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.
npx agentmods add commands/ushibo/brigade/plangit clone --depth 1 https://github.com/ushibo/brigadeWhat 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 | $0.00014 | $0.03625 |
| Opus 5 | $0.00007 | $0.01813 |
| Sonnet 5 | $0.00003 | $0.00725 |
| Haiku 4.5 | $0.00001 | $0.00363 |
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.
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.mdreference. Go straight to phase 2 with the file as the spec source.
Preflight
-
Verify
.planning/tasks/ROLES.mdexists. If missing, tell the user to run/brigade:initfirst and stop. -
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:onboardfirst, 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.mdBEFORE phase 2 runs. Set an internal flagneeds_architecture = truefor 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.
-
-
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.
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 · 399 lines · 14 tokens per session scan A 19af80e3a61a
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.
Other commands, from other repositories
hire-assess-fit
Run a culture-add fit assessment for a candidate (NOT culture-fit). Names what the team currently lacks, names what this candidate adds, runs gap-bridge analysis. Refuses generic "great culture fit" framing — culture-fit reproduces, culture-add expands. Used as a SUPPLEMENT to the structured rubric, never as a…
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
audit-plugin
Audit plugin skills, commands, and agents for structure, size, and naming issues.
earnings-week
Upcoming earnings + dividend events for portfolio holdings over next N weeks (default 2). Surfaces event clusters (multiple positions on same day = concentrated event risk), consensus estimates, key questions to watch. Run before FOMC/earnings-heavy weeks.
eval
View agent evaluations and detect regressions.
auto
AI auto strategy executor. Analyzes task and automatically selects and executes the best strategy: direct execution, hybrid-auto PRD generation, hybrid-worktree isolated development, or mega-plan multi-feature orchestration.