plan

A planning command that first turns a feature request into an agreed design, then divides it into sprint tasks. TDD is not mentioned, and a sprint is a planned group of development work.

In plain words
What is it for?
Brainstorming features, writing a design, checking project architecture, and creating task specifications in work waves.
Why use it?
It prevents detailed task planning from starting before the project design and architecture have been reviewed.

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/plan
Clone the repo
git clone --depth 1 https://github.com/ushibo/brigade
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,625 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 $0.00014 $0.03625
Opus 5 $0.00007 $0.01813
Sonnet 5 $0.00003 $0.00725
Haiku 4.5 $0.00001 $0.00363

Measured 2d ago against content hash 19af80e3a61a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan 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/plan.md · 399 lines

How it starts

The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running the full planning pipeline for the user's feature request. This command has TWO phases: first a design phase (brainstorming → spec), then a sprint planning phase (manager-agent → task specs).

HARD GATE between phases: No sprint planning until the user approves the design.

Mode detection

Check $ARGUMENTS for this flag:

  • --skip-design — skip phase 1 entirely. Requires a @file.md reference. Go straight to phase 2 with the file as the spec source.

Preflight

  1. Verify .planning/tasks/ROLES.md exists. If missing, tell the user to run /brigade:init first and stop.

  2. Architecture must always be agreed before sprint planning. Check for .planning/ARCHITECTURE.md:

    • Brownfield (project has source code in src/, apps/, packages/, lib/, cmd/, pkg/) AND no ARCHITECTURE.md → tell the user to run /brigade:onboard first, stop. The architecture must be mapped from existing code before tasks can be planned.

    • Greenfield (no source code yet) AND no ARCHITECTURE.md → DO NOT skip. Instead, tell the user that architecture will be agreed as part of phase 1 (design phase). Phase 1 will propose the project architecture from the spec, get user approval, and write it to .planning/ARCHITECTURE.md BEFORE phase 2 runs. Set an internal flag needs_architecture = true for use in phase 1.

    • ARCHITECTURE.md exists → no action, proceed.

    The principle: manager-agent must always have an agreed architecture document to read. No exceptions for greenfield, no silent skips, no "trust me bro" planning.

  3. manager-agent (used in phase 2) is a planner only — it writes task specs and updates the sprint _README.md. It never spawns workers. Execution is /brigade:run's job at the top level.

Decision — phase 1 mode

Phase 1 (design / brainstorming) is ALWAYS run by /brigade:plan — even when the user provides a file reference. The file becomes input to brainstorming, not a bypass.

Read the full file on GitHub · 399 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 · 399 lines · 14 tokens per session scan A 19af80e3a61a

Subscribe to this mod's changes

plan is a command published in the GitHub repository ushibo/brigade (1 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 3,625 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.