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 atournayre/claude-marketplace --skill auto-reviewgit clone --depth 1 https://github.com/atournayre/claude-marketplaceWrote 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/atournayre/claude-marketplace/auto-review)<a href="https://agentmods.dev/skills/atournayre/claude-marketplace/auto-review"><img src="https://agentmods.dev/badge/skills/atournayre/claude-marketplace/auto-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/atournayre/claude-marketplace/auto-review"><img src="https://agentmods.dev/badge/skills/atournayre/claude-marketplace/auto-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 | $0.00019 | $0.01748 |
| Opus 5 | $0.00010 | $0.00874 |
| Sonnet 5 | $0.00004 | $0.00350 |
| Haiku 4.5 | $0.00002 | $0.00175 |
Grade A, and why
dev:auto:review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objectif
Instructions à Exécuter
IMPORTANT : Exécute ce workflow étape par étape :
Phase 7 du workflow automatisé : review de qualité avec correction automatique.
Boucle auto-fix max 3 tentatives. Si ça échoue → ROLLBACK + CLEANUP + EXIT 1.
Instructions
1. Lire le contexte
Déterminer le chemin du workflow state :
# Récupérer issue_number depuis le contexte
workflow_state_file=".claude/data/workflows/issue-${issue_number}-dev-workflow-state.json"
- Lire le workflow state pour les fichiers modifiés (Phase 6)
- Si phase 6 non complétée, exit avec erreur
2. Détecter les langages du projet
# Déterminer les langages présents (peut être multi-langage)
LANGUAGES=()
QA_TOOLS=()
# Vérifier PHP
if [ -f "composer.json" ] && [ -f "vendor/bin/phpstan" ]; then
LANGUAGES+=("php")
QA_TOOLS+=("phpstan")
fi
# Vérifier JavaScript
if [ -f "package.json" ]; then
LANGUAGES+=("javascript")
# Utiliser eslint ou prettier selon disponibilité
if command -v eslint &> /dev/null; then
QA_TOOLS+=("eslint")
fi
fi
# Vérifier Go
if [ -f "go.mod" ]; then
LANGUAGES+=("go")
QA_TOOLS+=("golangci-lint")
fi
if [ ${#LANGUAGES[@]} -eq 0 ]; then
echo "⚠️ Aucun langage détecté. Skipping review automatique."
exit 0
fi
3. Boucle de correction automatique (max 3 tentatives par langage)
# Lancer la review pour CHAQUE langage
for i in "${!LANGUAGES[@]}"; do
language="${LANGUAGES[$i]}"
tool="${QA_TOOLS[$i]}"
echo ""
echo "🔍 Reviewing $language (outil: $tool)..."
attempt=1
max_attempts=3
qa_exit_code=0
while [ $attempt -le $max_attempts ]; do
echo " Tentative $attempt/$max_attempts..."
# 1. Lancer l'outil de qualité
case "$language" in
"php")
qa_output=$(vendor/bin/phpstan analyse --level=9 2>&1)
qa_exit_code=$?
qa_errors=$(echo "$qa_output" | grep -c "error:" || true)
qa_name="PHPStan niveau 9"
;;
"javascript")
qa_output=$(eslint . 2>&1)
qa_exit_code=$?
qa_errors=$(echo "$qa_output" | grep -c "error" || true)
qa_name="ESLint"
;;
"go")
qa_output=$(golangci-lint run 2>&1)
qa_exit_code=$?
qa_name="golangci-lint"
;;
esac
# 2. Vérifier succès
if [ $qa_exit_code -eq 0 ]; then
echo " ✅ $qa_name : PASS"
break # Success for this language!
fi
echo " ⚠️ $qa_name : erreurs détectées"
# 3. Auto-fix si applicable
if [ "$language" = "php" ] && [ $attempt -lt $max_attempts ]; then
echo " 🔧 Auto-fix en cours..."
/qa:phpstan
fi
attempt=$((attempt + 1))
done
# 4. Vérifier succès final pour ce langage
if [ $qa_exit_code -ne 0 ]; then
echo "❌ ÉCHEC : $qa_name impossible après $max_attempts tentatives"
echo ""
echo "Erreurs :"
echo "$qa_output"
echo ""
exit 1
fi
done
# 5. Elegant Objects review (si PHP)
if [[ " ${LANGUAGES[@]} " =~ " php " ]]; then
echo ""
echo "🔍 Elegant Objects review..."
elegant_output=$(/qa:elegant-objects 2>&1)
fi
echo ""
echo "✅ Review automatique complète (tous les langages)"
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 · 263 lines · 19 tokens per session scan A f75e03ed4b88
dev:auto:review is a skill published in the GitHub repository atournayre/claude-marketplace (9 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 1,748 once invoked, about $0.0001 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 2026-08-31.
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…