claude

harness-engineering

Harness Engineering framework - skills, agents, and commands for safe, reviewable, incremental agent-driven development. Includes RPEQ workflow (Research, Plan, Execute, QA), ast-grep setup, and codebase analysis tools.

105 on GitHubby Harness Engineeringv0.1.0MITupdated 7 months ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin harness-engineering in alchemiststudiosDOTai/harness-engineering. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (8)

  • agents-md-mapper

    This skill should be used when creating, refreshing, or validating a repository `AGENTS.md` so it stays concise, current, and grounded in repository evidence. Use when `AGENTS.md` is missing or stale, after refactors or tooling changes, when new docs become the system of record, or when adding light

  • ast-grep-setup

    Set up ast-grep for a codebase with common TypeScript rules for detecting anti-patterns, enforcing best practices, and preventing bugs. Creates sgconfig.yml, rule files, and rule tests. Use when adding structural linting, banning legacy patterns, or implementing ratchet gates.

  • differential-session-runner

    Run or continue a differential debugging session between two implementations, traces, captures, or outputs. Record artifact identity, exact commands, first mismatch progression, findings, validation, and next probe in a durable session log.

  • execute-phase

    Execute implementation plans from .artifacts/plan/. Focus on EXECUTING ONLY - no planning, no fixes outside plan scope. Uses gated checks, atomic commits, and maintains a single execution log in .artifacts/execute/. Use when the user says "execute this plan" or provides a plan path.

  • harness-map

    Map a repository's mechanical harness layers: canonical check command, local and CI gates, architecture boundaries, structural rules, behavioral verification, docs ratchets, evidence workflows, and operator-facing surfaces. Use when you need to understand how a repo keeps change safe.

  • plan-phase

    Generate execution-ready implementation plans from research docs - planning ONLY, no fixing or verifying. North Star is whether a JR developer can execute the plan with zero additional context.

  • qa-from-execute

    Perform quality assurance on code changes after the research-phase -> plan-phase -> execute-phase workflow. STRICTLY QA only—no coding, no fixes, no source-code changes. Focus on changed areas only, emphasizing control/data flow correctness.

  • research-phase

    This skill should be used when mapping or researching a codebase to understand its structure, patterns, and architecture. Use when the user asks to "map the codebase", "research how X works", "find all Y patterns", or needs to understand code organization. Produces factual structural maps in .artifa

Slash commands (16)

  • /harness-engineering:COMMANDS
  • /harness-engineering:README
  • /harness-engineering:context engineering:deep-research

    Conduct comprehensive codebase research using parallel sub-agents

  • /harness-engineering:context engineering:execute-from-deep-research

    Execute implementation plans from research-plans/plans/ directory

  • /harness-engineering:context engineering:execute

    Executes a plan with gated checks, atomic commits, build/package/deploy, full validation, and immutable execution logs

  • /harness-engineering:context engineering:implementation-from-deep-research

    Create detailed implementation plans from research findings

  • /harness-engineering:context engineering:plan

    Generates a concrete implementation plan from a research doc, with milestones, tasks, gates

  • /harness-engineering:context engineering:research

    Research codebase comprehensively with parallel sub-agents and document findings

  • /harness-engineering:context engineering:three-step-workflow

    Three-step workflow guide for complex tasks (research, plan, implement)

  • /harness-engineering:integration:coderabbitai

    Normalize a GitHub issue by asking @coderabbitai to outline and structure it

  • /harness-engineering:integration:linear-continue-debugging

    Continue debugging a Linear issue with systematic analysis

  • /harness-engineering:integration:linear-continue-work

    Continue work on a Linear issue by understanding state and planning next steps

  • /harness-engineering:quality-assurance:fagan-inspection

    Fagan-style inspection for analysis only; identifies defects and prepares findings for the next devoir agent

  • /harness-engineering:utilities:context-compact

    Prepare context for compaction when approaching token limits

  • /harness-engineering:utilities:phase-planner

    Implement features in structured phases with automatic commits using git worktree

  • /harness-engineering:utilities:smart-git

    Stage all changes and generate smart commit with inline diff

Subagents (2)

  • README
  • guide
View source on GitHub

Similar plugins

Deterministic harness-maturity audit + remediation skill for this workspace.

1 skill · 1 command

paladini/harness-score 619

Design, diagnose, and evaluate coordination across multiple AI agents and heterogeneous harnesses: decomposition, topology, ownership, communication, distributed context, shared memory, integration, recovery, and collective failure patterns. Use for persistent agent teams, fleets, swarms, agent handoffs, coordination loops, or extracting portable lessons from OpenRig, HERDR and Block/Buzz. Do not use for a single agent's runtime, a named tool's installation or command manual, debate alone, or operating an evaluated production agent; route those to harness-engineering, the tool's documentation, agent-council, or agent-production-operations.

194 skills

magnus919/agent-skills 175

The AI Literacy framework's complete development workflow — harness engineering, agent orchestration, literate programming, CUPID code review, compound learning, and the three enforcement loops

41 skills · 32 commands · 20 agents · hooks

Habitat-Thinking/ai-literacy-superpowers 123

Makes a repo agent-ready: AGENTS.md, boundary tests, CI pipeline, GC scripts — based on OpenAI's harness engineering methodology

1 skill

Gizele1/harness-init 56

mycelium

claudecodex

I realized I let the agent start coding before I was sure it was working on the right thing, so I built this. Now it doesn't get to write code before there's a reason. The agent asks who this is for. It asks what you're assuming, and what would show you wrong. The rules run as hooks, so once you have started it in a repo the build stays shut until the answers are there. Purpose, strategy, opportunities, then delivery and market feedback. It adds skills and hooks, keeps its own state in a .claude/ folder, and won't edit the files already in your repo unless you ask it to.

63 skills · hooks

haabe/mycelium 52

arn-code

claude

Artifact-driven pipeline — spec, plan, implement, review, ship, plus batch CVE scan & fix. Three ceremony tiers scale process to scope, from a one-file fix to a large refactor. 37 skills, 18 agents.

37 skills · 18 agents · hooks

AppsVortex/arness 35

Maintain harness-engineering?

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