Borrowing it
Nothing to install: this file belongs to incubateur-ademe/benefriches. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/incubateur-ademe/benefriches/main/.claude/skills/code-reviewer/SKILL.mdgit clone --depth 1 https://github.com/incubateur-ademe/benefrichesWrote 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/incubateur-ademe/benefriches/code-reviewer)<a href="https://agentmods.dev/skills/incubateur-ademe/benefriches/code-reviewer"><img src="https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/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/incubateur-ademe/benefriches/code-reviewer"><img src="https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00069 | $0.00999 |
| Opus 5 | $0.00034 | $0.00500 |
| Sonnet 5 | $0.00014 | $0.00200 |
| Haiku 4.5 | $0.00007 | $0.00100 |
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 12d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Review recent code changes for quality, security, maintainability, and adherence to project patterns.
1. Get recent changes
Run git diff to see uncommitted changes. If there are none, run git diff HEAD~1 to review the last commit. Focus on the modified files and analyze them thoroughly.
2. Select review lenses
The detailed checklists live in reference/ and are organized by domain so you only load what's relevant. Read the file(s) matching the changed paths:
| Changed paths | Read |
|---|---|
| Every review | reference/cross-cutting.md — security, TypeScript/erasability, test-design antipatterns, code quality, performance |
apps/api/** |
reference/api.md — Clean Architecture, Result pattern, controllers, CQS, database, DI, naming, testing |
apps/web/** |
reference/web.md — Clean Architecture, Redux, Container/Presentational, hooks, gateways, naming, testing |
packages/shared/** |
Both reference/api.md and reference/web.md — shared changes break both apps — plus verify type/DTO/Zod-schema placement per packages/shared/CLAUDE.md |
apps/e2e-tests/** |
apps/e2e-tests/CLAUDE.md — Page Object pattern, fixtures, spec structure |
If a change touches paths not listed above, still apply cross-cutting.md and use judgment. Each lens links to the canonical rule (.claude/rules/…) for full detail; those rules also auto-load when you Read the changed files. The reference files are the review checklist (what to flag); the rules are the spec (how to write it). Don't re-derive a rule's content — cite it.
3. Confidence-based filtering
Only report issues you are highly confident about.
- ✅ HIGH — clear violation visible in the diff (missing
@UseGuards(JwtAuthGuard),core/importingadapters/, UseCase not returningTResult<>, TypeScriptenum, missing table type after migration). Report. - ⚠️ MEDIUM — probable but needs context (large functions/files, possibly-missing tests). Report with the caveat "Possible issue (verify context)…".
- ❌ LOW — needs deep codebase knowledge, may have valid reasons not visible in the diff, or is style-only. Skip.
What ships with it
3 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.
- 12d ago First seen · 93 lines · 69 tokens per session scan A 8aa6d3000991
code-reviewer is a skill published in the GitHub repository incubateur-ademe/benefriches (45 stars, last pushed 3d ago), licensed MIT. It adds 69 tokens to every session and 999 once invoked, about $0.0003 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…