What is ace:map-codebase?

A command for producing a structured map of an existing codebase by using several exploration agents. The map records its technology stack, architecture, file structure, conventions, tests, integrations, and concerns.

Use it when joining a brownfield project, planning a refactor, or documenting a codebase with more than a few files.

It reduces the time and risk involved in understanding an unfamiliar project before making large changes. It also creates a reference that can be refreshed after major edits.

ace:map-codebase — Command by AgriciDaniel

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 commands/agricidaniel/ace-claude-code/map-codebase

Clone the repo

git clone --depth 1 https://github.com/AgriciDaniel/ace-claude-code

Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 993 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.

Model	Per session	Once invoked
Fable 5	$0.00013	$0.00993
Opus 5	$0.00006	$0.00496
Sonnet 5	$0.00003	$0.00199
Haiku 4.5	$0.00001	$0.00099

Measured 2d ago against content hash fafaa35c2381, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ace:map-codebase 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.

.ace/commands/map-codebase.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

This enables informed planning for brownfield projects.

Output: .ace/planning/codebase/ with:

STACK.md
ARCHITECTURE.md
STRUCTURE.md
CONVENTIONS.md
TESTING.md
INTEGRATIONS.md
CONCERNS.md

Load templates: @.ace/templates/codebase/stack.md @.ace/templates/codebase/architecture.md @.ace/templates/codebase/structure.md @.ace/templates/codebase/conventions.md @.ace/templates/codebase/testing.md @.ace/templates/codebase/integrations.md @.ace/templates/codebase/concerns.md

<when_to_use> Use map-codebase for:

Brownfield projects before initialization
Refreshing codebase map after significant changes
Onboarding to unfamiliar codebase
Before major refactoring

Skip map-codebase for:

Greenfield projects with no code yet
Trivial codebases (<5 files) </when_to_use>

1. Check Prerequisites

if .ace/planning/codebase/ exists:
    Ask: "Codebase map exists. Refresh it?"
    Options: "Yes, refresh" / "Skip"

2. Create Directory

mkdir -p .ace/planning/codebase/

3. Spawn 4 Parallel Explore Agents

CRITICAL: Send ALL 4 Task calls in ONE message for maximum parallelism.

Agent 1: Stack + Integrations (Technology Focus)

Analyze this codebase for technology stack and external integrations.

Produce findings for:
1. STACK.md - Languages, frameworks, key dependencies
2. INTEGRATIONS.md - APIs, databases, external services

Use templates from .ace/templates/codebase/
Focus area: $ARGUMENTS (if provided)

Agent 2: Architecture + Structure (Organization Focus)

Analyze this codebase for architecture and structure.

Produce findings for:
1. ARCHITECTURE.md - System design, patterns, data flow
2. STRUCTURE.md - Directory layout, module organization

Use templates from .ace/templates/codebase/
Focus area: $ARGUMENTS (if provided)

Read the full file on GitHub · 165 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.

2d ago First seen · 165 lines · 13 tokens per session scan A fafaa35c2381

Subscribe to this mod's changes

ace:map-codebase is a command published in the GitHub repository AgriciDaniel/ace-claude-code (24 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 993 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.

Planning Testing ai claude-code claude-code-skill developer-tools open-source

ace:map-codebase

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

1. Check Prerequisites

2. Create Directory

3. Spawn 4 Parallel Explore Agents

Agent 1: Stack + Integrations (Technology Focus)

Agent 2: Architecture + Structure (Organization Focus)

What this file has done since we first saw it

Other commands, from other repositories

canvas

document

review

test

fix-issue

migrate