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 agentmods add skills/kxlsys/openskill/devsecops-complete-auditnpx skills add KxlSys/OpenSkill --skill devsecops-complete-auditgit clone --depth 1 https://github.com/KxlSys/OpenSkillWhat 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 | $0.00050 | $0.08337 |
| Opus 5 | $0.00025 | $0.04168 |
| Sonnet 5 | $0.00010 | $0.01667 |
| Haiku 4.5 | $0.00005 | $0.00834 |
Grade A, and why
devsecops-complete-audit 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 yesterday.
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 — 1,861 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🛡️ SKILL — AUDIT COMPLET, NETTOYAGE, DETTE TECHNIQUE & DURCISSEMENT DEVSECOPS
0. MISSION
Tu es chargé d'effectuer un audit professionnel complet d'un projet logiciel existant.
Ton rôle combine :
- expertise en architecture logicielle ;
- expertise frontend/backend ;
- expertise DevOps ;
- expertise Git/GitHub ;
- expertise CI/CD ;
- expertise cybersécurité défensive ;
- expertise en analyse de dette technique ;
- expertise en sécurité applicative ;
- expertise en qualité logicielle ;
- expertise en observabilité ;
- expertise en performance ;
- expertise en préparation à la production.
L'objectif n'est PAS simplement de « nettoyer le code ».
L'objectif est de produire un projet :
- maintenable ;
- cohérent ;
- minimal ;
- sécurisé ;
- testable ;
- observable ;
- reproductible ;
- documenté ;
- performant ;
- compatible avec son environnement de production ;
- sans régression fonctionnelle ;
- avec une surface d'attaque réduite ;
- avec une dette technique maîtrisée.
Priorité absolue :
COMPRENDRE → PROUVER → CORRIGER → TESTER → VÉRIFIER → DOCUMENTer.
Ne jamais modifier du code uniquement parce qu'il semble ancien, inutile, étrange ou redondant.
1. PRINCIPES DIRECTEURS
1.1 Règle absolue : aucune suppression sans preuve
NE SUPPRIMER AUCUN :
- fichier ;
- composant ;
- fonction ;
- classe ;
- endpoint ;
- route ;
- middleware ;
- hook ;
- service ;
- worker ;
- cron ;
- script ;
- migration ;
- configuration ;
- dépendance ;
- variable d'environnement ;
- mécanisme de sécurité ;
- procédure d'administration ;
- procédure de récupération.
simplement parce qu'il semble inutilisé.
Avant toute suppression, vérifier :
- références directes ;
- références indirectes ;
- imports ;
- exports ;
- dynamic imports ;
- chargement dynamique ;
- routes SPA ;
- routes backend ;
- endpoints API ;
- scripts ;
- workers ;
- cron ;
- migrations ;
- webhooks ;
- intégrations externes ;
- authentification ;
- autorisation ;
- mécanismes de sécurité ;
- administration ;
- récupération / disaster recovery ;
- configuration de production ;
- CI/CD ;
- tests ;
- génération automatique ;
- documentation opérationnelle.
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.
- yesterday First seen · 1,861 lines · 50 tokens per session scan A 13b70cf3f4fe
devsecops-complete-audit is a skill published in the GitHub repository KxlSys/OpenSkill (2 stars, last pushed 10d ago), licensed MIT. It adds 50 tokens to every session and 8,337 once invoked, about $0.0003 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
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
GRC & Compliance
Governance, risk, and compliance — risk assessment and scoring, control mapping across NIST CSF 2.0 / ISO 27001:2022 / SOC 2 / CIS Controls v8, gap analysis, audit evidence preparation, and security policy generation.
truecourse-list
List TrueCourse violations found in this repository.
skylos-security
Investigate and harden Skylos security behavior. Use when the user asks to validate a security finding, reproduce a scanner bypass, assess false negatives, review LLM evidence filters, analyze CI/cloud policy trust boundaries, classify severity, or add regression tests for security-sensitive analyzer behavior.
aod-orchestrate
Multi-feature orchestration skill that bridges /aod.blueprint output to parallel wave execution. Groups synced GitHub Issues by ICE priority tier (P0/P1/P2) into sequential waves, creates Task records, spawns batch sessions via the orchestrator API, monitors completion, and reports results. Supports --issues…
code-execution-helper
Guide for using code execution capabilities to perform parallel batch processing, conditional filtering, and data aggregation. This skill should be used when agents need to analyze multiple files efficiently, validate large result sets, aggregate data from multiple sources, or reduce token consumption through…