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/bidiche49/claude-conf/debug-forensicnpx skills add Bidiche49/claude-conf --skill debug-forensicgit clone --depth 1 https://github.com/Bidiche49/claude-confWrote 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/bidiche49/claude-conf/debug-forensic)<a href="https://agentmods.dev/skills/bidiche49/claude-conf/debug-forensic"><img src="https://agentmods.dev/badge/skills/bidiche49/claude-conf/debug-forensic.svg" alt="Measured on agentmods" 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 | $0.00077 | $0.04006 |
| Opus 5 | $0.00039 | $0.02003 |
| Sonnet 5 | $0.00015 | $0.00801 |
| Haiku 4.5 | $0.00008 | $0.00401 |
Grade A, and why
debug-forensic 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 3d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
debug-forensic — Recadrage forensique d'une session de debug
Ton role : transformer une investigation qui derive (accumulation d'hypotheses, lecture de plus en plus de fichiers, "ca pourrait etre X ou Y") en une posture forensique stricte. Tu produis soit (a) un prompt a coller dans une session vierge, soit (b) un bloc de recadrage a injecter dans la conv courante.
Posture imposee au prompt produit : donnees > inference > UNE hypothese > UN test decisif > STOP. Pas de speculation, pas de refactor preventif, pas de "lire tout le repo".
Etape 1 — Detecter le mode
Diagnostique la conversation courante avant toute autre action.
| Signal | Mode |
|---|---|
| Conv contient deja des logs concrets, des hypotheses testees, des fichiers lus, des eliminations explicites | AUTO-EXTRACT |
| Conv neuve, ou bug juste mentionne sans investigation | INTERVIEW |
Argument new passe au skill |
force INTERVIEW |
Argument here passe au skill |
force la sortie en bloc de recadrage (pas de nouvelle conv) |
Annonce le mode detecte en UNE ligne : Mode: AUTO-EXTRACT — j'ai trouve N donnees factuelles et M eliminations dans la conv.
Etape 2 — Collecter le contexte
Mode AUTO-EXTRACT
Scanne la conversation et extrait :
- Symptome exact : ce qui est observe (ex: "freeze + hot restart impossible apres push de MaterialPageRoute X").
- Donnees ground-truth : logs precis, traces, comportement reproductible. UNE phrase factuelle par donnee.
- Eliminations : hypotheses deja testees ET invalidees, avec la preuve (ex: "ce n'est pas la memoire — heap stable a 80MB pendant le freeze").
- Fichiers deja lus : chemins exacts.
- Zones suspectes restantes : ce qui n'a pas encore ete teste mais qui pourrait causer le bug.
- Plateforme / stack / version : iOS 17.4, Flutter 3.22, Dart 3.4, etc.
Si une donnee critique manque (logs absents, repro non confirmee, version inconnue), groupe toutes les questions en UN SEUL message plutot que de poser plusieurs questions a la suite.
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.
- 3d ago First seen · 298 lines · 0 tokens per session scan A 4a1cb13a53c4
debug-forensic is a skill published in the GitHub repository Bidiche49/claude-conf (2 stars, last pushed 4mo ago), licensed MIT. It adds 77 tokens to every session and 4,006 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 2026-08-31.
Other skills, from other repositories
hooks-eval
Evaluate hook security, performance, and SDK compliance. Use for audits.
webmcp-setup
Bootstraps webmcp-react into an existing React or Next.js app. Installs dependencies, adds WebMCPProvider, creates a first tool, and configures the MCP client bridge. Use when the user wants to set up WebMCP, add MCP tools to their app, integrate webmcp-react, or make their React app accessible to AI agents.
goal
Run a large or unfamiliar goal through the full ballast pipeline — mobilize what you already hold, terrain scan, full skeleton, atomic foundation learning with verification, then build from bedrock to a verified done. Use when the user hands over a big goal, enters a new field, or asks to learn X in order to achieve Y.
report
Read the delivery log and say which rules actually fire, which never have, and what to prune or fix. Use when the user asks whether ballast is doing anything, wants to clean up their rule catalog, or on a periodic review.
engram
Claude Engram persistent memory — quick reference for all MCP tools and automatic hook behaviors. Use when you need to remember how to store, search, or manage memories, or query session history.
eval-harness
Assessment-driven development — Quantify code generation quality with pass@k / pass^k metrics, automatically scored by Grader.