Borrowing it
Nothing to install: this file belongs to SocialGouv/egapro. 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/SocialGouv/egapro/alpha/.claude/skills/review/SKILL.mdgit clone --depth 1 https://github.com/SocialGouv/egaproWrote 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/socialgouv/egapro/review)<a href="https://agentmods.dev/skills/socialgouv/egapro/review"><img src="https://agentmods.dev/badge/skills/socialgouv/egapro/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/socialgouv/egapro/review"><img src="https://agentmods.dev/badge/skills/socialgouv/egapro/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 121 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00041 | $0.02273 |
| Opus 5 | $0.00020 | $0.01137 |
| Sonnet 5 | $0.00008 | $0.00455 |
| Haiku 4.5 | $0.00004 | $0.00227 |
Grade A, and why
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 5d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review
Délègue à l'agent review-fixer dans un worktree dédié pour : lire les commentaires non résolus, appliquer les fixes, valider, push, répondre aux threads. Trois modes auto-détectés :
| Mode | Trigger | Scope du review |
|---|---|---|
| epic | Issue type Feature |
Toutes les sub-task PRs liées à la feature + la PR finale epic/<N> → alpha. Les fixes sont appliqués sur la branche d'intégration epic/<N> (les sub-tasks sont déjà squash-mergées dedans). |
| task | Issue type Task |
La PR du ticket en review. Fixes sur la branche head du PR. |
| bug | Issue type Bug |
La PR du bug en review. Fixes sur la branche head du PR. |
| (no-arg) | Aucun argument, sur une branche de PR | La PR de la branche courante (équivalent task/bug single-PR). |
Globalement le fonctionnement reste identique au précédent /review : fetch, fix, re-validate, reply. La nouveauté c'est que le travail réel se passe dans un agent qui tourne en worktree (comme code-dev pour /implement), pas dans le main context.
Step 0 — Détecter le mode
ARG_HEAD="$(echo "$ARGUMENTS" | awk '{print $1}')"
case "$ARG_HEAD" in
'#'[0-9]*|[0-9]*)
ID="${ARG_HEAD#\#}"
# ID peut être un issue number ou un PR number — on essaie d'abord issue
;;
https://github.com/*/issues/*)
ID="$(echo "$ARG_HEAD" | sed -E 's#.*/issues/([0-9]+).*#\1#')"
;;
https://github.com/*/pull/*)
ID="$(echo "$ARG_HEAD" | sed -E 's#.*/pull/([0-9]+).*#\1#')"
IS_PR=1
;;
*)
ID=""
;;
esac
Cas A — argument fourni
- Si l'argument est un numéro d'issue :
gh issue view <ID> --json number,issueType,labels→ brancher selonissueType.name(Feature/Task/Bug). - Si l'argument est un numéro de PR :
gh pr view <ID> --json closingIssuesReferences→ trouver l'issue liée → brancher selon son type. - Type absent ou ambigu → demander à l'utilisateur quel mode utiliser.
Cas B — pas d'argument
- Si la branche courante est une PR branch (
gh pr view --json numberréussit) → modetaskoubugselon l'issue liée à cette PR. PR = la PR courante. - Sinon : lister les PRs ouvertes avec des reviews non adressées (
gh pr list --state open --json number,title,reviewDecision --jq '.[] | select(.reviewDecision == "REVIEW_REQUIRED" or .reviewDecision == "CHANGES_REQUESTED")') et demander laquelle traiter.
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.
- 5d ago First seen · 194 lines · 41 tokens per session scan A a2b726fbaded
review is a skill published in the GitHub repository SocialGouv/egapro (12 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 2,273 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
write-pr
Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.