onboard

A project-onboarding command that scans an existing codebase and records its structure, tools, entry points, configuration, and modules in ARCHITECTURE.md.

In plain words
What is it for?
It helps document where code lives, how the project starts, which package or workspace tools it uses, and how its main parts fit together.
Why use it?
It gives the brigade planning agent a map of an unfamiliar project, reducing poorly divided or misplaced tasks.

Command

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/ushibo/brigade/onboard
Clone the repo
git clone --depth 1 https://github.com/ushibo/brigade
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,057 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 $0.00018 $0.01057
Opus 5 $0.00009 $0.00528
Sonnet 5 $0.00004 $0.00211
Haiku 4.5 $0.00002 $0.00106

Measured 2d ago against content hash 99a3071f6b30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onboard 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.

commands/onboard.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are onboarding brigade to an existing project. Scan the codebase and produce .planning/ARCHITECTURE.md — a machine-readable project map that manager-agent reads when planning sprints. This is the brownfield counterpart to /brigade:init — init sets up roles, onboard tells brigade what already exists.

When to use

  • First time setting up brigade on an existing codebase (after /brigade:init)
  • After major structural changes (new services, moved directories, new tech stack)
  • When manager-agent makes bad task decompositions because it doesn't understand the project

Step 1 — Scan project structure

Read the project root. Identify:

  1. Top-level layout — what lives where (src/, apps/, packages/, server/, client/, etc.)
  2. Package manager and monorepo toolpackage.json, pnpm-workspace.yaml, Cargo.toml workspace, go.work, turbo.json, nx.json
  3. Entry points — main files, server starts, CLI entry
  4. Config filestsconfig.json, .env.example, docker-compose.yml, CI configs

Use ls, Glob, and Read on key files. Do not read every file — scan structure, read configs and entry points.

Step 2 — Identify modules and their tech stacks

For each logical module/service/package:

  • Name and path
  • Tech stack — language, framework, key libraries
  • Role — which dev agent would own this (frontend-agent, nodejs-agent, rust-agent, golang-agent, devops-agent)
  • Key files — entry point, main config, test config

Read .planning/tasks/ROLES.md if it exists — cross-reference the roles the user already picked with what you find in the codebase.

Step 3 — Map dependencies between modules

Identify how modules talk to each other:

  • Shared types/interfaces
  • API boundaries (REST, gRPC, message queues)
  • Shared packages in monorepo
  • Database schemas shared across services

This is critical for manager-agent — it needs to know which tasks can run in parallel (different modules) vs which have dependencies (shared interfaces).

Read the full file on GitHub · 129 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 · 129 lines · 18 tokens per session scan A 99a3071f6b30

Subscribe to this mod's changes

onboard is a command published in the GitHub repository ushibo/brigade (1 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,057 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 2026-08-31.