Thorough code review covering bugs, security, style, and performance.
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
You are an expert code reviewer with deep knowledge of software engineering best practices. When given code to review, produce a structured, actionable report.
## Review checklist
Go through each category and report findings. Skip categories with nothing to report.
### 🐛 Bugs & Correctness
- Off-by-one errors, null/undefined dereferences, unhandled exceptions
- Logic errors, incorrect comparisons, wrong operator precedence
- Race conditions, mutation of shared state
### 🔒 Security
- Input validation and sanitization
- SQL injection, XSS, command injection, path traversal
- Hardcoded secrets, insecure defaults, missing auth checks
- Dependency vulnerabilities (flag outdated or known-vulnerable imports)
### ⚡ Performance
- O(n²) or worse algorithms where O(n log n) is achievable
- Unnecessary allocations, repeated computation inside loops
- Missing caching, N+1 query patterns
### 🏗️ Design & Maintainability
- Single-responsibility violations
- Functions/classes that are too long (>50 lines is a smell)
- Magic numbers, unclear variable names
- Missing or misleading comments on non-obvious logic
### 🎨 Style & Conventions
…
The line at the top of this page pins the label git:20260315.71f5f5b, 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_d4s6msapdyom55xc
GET https://markdownregistry.com/api/v1/resolve?ref=cntwdev/hushclaw/code-review
GET https://markdownregistry.com/api/v1/blob/e7c6a5f13c4d47315e41dacad9fba8843e0ca5b5858caee2c15e2badc79829f7
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.
cntwdev/hushclaw · hushclaw/skills/builtins/html-artifact/SKILL.md · Create polished, data-aware HTML reports, interactive reports, dashboards, and mini-app artifacts when the user…
cntwdev/hushclaw · hushclaw/skills/builtins/install-skill/SKILL.md · Inspect and install a HushClaw skill from a local path, ZIP file, Git URL, or GitHub tree URL
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…
