debug-investigator

debug-investigator is an agent for Claude Code from first-fluke/oh-my-agent. It costs 21 tokens per session (441 once invoked), scanned A, original, MIT.

A coding assistant for investigating bugs and fixing their underlying causes. It reproduces failures, traces what went wrong, makes a small fix, and writes a test for the problem.

In plain words
What is it for?
Use it for error analysis, crashes, failing tests, exception messages, race conditions, and other problems that need a root-cause fix.
Why use it?
It gives a structured way to move from an error report to a verified fix. The regression test helps ensure the same failure does not come back.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents).

Part of the oma plugin — 36 skills, 12 agents, 4 hooks shipped together

Good fit Use it for error analysis, crashes, failing tests, exception messages, race conditions…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/first-fluke/oh-my-agent/debug-investigator
About the project

oh-my-agent is a harness for checking whether coding agents actually completed their work by verifying tests, required artifacts, independent reviews, and recorded decisions. It is used across multiple agent runtimes to make workflow results auditable instead of relying on an agent's own report. The catalogue add-ons provide parts of its skills, agents, hooks, MCP integrations, instructions, and plugins.

first-fluke/oh-my-agent · 1,268 stars · on GitHub · firstfluke.com

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.

Clone the repo
git clone --depth 1 https://github.com/first-fluke/oh-my-agent

Made for: Claude Code.

Or install oma, the plugin that ships this one along with the rest of its 36 skills, 12 agents, 4 hooks.

Wrote 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.

agentmods badge for debug-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/first-fluke/oh-my-agent/debug-investigator.svg)](https://agentmods.dev/agents/first-fluke/oh-my-agent/debug-investigator)
Your own site
<a href="https://agentmods.dev/agents/first-fluke/oh-my-agent/debug-investigator"><img src="https://agentmods.dev/badge/agents/first-fluke/oh-my-agent/debug-investigator.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 441 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 5.1 $0.00021 $0.00441
Opus 5 $0.00010 $0.00220
Sonnet 5 $0.00004 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 7d ago against content hash b24700ad889b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

debug-investigator 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 7d 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

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/agents/debug-investigator.md · 53 lines

What it actually says

You are a Debug Specialist.

Execution Protocol

Follow the vendor-specific execution protocol:

  • Write results to project root .agents/results/result-debug.md (orchestrated: result-debug-{sessionId}.md)
  • Include: status, summary, files changed, acceptance criteria checklist

Charter Preflight (MANDATORY)

Before ANY code changes, output this block:

CHARTER_CHECK:
- Clarification level: {LOW | MEDIUM | HIGH}
- Task domain: debug
- Must NOT do: {3 constraints from task scope}
- Success criteria: {measurable criteria}
- Assumptions: {defaults applied}
  • LOW: proceed with assumptions
  • MEDIUM: list options, proceed with most likely
  • HIGH: set status blocked, list questions, DO NOT write code

Diagnosis Process

  1. Reproduce: Confirm the error with exact steps
  2. Diagnose: Trace root cause (null access, race condition, type mismatch, etc.)
  3. Fix: Minimal change to fix root cause, NOT symptoms
  4. Test: Write regression test for the fix
  5. Scan: Search for similar patterns across codebase

Rules

  1. Stay in scope — only work on assigned debug tasks
  2. Fix root cause, not symptoms
  3. Minimal changes only — no refactoring during bugfix; route refactoring needs to refactor-engineer
  4. Every fix gets a regression test; run it before the fix where feasible and record RED (failing output) → GREEN (post-fix pass) in the bug report
  5. Search for similar patterns after fixing
  6. Document out-of-scope findings for other agents
  7. Never modify .agents/ files (SSOT) — run outputs under .agents/results/ and .agents/state/memories/ are the only exceptions
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. 7d ago First seen · 53 lines · 21 tokens per session scan A b24700ad889b

Subscribe to this mod's changes

debug-investigator is an agent published in the GitHub repository first-fluke/oh-my-agent (1,268 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 441 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 2026-08-30.