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/fixgit 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 | $0.00018 | $0.01412 |
| Opus 5 | $0.00009 | $0.00706 |
| Sonnet 5 | $0.00004 | $0.00282 |
| Haiku 4.5 | $0.00002 | $0.00141 |
Grade A, and why
fix 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running a fast-path for bug fixes and small changes. Unlike /brigade:plan, this
command skips the design phase and goes straight to sprint planning with manager-agent.
When to use /brigade:fix vs /brigade:plan
Use /brigade:fix for:
- Bug fixes (one clear symptom, one root cause)
- Small refactors (rename, extract, move)
- Config changes that have behavior but don't need architectural thought
- Dependency updates
- Copy/text changes
- Anything where the "what to build" is obvious and you just need rigor (tests, file ownership, review)
Use /brigade:plan for:
- New features
- Anything that needs to explore alternatives
- Work that touches multiple modules or roles
- Anything where you'd benefit from a written design doc
When in doubt: if you can describe the change in one sentence AND you know exactly
which files to touch, use /brigade:fix. Otherwise use /brigade:plan.
Preflight
- Verify
.planning/tasks/ROLES.mdexists. If missing, tell the user to run/brigade:initfirst and stop. - Verify the working tree is clean. If dirty, tell the user to commit or stash and stop.
Step 1 — Understand the problem (brief)
Unlike /brigade:plan phase 1, don't run a full brainstorming session. Just ask the user for
missing critical info if any:
- If the argument is vague ("fix the bug"), ask: "Which bug? Point me to the error, test, or symptom you're seeing."
- If you don't know which files are affected, ask once: "Which files should I look at?" OR quickly grep for relevant symbols yourself.
- If the fix approach has two obvious paths, ask: "I can do X or Y — which do you prefer?" (One question, not a design session.)
Do not propose multiple approaches, write a design doc, or create a spec file.
Do not ask more than 2 questions. If you need more, stop and suggest /brigade:plan instead.
Step 2 — Spawn manager-agent with fix-mode instructions
Call the Agent tool with:
subagent_type:manager-agentisolation:nonedescription:Plan fix: $ARGUMENTSprompt:Plan a small fix or bug repair. This is fast-path mode — NOT a new feature. User request: $ARGUMENTS Additional context from the user (if any): {paste anything captured in Step 1} Follow your `plan` workflow, but with these constraints: 1. Read .planning/tasks/ROLES.md and the project CLAUDE.md. 2. Read .planning/ARCHITECTURE.md if it exists. 3. Create at MOST 1-3 tasks. Most fixes need 1 task. Only split if the fix genuinely spans multiple roles (e.g. backend change + frontend change) or multiple files that can be worked in parallel. 4. Each task must have: - A clear `role` - `files_modify` listing the exact files (no glob patterns, specific paths) - Required Tests — for bugs, this MUST include a regression test that reproduces the bug. "I verified manually" is not acceptable. 5. Write task specs under .planning/tasks/sprint-N/ (latest open sprint or create new). 6. Update sprint-N/_README.md with a new section for this fix. 7. Assign waves: if 1 task, it's wave 1. If multiple independent tasks, one wave. Do NOT: - Write a design doc - Create multiple alternatives - Expand scope beyond what the user asked for - Add "while I'm here" improvements - Write any feature code Return: task IDs created, which wave, which files they'll touch, and whether they include regression tests.
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.
- yesterday First seen · 136 lines · 18 tokens per session scan A 2558a48c1ffd
fix 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 1,412 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
OPSX: Propose
Propose a new change - create it and generate all artifacts in one step.
create
Scaffold a new plugin with directory structure, manifests, and marketplace registration.
compose-stack
Compose a sequenced Intelligence Stack Plan for a sovereign person. Analyzes their Genius Profile + Freedom Path + stated priorities + life stage, then sequences which of the 9 layers activate first, second, third. Produces a 90-day sprint plan for building their full intelligence stack. For humans with Genius Profile…
bugfix
TDD-driven bugfix workflow: tester writes failing test (RED) → developer fixes (GREEN) → developer refactors (REFACTOR) → reviewer validates. Accepts issue number, description, or both. Auto-creates PR unless --no-pr flag is passed.
develop
Implement skill development issues with TDD-governed workflow.
dev-task
Create an agent team to develop: Developer teammate + Code-tester teammate + QA-tester teammate + Reviewer teammate + Researcher subagent → implements .dev/cdt/plans/plan-$TIMESTAMP.md in waves.