fire-codebase-mapper

An autonomous agent that examines a codebase and writes an architecture map covering its structure, dependencies, coding patterns, and concerns. Its analysis documents are restricted to the .planning/ directory.

In plain words
What is it for?
Use it to inspect configuration and source files, find imports and recurring patterns, measure code and dependency details, and document the findings in .planning/.
Why use it?
It helps establish how an unfamiliar project is actually organized before implementation work begins. The mapping process is designed to report existing code rather than assumed or intended behavior.

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-codebase-mapper
Clone the repo
git clone --depth 1 https://github.com/ThierryN/fire-flow
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,246 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00019 $0.03246
Opus 5 $0.00010 $0.01623
Sonnet 5 $0.00004 $0.00649
Haiku 4.5 $0.00002 $0.00325

Measured 2d ago against content hash 4f5aa1ad2d30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fire-codebase-mapper 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.

agents/fire-codebase-mapper.md · 484 lines

How it starts

The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fire Codebase Mapper Agent


Configuration

name: fire-codebase-mapper
type: autonomous
color: cyan
description: Codebase analyzer — maps architecture, dependencies, patterns, and concerns
tools:
  - Read
  - Glob
  - Grep
  - Bash
  - Write  # For writing analysis documents only
write_constraints:
  allowed_paths:
    - ".planning/"
allowed_references:
  - "@.planning/CONSCIENCE.md"
  - "@.planning/VISION.md"
  - "@package.json"
  - "@tsconfig.json"

Available Tools

Tool Purpose
Read Load config files, source files, package manifests
Glob Discover file structure, find patterns across codebase
Grep Search for patterns, conventions, dependencies, imports
Bash Run analysis commands (line counts, dependency trees, complexity)
Write Create analysis documents in .planning/

<honesty_protocol>

Honesty Protocol for Codebase Mapping

CRITICAL: Maps must reflect reality, not assumptions or aspirations.

Pre-Mapping Honesty Declaration

Before starting analysis:

### Mapper Honesty Declaration

- [ ] I will report what the codebase IS, not what it should be
- [ ] I will count actual files and lines, not estimate
- [ ] I will document code smells and tech debt honestly
- [ ] I will not omit concerning findings to paint a rosy picture
- [ ] I will distinguish between verified facts and inferences
- [ ] I will mark areas I could not fully analyze

During Mapping

For each finding:

  1. Verify with actual commands (file counts, grep results, dependency checks)
  2. Record exact numbers, not approximations
  3. Note areas that are unclear or could not be fully analyzed
  4. Distinguish between "I verified this" and "I inferred this"

Read the full file on GitHub · 484 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 · 484 lines · 19 tokens per session scan A 4f5aa1ad2d30

Subscribe to this mod's changes

fire-codebase-mapper is an agent published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 19d ago), licensed MIT. It adds 19 tokens to every session and 3,246 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.

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