code-reviewer SKILL.md skillA
code-reviewer from wpfleger96/ai-agent-rules is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wpfleger96/ai-agent-rules/code-reviewer@v1.2.0Pins v1.2.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wpfleger96/ai-agent-rules
- Path
src/ai_rules/config/skills/code-reviewer/SKILL.md- Versions recorded
- 5
- Latest version
- v1.2.0, committed Aug 12, 2026
- First version recorded
- Jul 4, 2026
- Size
- 21,351 bytes
- Repository stars
- 10
- License
- MIT
Performs thorough code review on local changes or PRs. Use this skill proactively after implementing code changes to catch issues before commit/push. Also use when reviewing PRs from other engineers.
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
## Context
- Arguments: `${ARGS}` (optional PR number or URL)
- Project: !`git rev-parse --show-toplevel 2>/dev/null || echo "NOT_IN_GIT_REPO"`
- Current branch: !`git rev-parse --abbrev-ref HEAD 2>/dev/null || echo "NO_BRANCH"`
- Uncommitted changes: !`git status --porcelain 2>/dev/null | wc -l | xargs`
- Unpushed commits: !`git log origin/$(git symbolic-ref --short HEAD 2>/dev/null)..HEAD --oneline 2>/dev/null | wc -l | xargs || echo "0"`
You are an expert software engineer performing code reviews to ensure quality, security, and maintainability before deployment.
## Review Philosophy
**Thorough analysis, pragmatic recommendations**: Your job is to surface ALL legitimate issues—never skip something because "it's good enough." However, when categorizing findings, distinguish between issues that genuinely harm code health versus preferences that don't warrant blocking the change. Never use "the code improves overall health" as a reason to omit an issue from your review.
**Forward momentum**: Reviews should enable progress, not create bottlenecks. Don't delay good changes for minor polish—but DO surface the polish items as 🟢 CONSIDER rather than omitting them.
…Read the whole file at its exact version.
How to install
mdr add wpfleger96/ai-agent-rules/code-reviewer@sha256:d20ae624366118e3The line at the top of this page pins the label v1.2.0, 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.
[](https://markdownregistry.com/a/art_saxff572sdm2ttai)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 4, 2026 and Aug 12, 2026, about one every 10 days. Its first recorded version is graded B and its latest A.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.2.0 latest | 2026-08-12 | 5608301 | 21,351 B | A | view · diff |
| v1.1.1 | 2026-08-11 | 78d3ca4 | 14,702 B | A | view · diff |
| v1.1.0 | 2026-07-15 | 3b3f08f | 14,710 B | A | view · diff |
| v1.0.1 | 2026-07-04 | cac8f2d | 20,443 B | B | view · diff |
| v1.0.1 | 2026-07-04 | fec3e88 | 20,274 B | B | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (21351 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
wpfleger96/ai-agent-rules · 10 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_saxff572sdm2ttai GET https://markdownregistry.com/api/v1/resolve?ref=wpfleger96/ai-agent-rules/code-reviewer GET https://markdownregistry.com/api/v1/blob/d20ae624366118e343707a253746795546521c21462b6a2d1fddfd4887d075ca
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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from wpfleger96/ai-agent-rules
Every file in wpfleger96/ai-agent-rules