agent-harness-design

Design agent tool sets with stable names, narrow schemas, deterministic output shapes, and explicit error paths. No catch-all tools unless unavoidable.

omh

Generate oh-my-hi dashboard. Visual catalog and usage/token analysis of skills, agents, plugins, hooks, memory, MCP servers, rules, and principles. Triggered by "/omh", "harness status", "dashboard", etc.

Dayu Harness Skill

reverse-engineering-api

Reverse engineer web APIs by capturing browser traffic (HAR files) and generating production-ready Python API clients. Use when the user wants to create an API client for a website, automate web interactions, or understand undocumented APIs. Activate on tasks mentioning "reverse engineer", "API client", "HAR file", "capture traffic", or "automate website".

Harness Engineering Guide

You are a harness engineering consultant. Your job is to audit, design, and implement the environments, constraints, and feedback loops that make AI coding agents work reliably at production scale.

better-harness

Use when /better-harness reviews the outer coding-agent Harness for lifecycle controls, repeated work, project feedback, agent assets, session outcomes, repair planning, durable reports, finding-bound fixes, or manual direct fixes. Invoke only via slash command.

haiku-pilot

Haiku-first execution playbook: through deliberate prompt structure, sub-agent delegation, and quantitative escalation gates, get Haiku 4.5 to produce near-Opus quality on most tasks. Escalate to Sonnet/Opus only when gates trigger. Triggers: "haiku", "Haiku", "Haiku mode", "haiku-pilot". Do NOT use for: cost-only token optimization, file-count cognitive heuristic, agent dispatch table, CLAUDE.md / rules audit, harness health check. This SKILL is a runtime router + escalation gate, not a decision tree or directory.

Harness — Multi-Agent Orchestration

Orchestrate complex tasks through Planning → Generation ��� Evaluation → Retro. Fresh sub-agents per checkpoint prevent drift. Retro accumulates learning across tasks.

Harness

MCP server for Harness API integration

Mcp Eval Runner

A standardized testing harness for MCP servers and agent workflows

the-loop

"the-loop" is an opinionated product-development-lifecycle (PDLC) harness, shipped as a plugin for Claude Code, Cursor and Codex. Once a work item's spec chain (requirements → design → testing plan → tasks) is approved, the harness executes it end-to-end with MINIMAL or NO human intervention,

agentic-legibility

Score a repository's agentic legibility from repo-visible evidence only. Use when Codex needs to audit how easy a codebase is for coding agents to discover, bootstrap, validate, and navigate, especially for harness-engineering reviews, developer-experience audits, repo cleanup, or before/after comparisons after improving docs, tooling, or architectural constraints.

agent-view

Diagnose Claude Code Agent View readiness safely inside the minmaxing harness. This route is static readiness and troubleshooting only; open the live Agent View TUI manually with claude agents.

Skill, agent, MCP, and harness recommendations for Claude Code/custom LLMs: 102,696-node LLM-wiki graph, 91,432 skills, 10,787 MCPs, 13 harnesses, and capped execution recommendations.

Risk-gated /skills for Claude Code — 14 invocable skills carry a change from brainstorm → ship.

Unity Agent Harness for Claude Code — auto-compile, test pipelines, cross-model review, out of the box.

Compare the current branch against develop and generate two review documents: architecture change diagram + PR review checklist.

fixture-skill

Use this Skill to exercise the Harness review fixture.

Implement Universal — Single-Context Workshop Implementation Loop

This is the harness-agnostic twin of `/implement`. It is functionally identical, but instead of dispatching subagents via Claude Code's `Task` tool, it instructs **you** to adopt two distinct roles in sequence:

harness-engineering-orchestrator

Repo-backed PRD-to-code orchestration for Claude and Codex. Use when the user wants a new app or existing repository run through discovery, architecture, milestones, execution, and validation instead of ad-hoc prompt-only delivery. Supports greenfield and existing codebases across web, iOS, Android, CLI, agent, API, and desktop projects, with first-class workspace-first support for Bun, npm, and pnpm repositories plus reference templates for additional ecosystems.

harness

하네스를 구성합니다. 전문 에이전트를 정의하며, 해당 에이전트가 사용할 스킬을 생성하는 메타 스킬. (1) '하네스 구성해줘', '하네스 구축해줘' 요청 시, (2) '하네스 설계', '하네스 엔지니어링' 요청 시, (3) 새로운 도메인/프로젝트에 대한 하네스 기반 자동화 체계를 구축할 때, (4) 하네스 구성을 재구성하거나 확장할 때 사용.

capture

Capture HTTP traffic from web apps using playwright-cli. Includes site fingerprinting (framework detection, protection checks, iframe detection, auth detection, API discovery) and full traffic recording with tracing and optional HAR output. TRIGGER when: "record traffic from", "capture API calls from", "start Phase 1 for", "analyze traffic from URL", "assess site", "site fingerprint", "start capture for", "open browser for", or any URL is given as the first step of CLI generation. DO NOT trigger for: Phase 2 implementation, test writing, or quality validation.

bootstrap-realtime-eval

Bootstrap a new realtime eval folder inside this cookbook repo by choosing the right harness from examples/evals/realtime_evals, scaffolding prompt/tools/data files, generating a useful README, and validating it with smoke, full eval, and test runs. Use when a user wants to start a new crawl, walk, or run realtime eval in this repository.

codeman

Drive Codeman, the session manager this agent is running inside, over its HTTP API, from any agent CLI (Claude Code, Codex, Gemini CLI, OpenCode, Antigravity, Grok Build, DeepSeek Harness, OMP): list sessions, start worker sessions in any installed CLI, send them prompts, block until they finish (wait / wait-output / send-and-wait), read their output, and clean up; where available, message claude workers directly (Claude Code cross-session messaging). Use when asked to orchestrate or parallelize work across Codeman sessions, get a second opinion from another CLI or model, watch another session, start and manage workers, or retrieve saved local Codex history by file/native ID or root and descendants with topic/date filters. Live API operations require a Codeman-managed session (CODEMAN_MUX=1). Offline history reads do not require a server or managed session.

Agent Harness Architect Skill

audit-harness

Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.

Gigaxity Deep Research

A skill-format reference for any agent (Claude Code, Codex, Cursor, Hermes, plain-MCP) calling this server. For human-readable installation instructions, see [README.md](README.md). For harness-agnostic routing logic and the pasteable instruction block (drop into your harness's global `CLAUDE.md` /

create-harness

This skill scaffolds an AI agent harness — your own focused, branded harness with its own `npx <name>` CLI, MCP server registration, memory namespace, learning loop, and marketplace identity.

acp-router

Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation.

A provider-agnostic scaffolding kit for running structured multi-agent workflows in your codebase.

deep-agents-core

INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.

align-grid

"Build editorial/magazine/report webpages on a GENUINE Müller-Brockmann modular grid (International Typographic Style) — not a decorative one. Encodes the discipline (columns + modules + baseline, grotesque type, flush-left, restrained black/white/red palette) AND the hard-won front-end engineering to make the grid real, visible, and verified: one CSS-variable source of truth, an interactive grid-toggle overlay that lives in the SAME content box as the content, subgrid \"bands\" so every element snaps to a column line, an 8px baseline lock, and runtime OPTICAL ALIGNMENT that puts display type's ink (not its box) on the line. Ships with a scaffold generator and a Puppeteer verification harness that proves 0px adherence."

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

Adding Fjall partitions and key encodings safely

ableton-ai

Create and inspect music projects in the Ableton AI Harness workspace, including its local starter and optional upstream integration.

workflow-record-decision

product·harness 의사결정을 DR 파일로 기록한다