codeharness
claudeMakes autonomous coding agents produce software that actually works — real-world verification, observability, and mechanical enforcement via Claude Code hooks.
46 skills · 5 commands · 2 agents · hooks
Autonomous development toolkit — autopilot, quality gates, story validation, autonomy assessment
Plugin famdeck from marketplace ivintik in iVintik/private-claude-marketplace. Commands read from the repo's manifest — 1 month 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.
autonomy-assessAssess project's verification infrastructure and autonomy readiness level (L0-L2). Trigger on: 'project readiness', 'autonomy level', 'verification tools', 'is this project ready', 'quality baseline', starting work on a new project.
autonomy-scaffoldGenerate missing verification tool configs to reach target autonomy level. Trigger on: 'set up linting', 'add CI', 'add tests', 'improve quality tooling', 'scaffold verification', after autonomy-assess shows below L2.
autopilotAutonomous Beads/BMAD development loop -- reconcile orphan issues, execute BMAD stories, close on completion, repeat. Trigger on: 'autopilot', 'start working autonomously', 'run the dev loop', 'hands-off mode', 'night shift'. IMPORTANT: This skill runs INSIDE a Claude Code session (Codeman). If the
bmad-importImport BMAD story/epic artifacts into Beads as trackable issues. Trigger on: 'import stories', 'sync BMAD to Beads', 'create issues from epics', after creating new BMAD epics.
project-addClone a git repo and register it as a project (Atlas, Beads, Relay initialized). Trigger on: 'add project', 'clone and register', 'set up new project', 'add repo', 'onboard project'.
session-approveApprove, reject, or list pending approval requests from Codeman sessions. Trigger on: 'approve session', 'reject session', 'pending approvals', 'session needs permission', 'waiting for approval'.
session-dismissTerminate a running Codeman session. Trigger on: 'dismiss session', 'stop session', 'kill session', 'terminate session', 'cancel session'.
session-listenStart or stop the SSE event stream for real-time Codeman session events. Trigger on: 'listen for sessions', 'start event stream', 'stop listening', 'session events', 'watch sessions'.
session-promptSend a follow-up prompt to a running Codeman session. Trigger on: 'send to session', 'tell session', 'message session', 'prompt session', 'follow up with session'.
session-resultsView session completion summaries, errors, and pending delivery failures. Trigger on: 'session results', 'what did the session produce', 'session output', 'session errors', 'pending deliveries'.
session-rulesView auto-approve rule presets for Codeman sessions. Trigger on: 'session rules', 'auto-approve rules', 'approval presets', 'what rules are available', 'safe vs standard vs permissive'.
session-statusQuery Codeman session status -- all active sessions or a specific one. Trigger on: 'session status', 'what sessions are running', 'check on session', 'how is the session doing', 'list sessions'.
session-summonCreate a new Codeman session for a project and optionally run a task in it. Trigger on: 'summon session', 'start a session', 'spin up codeman for X', 'launch session', 'work on project X remotely', 'delegate to codeman', 'run autopilot for X', 'autopilot session for X', 'autopilot codeman X', 'start
verifyInvoke this skill whenever the user has finished an implementation task and needs an outside check that it actually works and meets requirements. This covers: post-implementation sanity checks (\"is it done?\", \"does it pass?\", \"am I good?\"), pre-ship quality gates (lint + types + tests + AC che
session-analystpython3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/daily-sweep.py
python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/post-tool-use.py
python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/user-prompt.py
python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session-end.py
Makes autonomous coding agents produce software that actually works — real-world verification, observability, and mechanical enforcement via Claude Code hooks.
46 skills · 5 commands · 2 agents · hooks
Cross-project issue routing & work handoff — route issues to GitHub/GitLab/Jira, transfer work between sessions and people
8 skills · 2 agents · 1 MCP server · hooks
Setup and project init for Claude Code tools — Context7, Serena, Beads, Agent Mail, Atlas, Relay, Codeman
5 skills · 5 commands · hooks
Plugin lifecycle management — issue tracking, health audits, optimization, fixing, releasing, and marketplace operations for Claude Code plugins
7 skills · 3 agents · hooks
Project registry & awareness across all Claude sessions — discover, cache, and serve project metadata via MCP tools
2 skills · 2 agents · 1 MCP server · hooks
Wraps the ai-pkm CLI as a Claude Code plugin — query, ingest, lint, and inspect a personal knowledge wiki via slash commands and an auto-triggering skill.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
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.