openpua

A structured method for helping an AI agent investigate and debug difficult technical problems.

In plain words
What is it for?
Use it when debugging software failures that need several investigation paths and careful diagnosis.
Why use it?
It reduces premature conclusions by requiring the agent to check errors, test possible causes, consult relevant documentation, and find the underlying problem.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/kxlsys/openskill/openpua
Any agent
npx skills add KxlSys/OpenSkill --skill openpua
Clone the repo
git clone --depth 1 https://github.com/KxlSys/OpenSkill

Made for: Claude Code, Codex.

Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 681 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00681
Opus 5 $0.00005 $0.00341
Sonnet 5 $0.00002 $0.00136
Haiku 4.5 $0.00001 $0.00068

Measured 2d ago against content hash 73a93fbe7b52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openpua 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 2d 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.

skills/ai/openpua/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenPUA

Description

OpenPUA est une skill open source conçue pour améliorer la persévérance et la rigueur des agents IA lors des tâches complexes de débogage.

Au lieu d'accepter rapidement un échec ou une impasse, OpenPUA impose une méthodologie structurée qui pousse l'agent à :

  • Vérifier systématiquement les journaux d'erreurs
  • Explorer plusieurs pistes de résolution
  • Consulter la documentation pertinente
  • Tester différentes hypothèses
  • Identifier la cause racine du problème
  • Éviter les boucles de raisonnement répétitives.

Le projet applique une approche d'escalade progressive et des checklists obligatoires afin de réduire les abandons prématurés lors des investigations techniques.


Pourquoi nous le recommandons

OpenPUA démontre parfaitement la puissance du standard Agent Skills.

Cette skill ne fournit pas un simple prompt.

Elle implémente :

  • Une méthodologie de débogage réutilisable
  • Des règles comportementales pour les agents
  • Un processus d'investigation structuré
  • Une amélioration de la qualité des diagnostics.

Elle constitue un excellent exemple de ce qu'une Skill bien conçue peut apporter à un agent IA.


Fonctionnalités principales

Escalade progressive

Système de plusieurs niveaux visant à empêcher les abandons précoces et à encourager l'exploration de solutions alternatives.

Checklist obligatoire

Validation systématique de plusieurs éléments avant de conclure à un échec :

  • Logs
  • Dépendances
  • Configuration
  • Documentation
  • Hypothèses alternatives
  • Validation finale

Méthodologie de débogage

Approche structurée :

  1. Reproduire
  2. Isoler
  3. Formuler une hypothèse
  4. Tester
  5. Vérifier

Cas d'utilisation

  • Débogage logiciel
  • Résolution d'erreurs CI/CD
  • Analyse d'échecs de déploiement
  • Investigation de problèmes réseau
  • Dépannage DevOps
  • Analyse de bugs complexes
  • Support technique avancé

Compatibilité

Compatible avec :

  • Claude Code
  • OpenAI Codex CLI
  • Cursor
  • OpenCode
  • GitHub Copilot
  • Agents compatibles Agent Skills

Read the full file on GitHub · 134 lines

Changes

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.

  1. 2d ago First seen · 134 lines · 11 tokens per session scan A 73a93fbe7b52

Subscribe to this mod's changes

openpua is a skill published in the GitHub repository KxlSys/OpenSkill (2 stars, last pushed 11d ago), licensed MIT. It adds 11 tokens to every session and 681 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.

Related

Other skills, from other repositories

Troubleshooting Guide Builder

Builds a structured troubleshooting guide with symptom → cause → fix format for any tool or system.

Notysoty/openagentskills · 25 tokens

repo-doctor

Activate when a developer encounters a broken repository state, failed startup commands, missing runtime dependencies, unconfigured virtual environments, or mysterious build crashes — trigger phrasings include "why won't my project start", "run a health check on this repo", "diagnose my codebase", "npm run dev is…

ieeecsopen/mcp-cs · 138 tokens

etsy-category-listing

Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…

browser-act/skills · 209 tokens

human-approval

Request human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs /…

Prismer-AI/PrismerCloud · 168 tokens

firebase-analytics

Use when logging analytics events, setting user properties, configuring default event parameters, building funnels, or adding screen-view tracking.

evanca/flutter-ai-rules · 28 tokens

firebase-remote-config

Use when implementing feature flags, running A/B tests, setting parameter defaults, fetching/activating config, or enabling real-time config updates.

evanca/flutter-ai-rules · 33 tokens