By mission42-ai
Learning loop for agent evolution - extracts wisdom from session failures and applies them as signs in CLAUDE.md files
Add a new learning sign manually to the backlog or directly to CLAUDE.md
Apply approved learnings from backlog to CLAUDE.md files
Extract learnings from session transcript via parallel subagent processing
Show m42-signs plugin help and available commands
List all signs across CLAUDE.md files in the project
Analyze preprocessed transcript chunk for learning extraction. Use when extract command processes large transcripts in parallel.
Match learning candidates to appropriate CLAUDE.md files and detect duplicates. Use proactively when matching learnings to CLAUDE.md files, detecting duplicate learnings, or assigning learning targets.
Score and filter learning candidates by quality. Use after transcript-section-analyzer and context-matcher complete.
Analyzes transcript sections to extract learning candidates with structured metadata. Used by extract command for parallel section processing. Use proactively when extract command delegates section analysis.
Domain knowledge for extracting learnings from session transcripts. Provides learning taxonomy (8 categories), quality criteria, extraction patterns (linguistic/tool signals), and confidence scoring. Used by subagents during transcript analysis to identify and classify actionable insights.
Manages learning extraction and sign application workflows. This skill should be used when extracting learnings from session transcripts, reviewing proposed signs, or applying approved learnings to CLAUDE.md files. Triggers on "extract learnings", "review signs", "apply signs", "manage signs", "learning backlog".
Uses power tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A marketplace of Claude Code plugins for modular development workflows.
Add this marketplace to Claude Code:
claude marketplace add https://github.com/mission42-ai/m42-claude-plugins
Then install individual plugins:
claude plugin install m42-planning
claude plugin install m42-sprint
claude plugin install m42-task-execution
claude plugin install m42-meta-toolkit
claude plugin install m42-signs
claude plugin install m42-dev
Or install all plugins:
claude plugin install m42-planning m42-sprint m42-task-execution m42-meta-toolkit m42-signs m42-dev
Epic and story planning with GitHub integration, gherkin-based acceptance criteria, and structured issue templates.
Features:
Sprint orchestration with ralph-loop driven task queue processing.
Features:
/start-sprint - Initialize new sprint/add-task - Add tasks to queue (issue, refactor, docs, custom)/run-sprint - Start ralph-loop execution/sprint-status - View progress dashboard/pause-sprint / /resume-sprint - Control execution/import-tasks - Bulk import from GitHubReusable 6-phase task execution workflow.
Features:
Meta-tooling for creating and managing Claude Code artifacts (skills, commands, subagents, hooks) with quality assurance workflows.
Features:
/create-skill - Create new skills with proper structure and frontmatter/create-command - Create new slash commands/create-subagent - Create new subagents with validation/create-hook - Create new hooks/scan-claudemd - Scan CLAUDE.md files for issues/optimize-claudemd - Optimize CLAUDE.md contentLearning extraction and management from session transcripts. Extracts wisdom from session failures and applies them as learnings in CLAUDE.md files.
Features:
/extract - Extract learnings from session transcripts/review - Review extracted learnings before applying/apply - Apply approved learnings to CLAUDE.md files/add - Manually add a learning/list - List current learnings in backlog/status - View learning pipeline statusDevelopment utilities for software engineers - specs, planning, and daily practice support. (Early development)
Features:
creating-specs skill - Guide for writing effective specification filesWorkflow Plugins:
Planning ──────────────> m42-planning
│
▼
Sprint ────────────────> m42-sprint
│
▼
Execution ─────────────> m42-task-execution
Tooling Plugins:
Meta-tooling ──────────> m42-meta-toolkit
Learning Loop ─────────> m42-signs
Dev Utilities ─────────> m42-dev
Each plugin is independent but they compose together for end-to-end automation. Workflow plugins handle the planning-to-execution pipeline. Tooling plugins provide cross-cutting utilities for plugin development, learning management, and engineering practices.
m42-claude-plugins/
├── .claude-plugin/
│ └── marketplace.json # Plugin registry
├── plugins/
│ ├── m42-planning/
│ │ ├── .claude-plugin/
│ │ │ └── plugin.json
│ │ ├── skills/
│ │ │ └── epic-story-planning/
│ │ └── templates/
│ ├── m42-sprint/
│ │ ├── .claude-plugin/
│ │ │ └── plugin.json
│ │ ├── commands/
│ │ └── skills/
│ │ └── orchestrating-sprints/
│ ├── m42-task-execution/
│ │ ├── .claude-plugin/
│ │ │ └── plugin.json
│ │ └── skills/
│ │ └── task-execution/
│ ├── m42-meta-toolkit/
│ │ ├── .claude-plugin/
│ │ │ └── plugin.json
│ │ ├── commands/
│ │ ├── agents/
│ │ └── skills/
│ ├── m42-signs/
│ │ ├── .claude-plugin/
│ │ │ └── plugin.json
│ │ ├── commands/
│ │ ├── agents/
│ │ └── skills/
│ └── m42-dev/
│ ├── .claude-plugin/
│ │ └── plugin.json
│ ├── commands/
│ ├── agents/
│ └── skills/
└── README.md
MIT
npx claudepluginhub mission42-ai/m42-claude-plugins --plugin m42-signsSprint orchestration with autonomous task queue processing, polymorphic task types, and progress tracking
Meta-tooling for creating and managing Claude Code artifacts (skills, commands, subagents, hooks) with quality assurance workflows
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.