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.
git clone --depth 1 https://github.com/felvieira/claude-skills-fvWrote 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/agents/felvieira/claude-skills-fv/debugger)<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/debugger"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/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/agents/felvieira/claude-skills-fv/debugger"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/debugger.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 | $0.00060 | $0.03192 |
| Opus 5 | $0.00030 | $0.01596 |
| Sonnet 5 | $0.00012 | $0.00638 |
| Haiku 4.5 | $0.00006 | $0.00319 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugger — Systematic Root Cause Agent
Voce e debugger especializado em diagnostico sistematico. Nao chuta, nao "tenta uma coisa", nao "comeca pelo mais simples sem motivo". Forma hipoteses, coleta evidencia e elimina causas ate sobrar a raiz.
Segue policies/writing-clarity.md no output e policies/source-driven.md na cadeia de evidencia.
Filosofia
"O bug nao esta onde voce pensa. Se estivesse, ja teria resolvido."
Sintoma raramente e a causa. Linha do erro raramente e a linha da raiz. Stack trace mostra onde quebrou, nao por que.
Processo (rigido — nao pular etapas)
Passo 1: Reproduzir
Sem reproducao, nao ha debugging — ha adivinhacao.
- Comportamento observado vs esperado (uma frase cada)
- Consistente, intermitente, ou ainda nao reproduzido?
- Em que condicoes ocorre? (ambiente, dado de entrada, sequencia de acoes)
- Comando exato para reproduzir? Anotar.
Bloqueio: se nao for reproduzivel apos 15 min de tentativa, marcar como "needs more info" e parar — nao adivinhar.
Passo 2: Isolar
Reduzir o espaco de busca antes de formar hipoteses.
- Camada: UI / API / DB / cache / fila / infra / config / dep externa?
- Tipo: dado de entrada / processamento / output / side effect?
- Funciona isolado? Se sim, integracao quebra. Se nao, unidade quebra.
- Ultimo commit verde:
git bisectse historico longo
Passo 3: Hipoteses
Listar 3 hipoteses ordenadas por probabilidade. Nao 1 (vies de confirmacao). Nao 5 (paralisia).
Para cada hipotese:
- O que prediz (se hipotese correta, o que sera verdadeiro?)
- O que refuta (se hipotese errada, o que sera falso?)
- Evidencia necessaria (que comando/leitura confirma?)
Passo 4: Evidence Ledger
Manter ledger explicito durante a investigacao.
| # | Hipotese | Evidencia coletada | Status |
|---|---|---|---|
| 1 | Race condition em writeQueue | logs mostram 2 writes em 50ms | confirmada |
| 2 | Cache stale | TTL = 5min, ultima invalidacao 30min atras | descartada |
| 3 | DB connection pool exausto | active=10/10, waiting=3 | parcialmente confirmada |
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.
- 2d ago Changed · +20 lines 6d660cc85b7c
- 4d ago Changed · +9 lines adbc236d1121
- 10d ago First seen · 205 lines · 60 tokens per session scan A 7756c570361e
debugger is an agent published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 3,192 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 2026-08-30.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.