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-documentation-progit 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-documentation-pro)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/code-documentation-pro"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/code-documentation-pro/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-documentation-pro"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/code-documentation-pro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
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 →
- medium MCP Rug Pull · line 151 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]
- medium MCP Rug Pull · line 157 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]
- medium MCP Rug Pull · line 174 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 | $0.00075 | $0.02070 |
| Opus 5 | $0.00037 | $0.01035 |
| Sonnet 5 | $0.00015 | $0.00414 |
| Haiku 4.5 | $0.00007 | $0.00207 |
Grade A, and why
code-documentation-pro 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 8d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Documentation Pro
Philosophie : commenter le POURQUOI, pas le QUOI
Le code bien écrit s'auto-documente (noms clairs, fonctions courtes, types expressifs). Un commentaire qui répète le code est du bruit. Un commentaire qui explique une décision non-évidente est de la valeur.
# BAD — répète le code
i += 1 # incrémente i
# GOOD — explique la contrainte métier
i += 1 # l'index commence à 1 côté API fournisseur (spec §4.2), pas 0
Workflow en étapes
1. Choisir le format adapté au langage
| Langage | Format | Outils de génération |
|---|---|---|
| Python | Google style / NumPy style | Sphinx + autodoc, pdoc |
| TypeScript / JavaScript | JSDoc (/** */) |
TypeDoc |
| C# | XML doc (///) |
DocFX, Sandcastle |
| Java | Javadoc (/** */) |
Javadoc CLI, Dokka |
| Go | GoDoc (commentaire au-dessus du symbole) | go doc, pkg.go.dev |
| C++ | Doxygen | Doxygen |
2. Structurer chaque docstring publique
Ordre canonique : description courte → paramètres → retour → exceptions → exemple.
Python (Google style) :
def charge_payment(amount: Decimal, currency: str, idempotency_key: str) -> PaymentResult:
"""Débite le montant depuis la passerelle configurée.
N'effectue aucune opération si la clé d'idempotence est déjà connue (replay safe).
Args:
amount: Montant en unité principale (ex: 10.50 pour 10,50 TND).
currency: Code ISO 4217 en majuscules (ex: "TND").
idempotency_key: UUID v4 unique par tentative, persisté avant l'appel.
Returns:
PaymentResult avec status, transaction_id et timestamp.
Raises:
InsufficientFundsError: Si le solde est insuffisant.
GatewayTimeoutError: Si la passerelle ne répond pas en < 10 s.
Examples:
>>> result = charge_payment(Decimal("50.00"), "TND", str(uuid4()))
>>> assert result.status == "SUCCESS"
"""
TypeScript (JSDoc) :
/**
* Génère un token JWT signé avec rotation automatique des clés.
*
* @param payload - Données à embarquer ; ne pas inclure de PII sensibles.
* @param ttlSeconds - Durée de validité en secondes (défaut : 3600).
* @returns Token signé ou lève une erreur si le keystore est indisponible.
* @throws {KeystoreUnavailableError} Quand aucune clé active n'est trouvée.
* @example
* const token = generateJwt({ userId: "u_123", role: "admin" });
*/
export function generateJwt(payload: JwtPayload, ttlSeconds = 3600): string { ... }
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.
- 8d ago First seen · 222 lines · 75 tokens per session scan A ca335bb8bd73
code-documentation-pro is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 17d ago), licensed MIT. It adds 75 tokens to every session and 2,070 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
python-rules
Python coding rules: style, patterns, security, testing. Triggers: .py, .pyi, pyproject.toml, requirements.txt, Pipfile, FastAPI, Django, Flask, pytest, SQLAlchemy, ruff, mypy.
plugin-system
Generic plugin system for Python applications. Auto-discovery, validation, fault tolerance. Zero dependencies (Python stdlib only).
encoding-fix
Mojibake-Reparatur für doppelt/dreifach kodiertes UTF-8. Behebt Windows-cp1252/Latin-1-Fehlinterpretationen. Ohne Abhängigkeiten.
dep-audit
Cross-repository dependency audit. Scans package manifests for outdated packages, security advisories, version conflicts, and license issues. Produces a prioritized update plan. Supports Node.js, Python, Rust, and Go projects.
python
Apply when writing Python code. Type hints, error handling, mutable defaults, async patterns, and packaging conventions.
pydub-automation
Automate repetitive audio tasks with Python using PyDub for batch processing, format conversion, normalization, and content assembly. Use when: Processing large numbers of audio files consistently; Converting between audio formats at scale; Normalizing loudness across a batch of files; Assembling intros/outros…