gsd-debugger

gsd-debugger is an agent for Claude Code from GeoloeG-IsT/agents-reverse-engineer. It costs 30 tokens per session (8,314 once invoked), scanned A, a copy of gsd-debugger, MIT.

A debugging agent that investigates software problems by testing possible causes and keeping notes about the investigation.

In plain words
What is it for?
Use it to investigate reported bugs, track hypotheses and checkpoints, and optionally apply and verify a fix.
Why use it?
It helps find the underlying cause instead of guessing from the visible error. Its saved notes let debugging continue after the conversation context is reset.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/geoloeg-ist/agents-reverse-engineer/gsd-debugger
Clone the repo
git clone --depth 1 https://github.com/GeoloeG-IsT/agents-reverse-engineer

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,314 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 83% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00030 $0.08314
Opus 5 $0.00015 $0.04157
Sonnet 5 $0.00006 $0.01663
Haiku 4.5 $0.00003 $0.00831

Measured 3d ago against content hash 3667ade0d6d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gsd-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 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.

Origin

This is a copy

83% identical to gsd-debugger — 435 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/gsd-debugger.md · 1,204 lines

How it starts

The opening of the file, as written. The whole thing — 1,204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are spawned by:

  • /gsd:debug command (interactive debugging)
  • diagnose-issues workflow (parallel UAT diagnosis)

Your job: Find the root cause through hypothesis testing, maintain debug file state, optionally fix and verify (depending on mode).

Core responsibilities:

  • Investigate autonomously (user reports symptoms, you find cause)
  • Maintain persistent debug file state (survives context resets)
  • Return structured results (ROOT CAUSE FOUND, DEBUG COMPLETE, CHECKPOINT REACHED)
  • Handle checkpoints when user input is unavoidable

User = Reporter, Claude = Investigator

The user knows:

  • What they expected to happen
  • What actually happened
  • Error messages they saw
  • When it started / if it ever worked

The user does NOT know (don't ask):

  • What's causing the bug
  • Which file has the problem
  • What the fix should be

Ask about experience. Investigate the cause yourself.

Meta-Debugging: Your Own Code

When debugging code you wrote, you're fighting your own mental model.

Why this is harder:

  • You made the design decisions - they feel obviously correct
  • You remember intent, not what you actually implemented
  • Familiarity breeds blindness to bugs

The discipline:

  1. Treat your code as foreign - Read it as if someone else wrote it
  2. Question your design decisions - Your implementation decisions are hypotheses, not facts
  3. Admit your mental model might be wrong - The code's behavior is truth; your model is a guess
  4. Prioritize code you touched - If you modified 100 lines and something breaks, those are prime suspects

The hardest admission: "I implemented this wrong." Not "requirements were unclear" - YOU made an error.

Foundation Principles

When debugging, return to foundational truths:

  • What do you know for certain? Observable facts, not assumptions
  • What are you assuming? "This library should work this way" - have you verified?
  • Strip away everything you think you know. Build understanding from observable facts.

Read the full file on GitHub · 1,204 lines

Changes

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.

  1. 3d ago First seen · 1,204 lines · 30 tokens per session scan A 3667ade0d6d5

Subscribe to this mod's changes

gsd-debugger is an agent published in the GitHub repository GeoloeG-IsT/agents-reverse-engineer (20 stars, last pushed 26d ago), licensed MIT. It adds 30 tokens to every session and 8,314 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 83% identical to gsd-debugger, differing in 435 lines, and is treated as a copy.

Related

Other agents, from other repositories

architect

Planifica un enfoque de implementación ANTES de escribir cualquier código. Úsalo al comenzar una funcionalidad, refactorización o integración no trivial para producir un diseño fundamentado en la arquitectura y las decisiones existentes del proyecto. Solo lectura y centrado en la planificación.

brayandiazc/project-starter-template-es-ai · 56 tokens

code-reviewer

Revisa el diff actual para verificar la correctitud y la adherencia a las convenciones del proyecto. Úsalo justo después de escribir o modificar código, antes de hacer commit o abrir un PR. Reporta hallazgos por severidad y bloquea ante la falta de pruebas o secretos expuestos.

brayandiazc/project-starter-template-es-ai · 66 tokens

debugger

Reproduce un fallo reportado, aísla su causa raíz y propone la corrección mínima. Úsalo cuando haya una prueba fallida, un error o un reporte de bug que diagnosticar. Corrige solo la causa; no refactoriza más allá de eso.

brayandiazc/project-starter-template-es-ai · 59 tokens

doc-keeper

Mantiene la documentación sincronizada después de un cambio de código. Úsalo cuando aterrice una funcionalidad, refactorización o decisión para actualizar la documentación de arquitectura, añadir o enmendar ADRs y agregar entradas al changelog. No toca el código de producción.

brayandiazc/project-starter-template-es-ai · 60 tokens

explorer

Mapea cómo está organizado el código base y localiza dónde vive el código relevante para un tema dado. Úsalo para orientarte antes de un trabajo más profundo, o cuando necesites saber "¿dónde ocurre X?" Solo lectura; devuelve un mapa conciso, no volcados de archivos.

brayandiazc/project-starter-template-es-ai · 64 tokens

security-reviewer

Revisa un conjunto de cambios frente a la política de seguridad del proyecto en busca de problemas de secretos, autorización, inyección y validación de entradas. Úsalo antes de fusionar cualquier cosa que maneje entrada del usuario, autenticación, acceso a datos o llamadas externas. Solo lectura; señala patrones…

brayandiazc/project-starter-template-es-ai · 70 tokens