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 khalilbenaz/claude-skills-collection --skill code-review-subagentgit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/code-review-subagent)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/code-review-subagent"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/code-review-subagent/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/khalilbenaz/claude-skills-collection/code-review-subagent"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/code-review-subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Tool Misuse · line 59 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium MCP Rug Pull · line 46 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00118 | $0.02398 |
| Opus 5 | $0.00059 | $0.01199 |
| Sonnet 5 | $0.00024 | $0.00480 |
| Haiku 4.5 | $0.00012 | $0.00240 |
Grade A, and why
code-review-subagent scanned grade A with 1 finding 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 10d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Injections** : SQL (`f"SELECT … {user_input}"`), command (`subprocess.call(input, shell=True)`) How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Sub-Agent
Rôle et périmètre
Sous-agent invocable depuis un agent parent ou un pipeline CI. Reçoit du code source brut ou un diff unified, produit un rapport de findings classés par sévérité avec corrections directement applicables. Supporte Python, JavaScript, TypeScript, Java, Go, Rust, C#.
Workflow en 10 étapes
Étape 1 — Validation des inputs
Vérifier avant toute analyse :
codenon vide, longueur raisonnable (< 10 000 lignes → OK ; > 10 000 lignes → tronquer et signaler)languagesupporté ; si absent, détecter via heuristique (tokens + shebang + extension dans le contexte)severity_thresholdvalide parmicritical | high | medium | low | info
Si validation KO → retourner immédiatement {"findings": [], "score": null, "summary": "<raison>"} sans lancer l'analyse.
Étape 2 — Analyse statique
Lancer l'outil adapté au langage :
| Langage | Outil principal | Fallback |
|---|---|---|
| Python | ruff check --output-format json |
flake8 --format json |
| JS/TS | eslint --format json |
- |
| Java | checkstyle -f json |
pmd -f json |
| Go | staticcheck -f json |
go vet |
| Rust | cargo clippy --message-format json |
- |
| C# | dotnet-format --report json |
Roslyn analyzers |
Seuil de complexité cyclomatique : > 10 → finding medium ; > 20 → finding high.
# Python — mesurer la complexité avec radon
radon cc -j -s src/
# Go — staticcheck JSON
staticcheck -f json ./...
# JS — eslint JSON
npx eslint --format json src/ > eslint-report.json
Étape 3 — Security scan
Priorité absolue. Utiliser semgrep en mode multi-langage + outil natif :
semgrep --config=p/default --json --quiet .
bandit -r src/ -f json -o bandit-report.json # Python
Patterns à détecter systématiquement :
- Injections : SQL (
f"SELECT … {user_input}"), command (subprocess.call(input, shell=True)) - Secrets hardcodés : regex
(api_key|password|token|secret)\s*=\s*['"][^'"]{8,}sur tout le diff - Désérialisation :
pickle.loads,yaml.load(…)sansLoader=yaml.SafeLoader - Cryptographie faible : MD5, SHA1 pour hachage de mots de passe, ECB mode
- IDOR / autorisation manquante : endpoint qui utilise un ID sans vérifier
current_user
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.
- 10d ago First seen · 239 lines · 118 tokens per session scan A 3dd7ef9d3702
code-review-subagent is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 16d ago), licensed MIT. It adds 118 tokens to every session and 2,398 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ln-41-test-strategy-planner
Plans a risk-based test portfolio and prioritized scenarios without editing tests. Not for test execution or implementation.
ai-slop
Operational rubric that turns "don't make AI slop" into observable properties, severity levels, evidence requirements, and repair actions for interface design. Use as the reference rubric when building or reviewing marketing sites, product interfaces, dashboards, portfolios, or e-commerce pages, especially alongside…
review
Reviews code for quality, security, correctness. Triggers: code review, quality review, security review, review PR, review branch.
architecture-audit
Audits codebase for architectural friction, shallow modules; proposes RFCs. Triggers: improve architecture, shallow modules, deepen modules, reduce coupling.
refactor
Refactors code for quality and maintainability. Triggers: refactor, clean up, restructure, improve code, modernize.
clean-code
Code quality: meaningful names, SRP, DRY, small functions, guard clauses, refactoring. Triggers: clean code, naming, code smell, SRP, DRY, long function, god class, dead code.