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 bug-debuggergit 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/bug-debugger)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/bug-debugger"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/bug-debugger/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/bug-debugger"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/bug-debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00112 | $0.01312 |
| Opus 5 | $0.00056 | $0.00656 |
| Sonnet 5 | $0.00022 | $0.00262 |
| Haiku 4.5 | $0.00011 | $0.00131 |
Grade A, and why
bug-debugger 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 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.
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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Debugger
Étape 0 — Collecter le contexte minimal
Avant toute hypothèse, s'assurer d'avoir :
| Info | Exemples |
|---|---|
| Message d'erreur complet | stack trace, code HTTP, errno |
| Comportement attendu vs observé | "devrait retourner 200, retourne 500" |
| Reproductibilité | toujours / parfois / en prod seulement |
| Dernière modification | commit, déploiement, changement config |
| Environnement | OS, version runtime, variables d'env |
Si un de ces éléments manque et bloque le diagnostic → demander uniquement ce qui est nécessaire, pas tout à la fois.
Étape 1 — Lire l'erreur sans sauter aux conclusions
TypeError: Cannot read properties of undefined (reading 'id')
at getUserName (user.js:42:18)
at processRequest (api.js:17:5)
- Lire le type d'erreur :
TypeError,NullReferenceException,SIGSEGV… - Localiser le premier frame applicatif (ignorer les frames de libs tierces).
- Identifier l'opération qui échoue : accès propriété, appel fonction, cast, IO…
Étape 2 — Formuler 3 hypothèses classées par probabilité
Format attendu :
- (Probable)
userestundefinedcar la DB ne retourne rien pour cet ID → vérifier avecconsole.log(user)avant la ligne 42. - (Possible) La fonction est appelée avant que la promesse soit résolue → ajouter
await. - (Moins probable) Race condition sur un cache partagé → vérifier si ça arrive en parallèle.
Règle : ne pas proposer plus de 3 hypothèses sans validation intermédiaire.
Étape 3 — Vérification rapide par hypothèse
JavaScript/TypeScript
// Inspecter sans modifier le flux
console.log('[debug] user:', JSON.stringify(user, null, 2));
// Vérifier le type exact
console.log('[debug] typeof user:', typeof user, user instanceof Object);
Python
import pprint
print('[debug] user:', pprint.pformat(user))
# Ou avec breakpoint natif (Python 3.7+)
breakpoint()
.NET / C#
// Ajouter un point de log avant la ligne incriminée
_logger.LogDebug("user={User}", JsonSerializer.Serialize(user));
// Ou utiliser le debugger avec Watch sur l'expression
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 · 159 lines · 112 tokens per session scan A 2440044def4e
bug-debugger is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 19d ago), licensed MIT. It adds 112 tokens to every session and 1,312 once invoked, about $0.0006 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
debug
Systematic debugging via logs, health checks, hypothesis-driven investigation. Triggers: debug, error, trace root cause, fix bug, reproduce symptom, investigation.
introspect
Agent self-debugging and recovery. Use when stuck in loops, making repeated errors, or quality degrades. Triggers: introspect, self-debug, stuck, loop, why failing.
fix
Applies targeted fix to known bug/lint error, verifies with same command that surfaced it. Triggers: fix, apply fix, fix bug, fix lint, targeted fix.
git-mastery
Advanced Git: rebase, bisect, reflog, cherry-pick, worktrees, LFS. Triggers: rebase, bisect, cherry-pick, reflog, force push, merge conflict, worktree.
lint
Runs linter+typechecker with auto-detected toolchain (ruff/mypy, eslint/tsc, phpstan, golangci-lint, clippy). Triggers: lint, typecheck, static analysis.
performance-profiling
Performance: golden signals, p50/p95/p99, flame graphs, load testing. Triggers: performance, slow, latency, p99, flame graph, bottleneck, memory leak.