Skip to content

Quickstart ​

Muster turns an outcome into finished work. You give it a goal in plain language; it picks the right tools for each piece and drives toward your success criteria, showing its reasoning the whole way.

Choose a mode by task ​

Muster has seven modes, including Design for human-facing work and Init for native repository instruction setup. Start with the result you need:

Shape an outcome or a backlog before work startsUse Plan to inspect the checked plan and approve it.
Deliver an outcome or a backlog end to endUse Go for the hands-off lifecycle, attended or scheduled.
Reproduce and fix one failureUse Diagnose.
Find and fix broad codebase risksUse Audit.
Create or improve a human-facing surfaceUse Design.
Turn decisions into backlog itemsUse Capture.
Prepare a repository for MusterUse Init.

If you have not installed Muster yet, choose your harness first.

On Codex?

Every mode below is available on Codex as a skill ($muster-plan, $muster-go, and so on) once Muster's managed profiles and plugin are installed. See the Codex guide for that install path. If something does not appear or behaves oddly, start at Troubleshooting.

Plan and review: /muster:plan ​

The approve-first planner. One muster preflight call sizes up the outcome; if it is unclear, Muster asks up to four questions in one prompt and records your answers as decisions in the run's CONTEXT.md. Then the muster:make-plan workflow writes PLAN.md and has a checker review it (revising at most three times), and Plan stops for your approval: Approve & build continues as /muster:go on the same branch, Revise re-plans with your feedback, Cancel stops.

sh
/muster:plan Add rate limiting to the public API with tests

Plan also takes a backlog (/muster:plan .muster/backlog.md): every item gets its own checked plan, and you approve the batch once.

Skip the per-run Workflow prompt

Plan and Go call Claude Code's Workflow tool, which asks for consent per run in manual and accept-edits modes. Add Workflow(muster:make-plan), Workflow(muster:build) and Workflow(muster:backlog) to your allow rules to skip it.

Hands-off delivery: /muster:go ​

The full lifecycle, hands-off. It plans like Plan, then commits the build arguments (muster build-args), runs the muster:build workflow (each wave's tasks in parallel isolated worktrees, a reviewer with at most two fix rounds, one verifier), merges the waves with muster merge-wave (which re-checks every claimed commit and re-runs the planned verify commands), reports the verification result, and asks how to merge. It only stops for an unclear outcome, an escalation, or that merge decision.

sh
/muster:go Resolve all open issues and update the README

You can also hand it a GitHub issue reference or a backlog:

sh
/muster:go #42
/muster:go .muster/backlog.md

For a scheduled run (a Claude Code Routine, cron with claude -p "/muster:go <outcome>", or a cloud scheduled task), Go asks nothing, records gaps as assumptions, and ends at a pull request instead of merging into your base branch. If a run is interrupted, muster next --run <runId> tells you where it stopped and /muster:go --run <runId> picks it up.

Fix a bug: /muster:diagnose ​

Failure-first. Reproduce, find the root cause via systematic debugging, fix, add a regression test, verify. No symptom-patching.

sh
/muster:diagnose Paste a failing test or stack trace here

Sweep the codebase: /muster:audit ​

Breadth-first review and fix. It fans out six read-only dimension reviews in parallel (architecture, tech-debt, coverage, simplification, readability, security), consolidates a ranked ledger, then fixes everything with tests and verifies.

sh
/muster:audit
/muster:audit src/payments

Prefix with backlog to sweep read-only instead of fixing: /muster:audit backlog writes the ranked ledger to .muster/backlog.md, one item per finding-cluster, ready for /muster:go .muster/backlog.md to clear later.

Design a human-facing surface: /muster:design ​

Initialize or inspect canonical DESIGN.md context, then run one of 24 design workflows. Human-facing implementation carries a scope-bound digest receipt; ordinary backend work never pays the design scan or provider cost.

sh
/muster:design init
/muster:design polish src/App.tsx

Turn a discussion into backlog items: /muster:capture ​

Had a conversation that produced findings, decisions, or an explicit "add those 5" -- but nothing has written them down yet? /muster:capture [hint] mines the session (or just the part hint scopes) for candidate backlog items, each traced back to what was actually said. Nothing is written until you approve the list; it never assembles a crew or runs anything itself.

sh
/muster:capture
/muster:capture the three findings from the audit we just discussed

Approve, and the items land in .muster/backlog.md alongside anything /muster:audit backlog or an interview decomposition already wrote there, ready for /muster:go .muster/backlog.md to clear.

Initialize a repository: /muster:init ​

Init learns bounded repository facts, writes .muster/project-profile.json plus .muster/init-receipt.json, and hands native instruction generation to the active harness. It never runs repository scripts, hooks, installers, or discovered commands.

sh
/muster:init
/muster:init path/to/repo

Claude Code and Codex use one canonical instruction pair: AGENTS.md is authoritative, and CLAUDE.md contains exactly:

md
# Claude Code

@AGENTS.md

If conflicting instruction files existed at the preparation baseline, Init leaves a HUMAN-HOLD instead of overwriting or merging them. See The seven modes for the evidence and finalization states.

Inspect the routing yourself ​

Because the CLI is deterministic and makes no model calls, you can run it in a terminal to see exactly how Muster would resolve work:

sh
# What did Muster detect about this project?
npx -y @adnova-group/muster detect

# Which provider wins each role, on which model, and what would beat it?
npx -y @adnova-group/muster capabilities

# Which specialist matches a free-text task?
npx -y @adnova-group/muster match "audit this code for security vulnerabilities"

# Which pipeline routes for an outcome?
npx -y @adnova-group/muster route "draft a PRD for a referral program"

Next: read Concepts to understand the router that powers all of this.

Released under the Apache-2.0 License.