benefriches: Skill for Claude Code

.claude/skills/code-reviewer/SKILL.md

code-reviewer is a skill for Claude Code from incubateur-ademe/benefriches. It costs 69 tokens per session (999 once invoked), scanned A, original, MIT.

A code-review skill that checks recent software changes for bugs, security weaknesses, maintainability problems, and project-rule violations.

In plain words
What is it for?
It is for reviewing diffs, branches, pull requests, and code immediately after a feature, fix, or refactor is completed.
Why use it?
It gives developers a structured review of changed files instead of relying only on manual inspection.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

This is incubateur-ademe/benefriches's own configuration. It tells Claude Code how to work on benefriches itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything benefriches configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/incubateur-ademe/benefriches/main/.claude/skills/code-reviewer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/incubateur-ademe/benefriches

Made for: Claude Code.

Wrote 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.

agentmods badge for code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/incubateur-ademe/benefriches/code-reviewer/github.svg)](https://agentmods.dev/skills/incubateur-ademe/benefriches/code-reviewer)
Your own site
<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.

agentmods 80×15 button for code-reviewer

Your own site · 80×15
<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>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 999 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash 8aa6d3000991, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

.claude/skills/code-reviewer/SKILL.md · 93 lines

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/ importing adapters/, UseCase not returning TResult<>, TypeScript enum, 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.

Read the full file on GitHub · 93 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 93 lines · 69 tokens per session scan A 8aa6d3000991

Subscribe to this mod's changes

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.