claude-skills is a collection of specialized skills that extends Claude Code for full-stack development. Developers use it for programming languages, frameworks, infrastructure, APIs, testing, DevOps, security, data and machine learning, platform tasks, and project workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Jeffallan/claude-skills --skill code-reviewergit clone --depth 1 https://github.com/Jeffallan/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jeffallan/claude-skills/code-reviewer)<a href="https://agentmods.dev/skills/jeffallan/claude-skills/code-reviewer"><img src="https://agentmods.dev/badge/skills/jeffallan/claude-skills/code-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jeffallan/claude-skills/code-reviewer"><img src="https://agentmods.dev/badge/skills/jeffallan/claude-skills/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk fail
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00130 | $0.01139 |
| Opus 5 | $0.00065 | $0.00570 |
| Sonnet 5 | $0.00026 | $0.00228 |
| Haiku 4.5 | $0.00013 | $0.00114 |
Grade A, and why
code-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- code-reviewer — 97% identical, 2 lines differ
- code-reviewer — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer
Senior engineer conducting thorough, constructive code reviews that improve quality and share knowledge.
When to Use This Skill
- Reviewing pull requests
- Conducting code quality audits
- Identifying refactoring opportunities
- Checking for security vulnerabilities
- Validating architectural decisions
Core Workflow
- Context — Read PR description, understand the problem being solved. Checkpoint: Summarize the PR's intent in one sentence before proceeding. If you cannot, ask the author to clarify.
- Structure — Review architecture and design decisions. Ask: Does this follow existing patterns in the codebase? Are new abstractions justified?
- Details — Check code quality, security, and performance. Apply the checks in the Reference Guide below. Ask: Are there N+1 queries, hardcoded secrets, or injection risks?
- Tests — Validate test coverage and quality. Ask: Are edge cases covered? Do tests assert behavior, not implementation?
- Feedback — Produce a categorized report using the Output Template. If critical issues are found in step 3, note them immediately and do not wait until the end.
Disagreement handling: If the author has left comments explaining a non-obvious choice, acknowledge their reasoning before suggesting an alternative. Never block on style preferences when a linter or formatter is configured.
Reference Guide
Load detailed guidance based on context:
| Topic | Reference | Load When |
|---|---|---|
| Review Checklist | references/review-checklist.md |
Starting a review, categories |
| Common Issues | references/common-issues.md |
N+1 queries, magic numbers, patterns |
| Feedback Examples | references/feedback-examples.md |
Writing good feedback |
| Report Template | references/report-template.md |
Writing final review report |
| Spec Compliance | references/spec-compliance-review.md |
Reviewing implementations, PR review, spec verification |
| Receiving Feedback | references/receiving-feedback.md |
Responding to review comments, handling feedback |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 122 lines · 130 tokens per session scan A 8f0ddb7d9017
code-reviewer is a skill published in the GitHub repository Jeffallan/claude-skills (11,361 stars, last pushed 1mo ago), licensed MIT. It adds 130 tokens to every session and 1,139 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
weave-review
Weave code review — run independent adversarial reviews in parallel, then synthesize findings.
pr-deslop
Use when cleaning AI slop, verbose commit messages, brittle references, or low-value changes from a branch before review.
slop-scan
Use when scanning tracked repository files for AI slop, verbosity, brittle references, or low-value contributions.
respond-action
Use when screened review findings should be fixed on the current branch, usually as one verified commit per finding.
ruff-bump
Use when upgrading Ruff in one repository or a fleet and evaluating newly applicable rules before committing each change.
weave-fix-review
Fix weave review findings — validate, add test coverage, fix, and commit each as atomic changes.