claude

fsm-workflow

23-agent FSM pipeline. Marketplace install ships agents, commands, and templates only. Run the /fsm-setup-hooks command after install to complete the enforcement layer (hooks cannot be installed via the plugin marketplace and are required for the full package).

0 on GitHubby itsaldrincrv1.2.2MITupdated 6 months agoworkflow
/

Plugin fsm-workflow from marketplace claude-code-fsm-workflow in itsaldrincr/claude-code-fsm-workflow. Commands read from the repo's manifest — 1 month ago.

What it installs

Slash commands (2)

  • /fsm-workflow:fsm-setup-hooks

    Install the FSM workflow enforcement hooks. Required after marketplace install for the full package — without these hooks the workflow loses context isolation, single-writer state, nonce-proof reads, and the discipline gate.

  • /fsm-workflow:init-workflow

    Bootstrap the FSM agent workflow in the current directory — installs CLAUDE.md, project hooks, the discipline gate, and orchestrator scripts.

Subagents (23)

  • advisor

    Wave-gate reviewer. Called once per wave boundary when ALL tasks in

  • architect

    Synthesizes explore agent reports into a structured build manifest.

  • bug-scanner

    Scans source files for logic bugs — null dereferences, unhandled

  • code-auditor

    Audits all Python or TypeScript source files in a directory against

  • code-fixer

    Fixes coding discipline violations from a code-auditor report.

  • code-reviewer

    Scans codebase for simplification and optimisation opportunities.

  • debugger

    Fixes complex bugs and failing tests. Reasons about interface changes,

  • dep-checker

    Reads all source files in a project and verifies every import resolves to an actual symbol. Catches missing imports, stale references, and cross-module type mismatches before they become runtime errors.

  • dispatcher

    Reads MAP.md and pipeline state, decides which agent to dispatch next,

  • doc-writer

    Handles project documentation — both pre-workflow setup (CLAUDE.md,

  • explore-scout

    Reads files, specs, or code and returns a structured report. Replaces

  • explore-superscout

    Reads large or dense documents (specs, design docs, cross-referenced

  • file-lister

    Scans a directory and returns a structured inventory of all source files with line counts, public functions, and classes. Use for quick context-building on unfamiliar codebases.

  • fsm-executor

    Executes a single focused FSM task file — reads task, writes code,

  • fsm-integrator

    Executes cross-module FSM integration tasks — modifies files across

  • mock-server

    Reads a protocol spec and generates a working mock HTTP server for testing without a real backend. Supports SSE streaming, tool_use cycles, and configurable responses.

  • mockup-verifier

    Use this agent to compare a reference mockup (JSX/TSX single-file artifact) against an implementation source directory and find all discrepancies. Launch this after building or modifying UI components to verify fidelity against the design reference. Examples: - user: "Check the web UI against the v2

  • research-scout

    Use this agent when you need to research external libraries,

  • session-closer

    Cleans up after a successful audit + test pass. Deletes task files,

  • session-handoff

    Writes a comprehensive status document at the end of a session so the next session can pick up with zero prior context. Reads the current project state from disk.

  • spec-writer

    Captures brainstorming intent into a structured spec markdown file in

  • task-planner

    Reads a build manifest (from the architect agent) and produces MAP.md

  • test-runner

    Runs the test suite for a project and reports results. Use after code changes to verify nothing is broken.

View source on GitHub

Similar plugins

superpowers

claudecodex

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

15 skills · hooks

obra/superpowers 316,836

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows

18 skills

MiniMax-AI/skills 13,828

worktrunk

claudecodex

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.

2 skills · hooks

max-sixty/worktrunk 12,481

gsd-core

claude

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

72 skills · 72 commands · 64 agents · hooks

open-gsd/gsd-core 11,494

Maintain fsm-workflow?

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