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 GlamgarOnDiscord/claude-saas-blueprint --skill debuggit clone --depth 1 https://github.com/GlamgarOnDiscord/claude-saas-blueprintWrote 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/glamgarondiscord/claude-saas-blueprint/debug)<a href="https://agentmods.dev/skills/glamgarondiscord/claude-saas-blueprint/debug"><img src="https://agentmods.dev/badge/skills/glamgarondiscord/claude-saas-blueprint/debug/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/glamgarondiscord/claude-saas-blueprint/debug"><img src="https://agentmods.dev/badge/skills/glamgarondiscord/claude-saas-blueprint/debug.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 | $0.00022 | $0.00509 |
| Opus 5 | $0.00011 | $0.00254 |
| Sonnet 5 | $0.00004 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
debug 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 10d 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.
What it actually says
Instructions
Phase 1 — Reproduire
- Comprendre le symptôme exact (message d'erreur, comportement attendu vs observé)
- Identifier le fichier et la ligne si disponible
- Identifier le contexte : quand ça arrive, quand ça n'arrive pas
Phase 2 — Isoler (paralléliser via sous-agents)
Lancer en parallèle :
Agent Explore → Tracer le call stack :
- Trouver la fonction qui crash
- Remonter la chaîne d'appels
- Identifier les inputs qui causent le problème
Agent Explore → Chercher des patterns similaires :
- Le même code fonctionne-t-il ailleurs ?
- Y a-t-il eu un changement récent dans le blast radius ?
git log --oneline -10 -- [fichier]pour l'historique récent
Agent WebSearch (si erreur de lib) → Chercher :
- Message d'erreur exact + nom de la lib
- Issues GitHub connues
- Breaking changes dans les mises à jour récentes
Phase 3 — Diagnostiquer
Utiliser l'agent unit-testing:debugger si le problème est complexe.
Checklist de causes courantes :
- Type mismatch (null/undefined inattendu)
- Import cassé ou circulaire
- Variable d'environnement manquante
- Race condition / async mal géré
- Cache stale (build, node_modules, .next)
- Version de dépendance incompatible
- Changement de schema DB sans migration
Phase 4 — Fix
- Écrire le fix minimal ciblé
- Ajouter un test qui aurait attrapé le bug
- Vérifier que le fix ne casse rien d'autre (
tsc --noEmit+ tests) - Documenter dans
.claude/memory/errors.mdsi le pattern est réutilisable
Anti-Patterns de Debug
- Ne PAS ajouter des
console.logpartout → utiliser un breakpoint mental - Ne PAS deviner → vérifier avec des faits (logs, valeurs, types)
- Ne PAS corriger le symptôme → trouver la cause racine
- Ne PAS réessayer en boucle → si 2 tentatives échouent, changer d'approche
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.
- 10d ago First seen · 54 lines · 22 tokens per session scan A 31c7193f3fda
debug is a skill published in the GitHub repository GlamgarOnDiscord/claude-saas-blueprint (2 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 509 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.
Other skills, from other repositories
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
debug-live
Guides root-cause investigations with debugging capabilities by setting breakpoints, starting a debug session, stepping through execution, inspecting variables, and tracing symptoms back to their origin. Prefer it for runtime bugs, failing tests, exceptions, crashes, hangs, wrong/null values, and unexpected output…
debug-helper
Help debug code by analyzing error messages, identifying root causes, and providing fix suggestions.
post-mortem
Diagnose instruction defects and optionally submit Rosetta GitHub issue.