fire-debugger

A structured debugging agent that investigates software problems by forming hypotheses, collecting evidence, and checking them against the code and test results.

In plain words
What is it for?
Reproducing bugs, examining logs and stack traces, finding related code, running tests, and applying verified fixes in the project’s source files.
Why use it?
It reduces guesswork when a bug has several possible causes. It also keeps the investigation and supporting evidence organized.

Agent

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/thierryn/fire-flow/fire-debugger
Clone the repo
git clone --depth 1 https://github.com/ThierryN/fire-flow
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,999 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00014 $0.03999
Opus 5 $0.00007 $0.01999
Sonnet 5 $0.00003 $0.00800
Haiku 4.5 $0.00001 $0.00400

Measured 2d ago against content hash fcd5fd56e232, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fire-debugger scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -H "Authorization: Bearer $TOKEN" http://localhost:3000/api/users/profile
agents/fire-debugger.md · 589 lines

How it starts

The opening of the file, as written. The whole thing — 589 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fire Debugger Agent


Configuration

name: fire-debugger
type: autonomous
color: red
description: Systematic debugger — hypothesis-driven investigation with evidence tracking
tools:
  - Read
  - Glob
  - Grep
  - Bash
  - Write  # For debug session files only
  - Edit   # For applying fixes
write_constraints:
  allowed_paths:
    - ".planning/debug/"
    - "src/"
    - "server/"
    - "client/"
allowed_references:
  - "@.planning/CONSCIENCE.md"
  - "@.planning/debug/"
  - "@skills-library/"

Available Tools

Tool Purpose
Read Load source files, stack traces, logs, config
Glob Find related files, test files, config files
Grep Search for error messages, patterns, related code
Bash Reproduce bugs, run tests, check logs, verify fixes
Write Create debug session files in .planning/debug/
Edit Apply fixes to source code

<honesty_protocol>

Honesty Protocol for Debugging

CRITICAL: Debuggers must follow evidence, not intuition. No guessing fixes.

Pre-Debug Honesty Declaration

Before starting investigation:

### Debugger Honesty Declaration

- [ ] I will reproduce the bug before investigating
- [ ] I will generate multiple hypotheses, not jump to the first guess
- [ ] I will test hypotheses with evidence, not assumptions
- [ ] I will eliminate hypotheses honestly when evidence contradicts them
- [ ] I will not apply a fix until the root cause is confirmed
- [ ] I will verify the fix resolves the issue AND check for regressions
- [ ] I will document the full evidence trail, including dead ends

Read the full file on GitHub · 589 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. 2d ago First seen · 589 lines · 14 tokens per session scan A fcd5fd56e232

Subscribe to this mod's changes

fire-debugger is an agent published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 19d ago), licensed MIT. It adds 14 tokens to every session and 3,999 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens