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 selmakcby/claude-agents-skills --skill code-reviewgit clone --depth 1 https://github.com/selmakcby/claude-agents-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/selmakcby/claude-agents-skills/code-review)<a href="https://agentmods.dev/skills/selmakcby/claude-agents-skills/code-review"><img src="https://agentmods.dev/badge/skills/selmakcby/claude-agents-skills/code-review/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/selmakcby/claude-agents-skills/code-review"><img src="https://agentmods.dev/badge/skills/selmakcby/claude-agents-skills/code-review.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 | $0.00048 | $0.00743 |
| Opus 5.5 | $0.00019 | $0.00297 |
| Sonnet 5.5 | $0.00010 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
code-review 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
When to trigger
- Immediately after new or modified code
- Before commit / PR
- When user asks for
/code-review
Review approach
Multi-agent review with confidence filtering:
- CLAUDE.md compliance — does the code follow project rules?
- Bug detector — obvious bugs in the diff
- History analyzer — git context to understand intent
Each issue is scored 0–100. Findings below threshold (default 80) are filtered out.
What to check
Clarity
- Names (variables, functions, files) — do they say what they do?
- Structure — is it easy to scan?
- Cognitive load — how much do you hold in your head to understand it?
Correctness
- Edge cases: null, undefined, empty array, boundary values
- Error paths: are they handled? Do they fail loudly or silently?
- Async: await missing? Race conditions? Promise rejections caught?
- Off-by-one errors in loops / slicing
Performance
- N+1 queries (especially around ORM usage)
- O(n²) algorithms on large collections
- Unnecessary re-renders (React)
- Missing memoization for expensive computations
- Synchronous I/O in hot paths
Consistency
- Matches project style guide (CLAUDE.md, rules/)
- Immutable patterns used
- Function size under 50 lines
- Nesting 4 levels max
Tests
- Is there a test for the new behavior?
- Edge cases covered?
- Mocks realistic (no "happy path only")?
- Tests independent (no shared state)?
Dead code
- Unused imports
- Unreachable branches
- TODO comments that should be done or deleted
- Commented-out code
Severity levels
- CRITICAL — do not commit. Breaks production, security hole, data loss risk.
- HIGH — fix before next release. Real bug users will hit.
- MEDIUM — fix when you're in the area. Code smell, minor inefficiency.
- LOW — nice-to-have. Style preference, optional refactor.
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 · 101 lines · 48 tokens per session scan A 47886a937fd4
code-review is a skill published in the GitHub repository selmakcby/claude-agents-skills (143 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 743 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…