59 workflow commands that enforce a verification-first approach to AI-assisted development

Workflow Commands

Massu AI provides 59 workflow commands organized into categories that enforce a structured, verification-first approach to AI-assisted development. These are not suggestions -- they are mandatory execution protocols that ensure every plan is thorough, every implementation is verified, and every commit meets quality standards.

Installation

All 59 commands are automatically installed when you run npx massu init. The command files are deployed into .claude/commands/ in your project directory and are available immediately in Claude Code.

The command definitions ship inside the @massu/core npm package. When you update @massu/core to a new version, run npx massu install-commands to get the latest command definitions without re-running full init.

bash

# Re-install or update commands only
npx massu install-commands

Implementation Workflow

The core pipeline for structured development:

/massu-create-plan  -->  /massu-plan  -->  /massu-loop  -->  /massu-commit  -->  /massu-push
   (create)          (audit)      (implement)     (pre-commit)     (pre-push)

Command	Edits Source Code?	Purpose
/massu-create-plan	No	Create a plan document
/massu-plan	No (plan doc only)	Audit and improve the plan
/massu-plan-audit	No	Combined create-plan + plan audit in one flow
/massu-loop	Yes	Implement with verification
/massu-commit	Fixes only	Pre-commit verification gate
/massu-push	Fixes only	Pre-push full verification
/massu-push-light	Fixes only	Fast pre-push verification (~90s)
/massu-new-feature	Yes	Feature scaffolding with patterns pre-applied
/massu-golden-path	Yes	Full end-to-end workflow from plan to push

Development Tools

10 commands for day-to-day development tasks:

Command	Edits Source Code?	Purpose
/massu-test	Yes	Intelligent test runner with failure analysis and generation
/massu-debug	Yes	Systematic debugging with hypothesis testing
/massu-refactor	Yes	Safe refactoring with behavioral equivalence
/massu-hotfix	Yes	Quick scoped fix with branch, test, commit, PR
/massu-tdd	Yes	Test-driven development cycle (RED/GREEN/IMPROVE)
/massu-batch	Yes	Apply same change across multiple files in parallel
/massu-ci-fix	Yes	Auto-diagnose CI failures, fix, commit, and re-push
/massu-simplify	Yes	Code simplification and complexity reduction
/massu-scaffold-page	Yes	Scaffold new page with layout, loading/error states
/massu-scaffold-router	Yes	Scaffold new tRPC router or API endpoint

Quality & Verification

7 analysis commands for code quality:

Command	Edits Source Code?	Purpose
/massu-review	No	Code review across 7 dimensions
/massu-audit-deps	No	Dependency vulnerability and license audit
/massu-verify	No	Run all VR-* verification checks with proof
/massu-verify-playwright	No	Browser-based page verification via Playwright
/massu-estimate	No	Effort estimation with complexity scoring
/massu-gap-enhancement-analyzer	No	Post-implementation gap analysis with enhancement recommendations
/massu-parity	No	Feature parity check between two systems

Release & Ops

4 commands for release and operational tasks:

Command	Edits Source Code?	Purpose
/massu-release	Yes	Release preparation with full verification
/massu-changelog	CHANGELOG.md only	Generate changelog from commits
/massu-deploy	No	Structured deployment with pre-deploy verification
/massu-incident	Yes	Incident documentation with root cause and prevention

Productivity

8 commands for codebase hygiene, documentation, and guided workflows:

Command	Edits Source Code?	Purpose
/massu-cleanup	Yes	Dead code removal, unused imports, orphaned files
/massu-dead-code	Yes	Detect and remove orphaned modules and unused exports
/massu-doc-gen	Yes	Generate JSDoc, README, and API documentation
/massu-docs	Yes (docs only)	Documentation sync ensuring docs match code
/massu-deps	No	Dependency audit (security, updates, compatibility)
/massu-guide	No	Interactive onboarding walkthrough
/massu-loop-playwright	Yes	Browser-based audit and fix loop
/massu-scaffold-hook	Yes	Scaffold new Claude Code hook with settings registration

Session Lifecycle

4 commands for session management and context:

Command	Edits Source Code?	Purpose
/massu-bearings	No	Session orientation -- recover context after being away
/massu-recap	No	End-of-session summary with handoff notes
/massu-squirrels	No	Park tangential ideas for later review
/massu-hooks	No	Hook status diagnostics and configuration check

Diagnostics

2 read-only commands for project health:

Command	Edits Source Code?	Purpose
/massu-status	No	Project health dashboard with 14 checks
/massu-review	No	Automated 7-dimension code review

Decision Tree

Not sure which command to use?

Starting new work -- /massu-create-plan then /massu-plan then /massu-loop
Quick plan + audit -- /massu-plan-audit (combines both steps)
Full end-to-end -- /massu-golden-path (plan through push)
Scaffolding a feature -- /massu-new-feature
Scaffolding a page -- /massu-scaffold-page
Scaffolding an API route -- /massu-scaffold-router
Scaffolding a hook -- /massu-scaffold-hook
Ready to commit -- /massu-commit
Ready to push -- /massu-push (full) or /massu-push-light (fast ~90s)
Tests are failing -- /massu-test
Bug to diagnose -- /massu-debug
Urgent production fix -- /massu-hotfix
CI pipeline failed -- /massu-ci-fix
Restructuring code -- /massu-refactor
Simplify complexity -- /massu-simplify
Apply change to many files -- /massu-batch
Before a code review -- /massu-review
Cutting a release -- /massu-release
Deploy to production -- /massu-deploy
Bug/incident happened -- /massu-incident
Project health check -- /massu-status
Dependency concerns -- /massu-audit-deps or /massu-deps
Dead code / cleanup -- /massu-cleanup or /massu-dead-code
Generate documentation -- /massu-doc-gen or /massu-docs
Effort estimation -- /massu-estimate
Run all VR checks -- /massu-verify
UI end-to-end verification -- /massu-verify-playwright
Post-implementation review -- /massu-gap-enhancement-analyzer
Feature parity check -- /massu-parity
TDD workflow -- /massu-tdd
Interactive onboarding -- /massu-guide
Browser-based testing loop -- /massu-loop-playwright
Starting a new session -- /massu-bearings
Ending a session -- /massu-recap
Got a tangential idea -- /massu-squirrels
Check hook status -- /massu-hooks

Why This Workflow?

AI assistants are powerful but they can also be careless. Without a structured workflow:

Plans have gaps that only surface during implementation
Implementations claim completion without verification
Commits include untested or type-unsafe code
Removals leave behind orphaned references
"100% complete" turns out to be 80% complete

The Massu AI workflow prevents all of these problems by requiring proof at every stage.

Core Principles

1. Plans Before Code

Every non-trivial change starts with a plan document. Plans live in docs/plans/ and include specific deliverables, file paths, and verification requirements.

2. Verification Before Claims

Every claim of completion requires a verification command and its output as proof. "I verified it" without showing the command output is treated as unverified.

3. Negative Verification for Removals

When a plan says "remove X", verification requires grep -rn "X" src/ returning 0 results. Partial removal is not removal.

4. All Items, Not Most Items

If a plan has 10 items, all 10 must be implemented and verified. Stopping at 8 and claiming complete is a protocol violation.

5. Protocols Are Mandatory

Slash commands are execution instructions, not suggestions. When a protocol says "loop until complete," it means loop until complete.