init

A project setup command that configures the brigade plugin for a codebase by selecting roles, stack settings, rules, and sprint-workflow files.

In plain words
What is it for?
It helps choose development roles, apply project rules, configure supported technology stacks, and create task-planning scaffolding.
Why use it?
It turns an unconfigured project into one with the files and rules needed for brigade agents to plan and work consistently.

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/init
Clone the repo
git clone --depth 1 https://github.com/ushibo/brigade
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,047 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 $0.00024 $0.03047
Opus 5 $0.00012 $0.01523
Sonnet 5 $0.00005 $0.00609
Haiku 4.5 $0.00002 $0.00305

Measured yesterday against content hash 9d69919eeba1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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 yesterday.

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/init.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are bootstrapping the brigade plugin for the user's current project. This is the single entry point for setup: role selection, stack configuration, rule activation, and sprint-workflow scaffolding.

Step 1 — List what is available

Run these first. Do not hardcode any names — always read from disk:

  • ls ~/.claude/plugins/brigade/agents/ — every agent file is one available role.
  • ls ~/.claude/plugins/brigade/presets/ — stack presets.
  • ls ~/.claude/plugins/brigade/rules/ — individual rule files.

For each agent, read the name and description fields from its frontmatter. For each preset, read the first heading and the short description block.

Step 2 — Ask which roles this project needs

Show a numbered checklist grouped logically. Example:

Which roles does this project need? (pick one or many, e.g. "1,3,5")

Development
  1. frontend      — React/Vue/Svelte, app logic, routing, state
  2. designer      — UI/UX, design systems, visual direction, styled components
  3. nodejs        — Node.js services, APIs, integrations
  4. golang        — Go services, CLI, microservices
  5. devops        — infra, CI/CD, k8s, cloud

  0. skip          — exit without changes
  • review-agent is always auto-included when any dev role is picked. Do not show it in the list.
  • manager-agent is always included — it is the orchestrator. Do not show it in the list.
  • Specialist reviewers (silent-failure-reviewer, test-coverage-reviewer, type-reviewer) and Bug Council agents are spawned conditionally by /brigade:run and /brigade:bug-council. Do not show them in the list.

Wait for the user's selection. Do not proceed until they reply.

Step 3 — Configure each picked role

For each selected role, check whether any preset or rule file applies to it. Today:

Role Ask about Options
frontend Which React flavour? react-mobx-strict, react-basic, or no rules
nodejs Which backend framework? nodejs-fastify, nodejs-express, nodejs-nestjs, or no rules
designer, golang, devops no presets yet skip

Read the full file on GitHub · 267 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. yesterday First seen · 267 lines · 24 tokens per session scan A 9d69919eeba1

Subscribe to this mod's changes

init is a command published in the GitHub repository ushibo/brigade (1 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 3,047 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.