codemap

codemap is a skill for Claude Code, Codex from lglucas/ai-dev-operating-system. It costs 130 tokens per session (1,091 once invoked), scanned A, original, MIT.

A project file index called CODEMAP.md, with one-line descriptions and line counts for code files. It tells developers where to look before searching through the whole repository.

In plain words
What is it for?
Use it when navigating a project, adding, removing, moving, or renaming code files, changing file-purpose descriptions, or checking the map before a release.
Why use it?
It reduces the time spent scanning an unfamiliar codebase and helps keep file descriptions accurate after changes. The map can be regenerated or checked by a script.

Skill for Claude CodeCodex

Part of the ai-dev-operating-system plugin — 28 skills, 11 commands, 12 agents, 1 hook shipped together

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 skills/lglucas/ai-dev-operating-system/codemap
Any agent
npx skills add lglucas/ai-dev-operating-system --skill codemap
Clone the repo
git clone --depth 1 https://github.com/lglucas/ai-dev-operating-system

Made for: Claude Code, Codex.

Or install ai-dev-operating-system, the plugin that ships this one along with the rest of its 28 skills, 11 commands, 12 agents, 1 hook.

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 codemap

README.md
[![agentmods](https://agentmods.dev/badge/skills/lglucas/ai-dev-operating-system/codemap.svg)](https://agentmods.dev/skills/lglucas/ai-dev-operating-system/codemap)
Your own site
<a href="https://agentmods.dev/skills/lglucas/ai-dev-operating-system/codemap"><img src="https://agentmods.dev/badge/skills/lglucas/ai-dev-operating-system/codemap.svg" alt="Measured on agentmods" height="20"></a>
Per session 130 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,091 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 $0.00130 $0.01091
Opus 5 $0.00065 $0.00545
Sonnet 5 $0.00026 $0.00218
Haiku 4.5 $0.00013 $0.00109

Measured 4d ago against content hash 005663630c2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codemap 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 4d 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.

.claude/skills/codemap/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codemap

Antes de procurar, leia o mapa

Se você está prestes a varrer o projeto atrás de um arquivo — pare e leia o CODEMAP.md primeiro. É uma leitura contra dezenas. É literalmente para isso que ele existe.

Se o arquivo não existir, verifique o marcador .aios-self antes de estranhar: dentro do repositório do próprio AI Dev OS não há mapa por design (veja Escopo), e nesse caso procurar direto é o certo. Em projeto derivado, mapa ausente significa que ninguém rodou o gerador ainda — rode.

Se o mapa existe mas não responde, aí sim procure. E quando achar, considere se a descrição daquele arquivo estava ruim: o conserto é melhorar o cabeçalho Purpose: dele.

Regenerar

node scripts/codemap.js

Sobrescreve o CODEMAP.md inteiro. Nunca edite o arquivo à mão — a próxima geração desfaz.

Para verificar sem escrever, como o CI faz:

node scripts/codemap.js --check

Quando regenerar

Momento Por quê
Criou, removeu, renomeou ou moveu arquivo de código a lista fica errada na hora
Mudou o Purpose: de um arquivo a descrição no mapa fica velha
Mudou o número de linhas de um arquivo o mapa grava a contagem exata
Ao fechar sprint sprint-management já toca changelog e docs; o mapa vai junto
Antes de release release-check delega para cá
Depois de refatoração que moveu arquivos é quando o mapa mais diverge

A terceira linha é a que pega desprevenido: como o mapa grava a contagem exata, editar o corpo de um arquivo já mapeado costuma bastar para o --check acusar divergência. Regenere junto com a mudança e comite os dois — é mais barato que descobrir pelo CI vermelho.

O limite de 200 linhas continua sendo só um aviso no mapa, não o gatilho da regeneração. O gatilho é a contagem mudar, qualquer que seja o valor.

De onde vem a descrição

Do cabeçalho que a code-style já exige:

/**
 * Purpose: o que este arquivo resolve, em uma frase.
 * Version: v0.1.0
 * Sprint:  01
 */

Read the full file on GitHub · 84 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. 4d ago First seen · 84 lines · 130 tokens per session scan A 005663630c2b

Subscribe to this mod's changes

codemap is a skill published in the GitHub repository lglucas/ai-dev-operating-system (11 stars, last pushed 25d ago), licensed MIT. It adds 130 tokens to every session and 1,091 once invoked, about $0.0006 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.