agentmods.dev

agentic-dev-harness AGENTS.md

agentic-dev-harness AGENTS.md is an instructions file for Codex, OpenCode from kohj1018/agentic-dev-harness. It costs 1,490 tokens per session, scanned A, original, MIT.

Repository instructions for agentic-dev-harness, a document-based starter structure for projects that use several AI coding agents, such as Claude Code and OpenAI Codex.

In plain words
What is it for?
Use them when starting or maintaining a multi-agent project, updating its development documents, defining work boundaries, planning implementation, or applying the project’s simplicity rules.
Why use it?
They keep project scope, facts, assumptions, work items, and development decisions organized while preventing one agent’s support from breaking another’s.

Instructions file for CodexOpenCode

not rated 2 6d ago A scan 1,490 tokens original MIT
View the source file kohj1018/agentic-dev-harness
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/kohj1018/agentic-dev-harness/agents-md
Clone the repo
git clone --depth 1 https://github.com/kohj1018/agentic-dev-harness

Made for: 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 agentic-dev-harness AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kohj1018/agentic-dev-harness/agents-md.svg)](https://agentmods.dev/instructions/kohj1018/agentic-dev-harness/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kohj1018/agentic-dev-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/kohj1018/agentic-dev-harness/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,490 This file is loaded in full into every session.
When invoked 1,490 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 $0.01490 $0.01490
Opus 5 $0.00745 $0.00745
Sonnet 5 $0.00298 $0.00298
Haiku 4.5 $0.00149 $0.00149

Measured 3d ago against content hash 68e99a072776, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-dev-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 3d 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 · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

프로젝트 지침

목적

  • 이 저장소는 여러 AI coding agent (Claude Code, OpenAI Codex 등)에서 동일하게 동작하는 문서 중심 개발 보일러플레이트다.
  • 새 프로젝트를 시작할 때 이 구조를 복제해 빠르게 적용할 수 있어야 한다.
  • 중요한 단계마다 해당 계층의 문서를 먼저 갱신한 뒤 다음 단계로 진행한다.

핵심 행동 규율

  • ✅ 상위 문서 없이 하위 문서를 먼저 만들지 않는다.
  • 🚫 .env, secrets/, 서명키·배포 인증서·service account 키 같은 민감 파일은 읽지도 쓰지도 않는다.
  • ✅ 작업 범위와 비범위를 명확히 적고, 범위 밖 변경은 하지 않는다.
  • ✅ 흩어진 임시 메모보다 정해진 위치의 문서를 갱신한다.
  • ⚠️ 사실, 가정, 열린 질문을 구분해서 적는다. 검증 가능한 표현을 우선한다.
  • ✅ 커밋은 작고 논리적인 단위로 나눈다. 커밋 전에 관련 workitem 문서와 구현 범위가 일치하는지 확인한다.

단순성·YAGNI (구현 시 항상 적용)

  • 요구한 범위만 구현한다. 추측성 추상화·미래 대비 코드·계획에 없는 헬퍼는 만들지 않는다.
  • 동일 패턴이 3회 이상 반복될 때까지는 추출하지 않는다. 비슷한 코드 3줄이 premature abstraction보다 낫다.
  • 시스템 경계(외부 입력, 외부 API)에서만 입력 검증·에러 핸들링을 둔다. 내부 호출에는 두지 않는다.
  • WHY가 비자명할 때만 주석을 단다(숨은 제약, 미묘한 invariant, 특정 버그 우회). WHAT 주석은 좋은 식별자 이름으로 대체한다.
  • backwards-compat shim, feature flag, 사용 안 되는 변수의 _ rename 같은 호환 hack을 만들지 않는다. 정말 안 쓰면 삭제한다.
  • 변경한 모든 줄은 task의 AC 또는 명시 요청으로 거꾸로 추적 가능해야 한다. 인접 코드 개선·무관 포맷팅·기존 스타일 무시·pre-existing dead code 삭제는 금지 (ADR-006#amend-1).

정책 근거: ADR-006-simplicity-and-architecture.md.

Claude Code plan 모드

Claude Code의 빌트인 plan 모드(Shift+Tab)는 사용자 자율 도구다. 본 보일러플레이트의 lifecycle은 plan 모드를 의무화하지 않으며 산출물 경로(plansDirectory)도 강제하지 않는다. Codex 사용자도 동등한 흐름을 갖는다 (ADR-010, ADR-024).

기본 자동화 직접 지원 범위

보일러플레이트의 기본 자동화·문서 템플릿이 직접 다루는 스택은 web frontend / API server / CLI / monorepo / Supabase 통합 / Flutter(Android·iOS) 6종이다. 그 외(iOS Swift / Android Kotlin / RN / ML / embedded / game / desktop)는 ADR-031의 기본 범위 결정을 supersede하는 project ADR을 발행하는 경로 (ADR-031#amend-1, ADR-059).

TDD 기본 (구현 시 디폴트)

구현은 Red → Green → Refactor 3 phase 사이클을 디폴트로 따른다. opt-out은 task 문서의 ## 6-2. TDD opt-out에 사유와 follow-up이 모두 있을 때만. 정책 근거: ADR-009-tdd-default.md.

깊은 운영 원칙은 다음 문서를 따른다

Read the full file on GitHub · 58 lines

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. 3d ago First seen · 58 lines · 1,490 tokens per session scan A 68e99a072776

Subscribe to this mod's changes

agentic-dev-harness AGENTS.md is an instructions file published in the GitHub repository kohj1018/agentic-dev-harness (2 stars, last pushed 6d ago), licensed MIT. It adds 1,490 tokens to every session, about $0.0075 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 2026-08-31.

Building agentsagentic-workflowai-agentsboilerplateclaude-codecodex-clideveloper-tools
Related

Other instructions, from other repositories

agent-sessions CLAUDE.md

Instructions for jazzyalex/agent-sessions: This repository uses a shared playbook for all agents (Claude, Codex, Xcode, Cursor, etc.).

jazzyalex/agent-sessions · 319 tokens

agentic-qa-boilerplate AGENTS.md

Instructions for upex-galaxy/agentic-qa-boilerplate, covering agents.md: ai persistent memory, 1. critical rules: always apply, 2. behavioral layer: how ai reasons, 3. orchestration mode: permanently active and 4. context loading map: task → what to load.

upex-galaxy/agentic-qa-boilerplate · 16,213 tokens

kirby-mcp AGENTS.md

Instructions for bnomei/kirby-mcp, covering repository guidelines, scoped agent guides (keep in sync), project structure & module organization, build, test, and development commands and coding style & naming conventions.

bnomei/kirby-mcp · 860 tokens

do-it AGENTS.md

Instructions for tdwhere123/do-it, covering agents.md, file rules, repository, source of truth vs build artifacts and closed-set contracts.

tdwhere123/do-it · 873 tokens

GameStudio-CodexKIT AGENTS.md

AGENTS.md instructions for hoatv2211/GameStudio-CodexKIT, covering gamestudio-codexkit operating contract, active sources of truth, primary distribution, repository-local maintenance and evidence.

hoatv2211/GameStudio-CodexKIT · 1,547 tokens

Hipson AGENTS.md

AGENTS.md instructions for Hipson47/Hipson, covering agents.md instructions for hipson, default behavior, orchestration, subagent prompt quality and coding standards.

Hipson47/Hipson · 744 tokens