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 script-automation-expertgit 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/script-automation-expert)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/script-automation-expert"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/script-automation-expert/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/script-automation-expert"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/script-automation-expert.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 | $0.00087 | $0.02328 |
| Opus 5 | $0.00044 | $0.01164 |
| Sonnet 5 | $0.00017 | $0.00466 |
| Haiku 4.5 | $0.00009 | $0.00233 |
Grade D, and why
script-automation-expert scanned grade D with 3 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 9d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
3. Fichier protégé hors dépôt Git (`chmod 600`) Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| `rm -rf` sans vérification | Perte de données | Vérifier le chemin, demander confirmation | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| API REST | `curl` | `Invoke-RestMethod` | `requests` / `httpx` | How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Script Automation Expert
1. Choisir le bon langage
| Critère | Bash | PowerShell | Python |
|---|---|---|---|
| OS cible | Linux/macOS | Windows/Azure | Cross-platform |
| Manipulation fichiers | ✅ natif | ✅ natif | ✅ via pathlib |
| API REST | curl |
Invoke-RestMethod |
requests / httpx |
| Parsing JSON/XML | jq requis |
natif ConvertFrom-Json |
natif json |
| Disponibilité par défaut | Linux/macOS | Windows Server 2016+ | à installer |
| Tests unitaires | bats |
Pester |
pytest |
Règle : si le script tourne sur plusieurs OS ou consomme des API complexes → Python. Si c'est pur Windows/AD/Azure → PowerShell. Si c'est du glue CLI Linux → Bash.
2. Workflow en étapes
Étape 1 — Analyser et cadrer
Avant d'écrire une ligne de code, répondre à :
- Entrées/sorties : fichiers, API, base de données ?
- Fréquence : unitaire, planifié, déclenché sur événement ?
- Volume : combien d'items par exécution ?
- Dépendances système : outils CLI, credentials, réseau ?
- Idempotence requise ? (re-run sans effet de bord)
Étape 2 — Structurer le script
Modèle Python minimal production-ready :
#!/usr/bin/env python3
"""process_invoices.py — traitement batch des factures."""
import argparse, logging, sys
from pathlib import Path
from datetime import datetime
LOG_FORMAT = "%(asctime)s %(levelname)s %(message)s"
logging.basicConfig(level=logging.INFO, format=LOG_FORMAT,
handlers=[logging.StreamHandler(),
logging.FileHandler(f"run_{datetime.now():%Y%m%d}.log")])
log = logging.getLogger(__name__)
def parse_args():
p = argparse.ArgumentParser()
p.add_argument("--input-dir", required=True)
p.add_argument("--dry-run", action="store_true")
return p.parse_args()
def process(path: Path, dry_run: bool) -> bool:
log.info("Traitement %s", path.name)
if dry_run:
log.info("[DRY-RUN] %s ignoré", path.name)
return True
# ... logique métier ici
return True
def main():
args = parse_args()
errors = 0
for f in Path(args.input_dir).glob("*.csv"):
if not process(f, args.dry_run):
errors += 1
sys.exit(1 if errors else 0)
if __name__ == "__main__":
main()
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.
- 9d ago First seen · 271 lines · 87 tokens per session scan D 8d2ee3d2c381
script-automation-expert is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 19d ago), licensed MIT. It adds 87 tokens to every session and 2,328 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
instinct-review
Reviews/promotes/removes instincts from .claude/instincts/.md. Triggers: instinct review, curate instincts, manage instincts, promote instinct.
repeat
Runs prompt/slash command on recurring interval until done or limit. Triggers: repeat, recurring task, poll status, run every N minutes, interval.
night-watch
Autonomous maintenance (dep updates, dead code, small refactors) in isolated branch, off-hours. Triggers: night watch, autonomous maintenance, dep updates.
briefing
Executive daily briefing aggregating reports from all agents into decision-focused summary. Triggers: briefing, daily summary, status across system, executive update.
work-autonomous
Abbruchbedingung für autonome Loops: So weit wie möglich selbständig weiterarbeiten UND einen Loop erst beenden, wenn belegt ist, dass keine autonom ausführbare Aufgabe mehr vorliegt. Der bloße Eindruck "nichts mehr zu tun" reicht NICHT — er löst eine vierstufige Prüfkette aus (think/decide, CONTROL/DECISIONS…
rotation-check
Standard-Gerüst für rotierende Pipeline-Checks: Pro Lauf genau ein Ziel aus einer Menge (Projekte, Ordner, Repos) wählen — bevorzugt das am längsten ungeprüfte —, den Check durchführen, Ergebnis in einer Check-Registry und einem Verlaufslog festhalten. Nutze diesen Skill, wenn ein wiederkehrender Check über viele…