harness engineering commands

datachain-ai/datachain

Command

Garbage collect temporary tables, failed dataset versions, and outdated checkpoints.

datachain-ai/datachain

Command

DataChain is a command-line tool for wrangling unstructured AI data at scale. Use datachain -h to list all available commands.

QoderAI/better-harness

Command

Review the selected change and report evidence.

melandlabs/openloomi

Command

Search OpenLoomi memory (files + knowledge base + insights) — thin doorway into the openloomi-memory sub-skill.

melandlabs/openloomi

Command

Set the OpenLoomi Pet to a specific state (theme-agnostic; fox sprite set active by default).

melandlabs/openloomi

Command

Run OpenLoomi one-time setup — auto-chains install → launch → guest login → ready in one call.

harnessworks/harness-starter-kit

Command

Run Harness Doctor to evaluate how ready the current repository is for reliable AI coding agent collaboration.

harnessworks/harness-starter-kit

Command

Review the current change set from an opposing harness-engineering perspective.

harnessworks/harness-starter-kit

Command

Update a target repository's harness from the latest harness-starter-kit reference material.

agentii-ai/DocMeld

Command Claude Code

Generate a custom checklist for the current feature based on user requirements.

agentii-ai/DocMeld

Command Claude Code

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

agentii-ai/DocMeld

Command Claude Code

Create or update the feature specification from a natural language feature description.

iLearn-Lab/EvoHarness

Command Claude Code

Diagnose long-search, large-file, and context-window pressure in a live session.

iLearn-Lab/EvoHarness

Command Claude Code

Audit how Evo turns real sessions into evolution plans and candidate artifacts.

iLearn-Lab/EvoHarness

Command Claude Code

Guided feature and bugfix workflow for Evo Harness itself.

btspoony/mstar-harness

Command

Deep, pre-merge review of a PR / branch / diff at three strengths — quick / default (default) / deep — one verdict, posted to GitHub when a PR number is given. Decides whether a change is safe to ship with evidence-backed findings, rather than a shallow "looks good" pass. Produces a ship it / needs fixes / blocked…

btspoony/mstar-harness

Command

Autonomous full iteration loop for cloud agents — Phase 1 (code-first auto direction lock + compass/plans + Review & Edit chain) through Phase 2–5 (execute → close → PR → merge-ready). Optional args: direction, scale (S|M|L|XL, default M). Not Done until Phase 5 exit checklist passes. Minimal human intervention; no…

btspoony/mstar-harness

Command

Start a new harness iteration — optional direction hint, research, grill-me, compass/plans, Review & Edit chain (long-lived {SPECSDIR}/ + {ITERATIONDIR}/ / package; compound promotes package at close only), PM lock, integration branch; then auto-continue Phase 2→5 (execute → close → PR → merge-ready) unless pause arg…

studioKjm/ai-harness-template

Command

Run 3-stage verification (Mechanical gates → Semantic AC compliance → Judgment quality) after /run. ALWAYS run before committing. Blocks at Stage 1 failures — no Stage 2 until gates pass.

studioKjm/ai-harness-template

Command

Execute seed spec via Double Diamond (Discover → Define → Design → Deliver). USE AFTER /decompose. Enforces D→L→P implementation order, writes tests immediately, runs gates continuously. Supports Pair Mode for medium/high complexity ACs.

studioKjm/ai-harness-template

Command

Define observability spec (metrics/logs/traces) for a target before implementation. Provided by the Observability First methodology.

wayne930242/Reflexive-Claude-Code

Command

Start the aref refactoring pipeline on the current project. Triggers analyzing-codebases skill.

wayne930242/Reflexive-Claude-Code

Command

Scaffold a new Claude Code plugin package with manifest, skills, and directory structure.

wayne930242/Reflexive-Claude-Code

Command

Scan the session, suggest candidate learnings, and deepen the ones you pick.