to sub-agents and gating progress on a dedicated verification pass…
henrigrimm/minnow · .cursor/skills/plan-work/SKILL.md · Produces implementation plans in documentation/plans/ through discovery, codebase research via sub-agents, and a review…
henrigrimm/minnow · src/skills/_template/SKILL.md · Describe what this skill does and when Minnow should apply it. Include example phrases users might say, such as "help…
henrigrimm/minnow · src/skills/ask-user/SKILL.md · Gather structured answers from the user with the ask_question tool when requirements, scope, or priorities are…
henrigrimm/minnow · src/skills/browser-automation/SKILL.md · Drive Minnow's visible preview or isolated Agent Browser for login flows, SPAs, and screenshots. Use when fetch tools…
henrigrimm/minnow · src/skills/caveman/SKILL.md · Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical…
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…
