claude

harness

Self-improving documentation system with agent evolution, metrics-driven self-modification, and stateless command protocol.

1 on GitHubby donovanyohanv5.0.1MITupdated 3 months ago
/

Plugin harness from marketplace chalk-bag in donovan-yohan/chalk-bag. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (1)

  • strangler-fig

    Use when breaking up a god class, extracting responsibilities from an oversized module, incrementally replacing legacy code, or when old and new must coexist during a refactor — symptoms include classes over 500 lines, modules with mixed concerns, or "we can't rewrite this all at once

Slash commands (13)

  • /harness:batch

    Use when executing a living plan via Claude Code's /batch tool for worktree-isolated parallel execution, or when user says "batch", "batch execute", "run batch", "parallel batch", "run the plan in parallel", "execute without checkpoints", "hands-off execution", or "use batch mode

  • /harness:brainstorm

    Use when starting new feature work, creative design, or when user says "brainstorm", "design a feature", or "let's think about

  • /harness:bug

    Use when investigating a bug, diagnosing an error, or when user says "debug", "fix bug", "investigate issue", or "root cause

  • /harness:complete

    Use when ready to archive the plan and create the PR, when user says "we're done", "complete this", "wrap up", or after /harness:reflect finishes

  • /harness:evolve

    Use after reflect to classify learnings, update metrics, and propose agent evolution, or when user says "evolve", "self-improve", "classify learnings

  • /harness:init

    Use when initializing structured documentation for a repository, when CLAUDE.md exceeds 120 lines, or when user says "set up docs" or "initialize harness

  • /harness:orchestrate

    Use when executing a living plan with agent teams, or when user says "orchestrate", "execute the plan", "start building", or "run the plan

  • /harness:plan

    Use when creating an implementation plan from a design doc, bug analysis, or refactor scope, or when user says "create a plan", "plan this", or "write the plan

  • /harness:prune

    Use when auditing docs for staleness, broken links, or bloat. Also use when user says "docs feel stale", "prune docs", or when CLAUDE.md exceeds 120 lines.

  • /harness:refactor-status

    Use when resuming an in-progress refactoring, checking goal progress, or when user says "refactor status", "where are we", or "continue refactoring

  • /harness:refactor

    Use when planning an incremental refactoring, extracting responsibilities from a large class, or when user says "refactor", "extract", "strangler fig", or "decompose

  • /harness:reflect

    Use when capturing learnings and updating docs after review, when user says "reflect", "retrospective", "update docs", or after /harness:review completes

  • /harness:review

    Use when implementation is done and code needs quality review, when user says "review the code", "check the code", or after /harness:orchestrate completes all tasks

Subagents (3)

  • harness-evolver

    Use when proposing modifications to agent definitions based on review escapes, metric anomalies, or universal learnings — invoked by /harness:evolve Phase 3

  • harness-pruner

    Use when auditing documentation health, finding stale or orphaned guides, checking CLAUDE.md bloat, or when /harness:prune is invoked

  • learnings-reviewer

    Use during /harness:review Phase 4 to check code changes against active learnings from docs/LEARNINGS.md for violations

View source on GitHub

More from donovan-yohan/chalk-bag

All 2 plugins →

pr

claude

Pull request lifecycle management — authoring, reviewing, resolving, and updating PRs.

5 commands

1

Similar plugins

Claude API and SDK documentation skill for building LLM-powered applications

19 skills

anthropics/skills 193,780

agents-md

claude

AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.

anthropics/claude-code 155,476

agent-skills

claudecodex

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

addyosmani/agent-skills 116,782

Generate natively editable PPTX from PDF / DOCX / URL / Markdown — real DrawingML shapes, text boxes, charts, and animations. Note: run `pip install -r requirements.txt` inside the installed plugin directory for the Python post-processing scripts to work.

1 skill

hugohe3/ppt-master 76,375

context7

claudecodex

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

upstash/context7 64,709

conductor

claudecodex

Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement

3 skills · 6 commands · 1 agent

wshobson/agents 42,461

Maintain 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 plugins2 plugins