my_harness: Instructions file for Claude Code

AGENTS.md

my_harness AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from cookyman74/my_harness. It costs 754 tokens per session, scanned A, original, Apache-2.0.

A guide for using a project’s harness factory, a system that creates agent teams and skills for a new project domain. It explains how Codex maps Claude Code concepts such as agents, teams, skills, and shared tasks to Codex equivalents.

In plain words
What is it for?
Use it to create or extend a project harness, configure Codex agents and skills, run multi-agent work, and pass information between steps through workspace files.
Why use it?
The same project may run under Claude Code and Codex, but the two systems organize agents and communication differently. This guide explains the correct entry points and file-based handoffs for Codex.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: Claude Code plugin machinery, but also runs codex exec. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is cookyman74/my_harness's own configuration. It tells Claude Code, Codex and OpenCode how to work on my_harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything my_harness configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cookyman74/my_harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cookyman74/my_harness/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/cookyman74/my_harness

Made for: Claude Code, Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for my_harness AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cookyman74/my_harness/agents-md.svg)](https://agentmods.dev/instructions/cookyman74/my_harness/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cookyman74/my_harness/agents-md"><img src="https://agentmods.dev/badge/instructions/cookyman74/my_harness/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 754 This file is loaded in full into every session.
When invoked 754 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00754 $0.00754
Opus 5 $0.00377 $0.00377
Sonnet 5 $0.00151 $0.00151
Haiku 4.5 $0.00075 $0.00075

Measured 6d ago against content hash 44912cdd8f0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

my_harness AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 27 lines

What it actually says

AGENTS.md — Codex 런타임 진입점

이 레포는 하네스 팩토리(도메인 한 문장 → 에이전트 팀 + 스킬 생성 메타 스킬)다. Claude Code와 Codex 양쪽에서 동작하도록 듀얼 런타임으로 구성돼 있다. 이 파일은 Codex CLI용 진입점이다(Claude Code는 CLAUDE.md + .claude-plugin/ 사용).

하네스 팩토리 사용

  • 새 도메인/프로젝트용 하네스를 만들거나 확장·점검하려면 skills/myharness/SKILL.md를 읽고 그 워크플로우(Phase 0~7)를 따른다.
  • Codex 스킬 자동 활성화를 쓰려면 install.sh.agents/skills/myharness를 설치한다(그 후 "하네스 만들어줘" 등에 description 기반 활성화 + /skills·$myharness 명시 호출).

Codex 런타임 어댑터 (중요)

팩토리 워크플로우는 기본이 Claude Code 에이전트 팀이다(Agent 팀원 spawn + SendMessage + 공유 작업 목록 — 구 TeamCreate/TeamDelete는 v2.1.178에서 제거). Codex에선 다음으로 매핑한다:

  • 멀티 에이전트 → Codex 네이티브 subagents(내장 default/worker/explorer 또는 .codex/agents/*.toml), /agent 전환. 완전 독립 병렬은 codex exec subprocess.
  • 팀원 통신/태스크 → _workspace/ 파일 기반 전달(다음 단계가 Read).
  • 에이전트 정의 → Claude는 .claude/agents/*.md, Codex는 .codex/agents/*.toml. ⚠️ 단 .codex/agents/*.toml대화형 세션에서만 이름 호출된다 — codex exec 등 tool-backed 세션에선 로드되지 않는다(upstream openai/codex#15250, open). 그 경로에선 오케스트레이터 스킬 단독으로 동작한다.
  • 스킬 → Claude .claude/skills/, Codex .agents/skills/ (SKILL.md 포맷 동일).
  • 상세: skills/myharness/references/runtime-adapters.md, 오케스트레이션은 references/orchestrator-template.md 템플릿 D.

외부 리뷰 게이트

skills/myharness/references/external-review-loop.md — codex/agy 독립 검증. 양쪽 런타임 동일하게 subprocess로 작동. skills/myharness/scripts/check-review-tools.sh로 도구 연동 점검(없으면 게이트 생략).

codex exec 베스트 프랙티스 (자동화 시)

기본 --sandbox read-only / 쓰기만 workspace-write / 스크립트 소비 --json / 최종 메시지만 -o / 격리 --ignore-user-config / stdin은 < /dev/null.

변경 이력

날짜 변경 내용 사유
2026-06-10 Codex 듀얼 런타임 진입점 신설 Claude Code + Codex 양쪽 설치 지원
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 27 lines · 754 tokens per session scan A 44912cdd8f0b

Subscribe to this mod's changes

my_harness AGENTS.md is an instructions file published in the GitHub repository cookyman74/my_harness (80 stars, last pushed 2d ago), licensed Apache-2.0. It adds 754 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens