claudecodex

maxi

Spec-driven development pipeline for Claude Code: constitution → specify → clarify → plan → tasks → analyze → implement

1 on GitHubby Antoine Moutiersv2.9.1MITupdated 20 days agoproductivity
/

Plugin maxi from marketplace maxi in amoutiers/maxi-superpowers. Commands read from the repo's manifest — 19 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (36)

  • doc-consistency

    Use when reviewing maxi-superpowers' own authored docs for factual drift — before committing pipeline/skill changes, after editing AGENTS.md/README/architecture.md, or when asked to check whether docs are consistent, in sync, or contradict each other

  • release

    Use when releasing a new version of the maxi plugin

  • analyze

    Use when the user invokes /maxi:analyze or wants to audit spec/plan/tasks artifacts for quality issues — spec must be at status "tasked" or later; constitution is required

  • board

    Use when the user invokes /maxi:board or wants a kanban overview of all specs and their pipeline status in the current project

  • brainstorming

    You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).

  • cancel

    Use when the user invokes /maxi:cancel, says a feature is abandoned, dead, or will never ship — requires active spec status, explicit reason, and explicit yes/no confirmation before writing anything.

  • clarify

    Use when the user invokes /maxi:clarify or when a spec.md has open questions, [NEEDS CLARIFICATION] markers, or ambiguous FRs — status must be "specified

  • constitution

    Use when the user invokes /maxi:constitution, wants to establish or amend project principles, or when docs/maxi/constitution.md does not yet exist and needs to be created

  • diagnosing-superpowers

    Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for

  • dispatching-parallel-agents

    Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

  • executing-plans

    Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

  • finishing-a-development-branch

    Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

  • implement

    Use when the user invokes /maxi:implement or wants to start coding from an existing tasks.md — spec must be at status "analyzed

  • migrate-adr

    Use when the user invokes /maxi:migrate-adr or wants to bootstrap a project's maxi ADR log — imports existing ADR files (Nygard, MADR, plain Markdown) and/or discovers undocumented architectural decisions from source code, config files, manifests, and git history

  • migrate-from-brownfield

    Use when the user invokes /maxi:migrate-from-brownfield or asks to reverse-engineer an existing brownfield codebase into spec.md baselines so a project with code but no specs can adopt spec-driven development — discovers feature boundaries, drafts as-built specs verified against code, writes them at

  • migrate-from-speckit

    Use when the user invokes /maxi:migrate-from-speckit or asks to migrate a github-spec-kit project to maxi conventions — detects .specify/ directory, previews the migration plan, confirms with user, then runs migrate.sh

  • park

    Use when the user invokes /maxi:park, wants to pause a spec, put a feature on hold, or says it is blocked — requires active spec status, explicit reason, and yes/no confirmation before writing.

  • plan

    Use when the user invokes /maxi:plan or wants to create a technical implementation plan for a clarified feature — spec must be at status "clarified

  • receiving-code-review

    Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

  • requesting-code-review

    Use when completing tasks, implementing major features, or before merging to verify work meets requirements

  • resume

    Use when the user invokes /maxi:resume, wants to unpause a spec, or asks to pick up a parked feature — requires a spec at status parked, reads parked_from to restore the prior status.

  • review

    Use when the user invokes /maxi:review or a newly completed plan reaches the design-review boundary before task extraction

  • revise

    Use when the user invokes /maxi:revise, says requirements changed, the spec needs updating, or the plan needs to change — accepts a spec at clarified or later, including done, and coordinates an authorized design revision.

  • specify

    Use when the user invokes /maxi:specify or wants to create a new feature specification in a maxi-managed project

  • subagent-driven-development

    Use when executing implementation plans with independent tasks in the current session

  • systematic-debugging

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

  • tasks

    Use when the user invokes /maxi:tasks or wants to extract a structured task list from an existing plan.md — spec must be at status "planned

  • test-driven-development

    Use when implementing any feature or bugfix, before writing implementation code

  • using-git-worktrees

    Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

  • using-maxi

    Use when starting any conversation for a Maxi project check, completing a local maintenance batch, reporting an external operational wait, or referencing pipeline phases, commands, artifacts, or statuses

  • using-superpowers

    Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

  • verification-before-completion

    Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

  • writing-plans

    Use when you have a spec or requirements for a multi-step task, before touching code

  • writing-skills

    Use when creating new skills, editing existing skills, or verifying skills work before deployment

  • x-adr

    Use when an internal Maxi workflow detects an architectural decision that is costly to reverse, constrains future choices, was contested, or changes an existing decision in the current Maxi project

  • x-develop

    Use when /maxi:implement delegates execution, or when executing a maxi plan via subagent-driven development

Hooks (1)

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd" session-start

View source on GitHub

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

Maintain maxi?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted