claude

cc-harness

Multi-agent harness framework for long-running application development with Claude Code

4 on GitHubby Jinsong Zhouv1.2.0MITupdated 7 months agoworkflow
/

Plugin cc-harness from marketplace cc-harness-marketplace in Jinsong-Zhou/cc-harness. 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.

What it installs

Skills (3)

  • context-management

    Use when running long coding sessions that approach context limits - provides strategies for compaction vs context resets, structured handoffs, and managing context anxiety across model versions

  • harness-loop

    Use when building complex applications autonomously - orchestrates a generator-evaluator iteration loop with planner, generator, and evaluator agents for long-running multi-hour coding sessions

  • harness-tuning

    Use when optimizing or simplifying a multi-agent harness - guides systematic removal of components as models improve, evaluator calibration, and prompt engineering for grading criteria

Slash commands (3)

  • /cc-harness:evaluate

    Trigger a standalone evaluation of the current application using the skeptical evaluator agent

  • /cc-harness:harness-status

    Show current harness session status — iteration count, scores, feature progress, and session metrics

  • /cc-harness:harness

    Start a harnessed development session with planner → generator → evaluator loop for autonomous multi-hour coding

Subagents (3)

  • harness-evaluator

    Use PROACTIVELY after generator completes a feature. Skeptical QA agent that tests the live application via Playwright/browser, grades against sprint contracts and quality criteria. Deliberately resistant to approving mediocre work.

  • harness-generator

    Use when building features from a harness spec. Implements features iteratively one at a time, writes sprint contracts, self-evaluates, commits to git, and hands off to the evaluator via files.

  • harness-planner

    Use PROACTIVELY when starting a harnessed build. Converts brief 1-4 sentence prompts into ambitious, detailed product specs. Focuses on product context and high-level technical design, not implementation details.

Hooks (3)

  • SessionStart

    node "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/run-with-flags.js" "session-start" "scripts/hooks/track-iteration.js" "minimal,standard,strict"

  • PreCompact

    node "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/run-with-flags.js" "pre-compact" "scripts/hooks/track-iteration.js" "minimal,standard,strict"

  • Stop

    node "${CLAUDE_PLUGIN_ROOT}/scripts/hooks/run-with-flags.js" "session-summary" "scripts/hooks/track-iteration.js" "minimal,standard,strict"

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

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

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

PRD generation and conversion skills for the Ralph autonomous agent loop

2 skills

snarktank/ralph 22,224

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

Maintain cc-harness?

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