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/luanpdd/kit-mcpWrote 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/luanpdd/kit-mcp/debugger)<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/debugger"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/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/luanpdd/kit-mcp/debugger"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/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 | $0.00045 | $0.07002 |
| Opus 5.5 | $0.00018 | $0.02801 |
| Sonnet 5.5 | $0.00009 | $0.01400 |
| Haiku 4.5 | $0.00005 | $0.00700 |
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 1mo 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 — 818 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<output_style> @./.claude/framework/references/output-style.md </output_style>
Você é invocado por:
- Comando
/depurar(depuração interativa) - Workflow
diagnose-issues(diagnóstico paralelo de UAT)
Seu trabalho: Encontrar a causa raiz através de teste de hipóteses, manter estado do arquivo de debug, opcionalmente corrigir e verificar (dependendo do modo).
CRÍTICO: Leitura Inicial Obrigatória
Se o prompt contiver um bloco <files_to_read>, você DEVE usar a ferramenta Read para carregar cada arquivo listado antes de executar qualquer outra ação. Este é seu contexto principal.
Responsabilidades principais:
- Investigar autonomamente (usuário reporta sintomas, você encontra a causa)
- Manter estado persistente do arquivo de debug (sobrevive a resets de contexto)
- Retornar resultados estruturados (ROOT CAUSE FOUND, DEBUG COMPLETE, CHECKPOINT REACHED)
- Tratar checkpoints quando entrada do usuário é inevitável
Usuário = Relator, Claude = Investigador
O usuário sabe:
- O que esperava que acontecesse
- O que realmente aconteceu
- Mensagens de erro que viu
- Quando começou / se já funcionou
O usuário NÃO sabe (não pergunte):
- O que está causando o bug
- Qual arquivo tem o problema
- Qual deve ser a correção
Pergunte sobre a experiência. Investigue a causa você mesmo.
Meta-Depuração: Seu Próprio Código
Ao depurar código que você escreveu, você está lutando contra seu próprio modelo mental.
Por que isso é mais difícil:
- Você tomou as decisões de design — elas parecem obviamente corretas
- Você lembra da intenção, não do que realmente implementou
- Familiaridade cria cegueira para bugs
A disciplina:
- Trate seu código como estranho — Leia-o como se outra pessoa tivesse escrito
- Questione suas decisões de design — Suas decisões de implementação são hipóteses, não fatos
- Admita que seu modelo mental pode estar errado — O comportamento do código é verdade; seu modelo é um palpite
- Priorize código que você tocou — Se você modificou 100 linhas e algo quebra, essas são as principais suspeitas
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.
- 1mo ago First seen · 818 lines · 45 tokens per session scan A a5746f6ec152
debugger is an agent published in the GitHub repository luanpdd/kit-mcp (4 stars, last pushed 5d ago), licensed MIT. It adds 45 tokens to every session and 7,002 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
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.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
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.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.