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 JayRHa/AgentSkills --skill code-reviewergit clone --depth 1 https://github.com/JayRHa/AgentSkillsWrote 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/jayrha/agentskills/code-reviewer)<a href="https://agentmods.dev/skills/jayrha/agentskills/code-reviewer"><img src="https://agentmods.dev/badge/skills/jayrha/agentskills/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/jayrha/agentskills/code-reviewer"><img src="https://agentmods.dev/badge/skills/jayrha/agentskills/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00120 | $0.01926 |
| Opus 5.5 | $0.00048 | $0.00770 |
| Sonnet 5.5 | $0.00024 | $0.00385 |
| Haiku 4.5 | $0.00012 | $0.00193 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer
Overview
This skill performs a thorough, structured code review of a change set (a diff, a pull request, staged changes, or a list of modified files). It surfaces correctness bugs, security vulnerabilities, and quality/maintainability issues, ranks every finding by severity, and gives an actionable fix for each one.
Keywords: code review, PR review, diff review, bug hunting, security review, pull request, merge readiness, static review, defect detection.
The review is diff-scoped by default: focus on what changed and what the change touches. Do not rewrite the whole codebase. The deliverable is a review report, not a refactor.
When To Use
- User says "review this PR / diff / branch / changes".
- User pastes a patch, unified diff, or set of files and asks for feedback.
- Before a merge, when the user wants a gate check.
- After implementing a feature, to self-review prior to opening a PR.
Workflow
Follow these steps in order.
1. Gather the change set
Determine exactly what to review. Prefer the narrowest accurate scope.
- GitHub PR:
gh pr diff <number>(orgh pr view <number> --json files,title,body). - Local branch vs base:
git diff <base>...HEAD(three-dot = changes on the branch since it forked). - Staged:
git diff --staged. Unstaged:git diff. - A given commit:
git show <sha>. - If only file paths are given, read those files and, where needed, the symbols they call.
Capture: changed files, hunks, the PR title/description (intent), and the target branch.
2. Understand intent before judging
Read the PR description / commit messages to learn what the change is supposed to do. A bug is a divergence between intent and behavior — you cannot find bugs without knowing intent. If intent is unclear, note it as a finding ("unclear intent / missing description") and review against the most reasonable interpretation.
3. Build minimal context
For each changed function, pull in just enough surrounding code to judge correctness:
- The function signature and its callers (does the change break callers?).
- Types/interfaces touched.
- Tests covering the changed code.
- Config/migration files referenced by the diff.
What ships with it
5 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.
- 1mo ago First seen · 128 lines · 120 tokens per session scan A 723cad3efb72
code-reviewer is a skill published in the GitHub repository JayRHa/AgentSkills (12 stars, last pushed 2mo ago), licensed MIT. It adds 120 tokens to every session and 1,926 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
code-reviewer
Use when reviewing pull requests, conducting code quality audits, or identifying security vulnerabilities. Invoke for PR reviews, code quality checks, refactoring suggestions.
claude-md-check
Use when the user asks to review, audit, improve, shorten or write a CLAUDE.md, CLAUDE.local.md, AGENTS.md or .claude/rules file, or says Claude Code keeps ignoring their instructions or forgetting project conventions. Checks the file against the repository it describes and against how memory files actually load, then…
developer-workflow
Use when the user is writing, reviewing, debugging, testing, or refactoring code, or wants help with commits and pull requests. Emphasizes reading existing code first, verifying changes, and never inventing APIs.
supreme-project-audit
Evidence-driven full-project audit skill for Product Engineers, AI Engineers, ML Engineers, LLM Engineers, LLM Architects, and AI Researchers. Enforces severity discipline (P0/P1/P2/P3 with objective criteria), explicit coverage maps (audited vs not-audited surface), threat modeling (STRIDE + OWASP LLM Top 10)…
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".