dmap: Instructions file for Codex

AGENTS.md

dmap AGENTS.md is an instructions file for Codex, OpenCode from unicorn-plugins/dmap. It costs 1,993 tokens per session, scanned A, original, MIT.

Repository instructions for dmap, a builder for declarative multi-agent plugins. They describe the company context, conversation rules, documentation style, and Git-related behavior.

In plain words
What is it for?
Use them when developing dmap, answering project questions, writing its documentation, consulting linked material, or handling requested Git pull and push operations.
Why use it?
They help an agent follow the repository’s language, response, planning, documentation, and version-control conventions. Without them, changes or answers could conflict with the project’s agreed workflow.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is unicorn-plugins/dmap's own configuration. It tells Codex and OpenCode how to work on dmap 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 dmap configures →

Reuse

Borrowing it

Nothing to install: this file belongs to unicorn-plugins/dmap. 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/unicorn-plugins/dmap/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/unicorn-plugins/dmap

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 dmap AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/unicorn-plugins/dmap/agents-md/github.svg)](https://agentmods.dev/instructions/unicorn-plugins/dmap/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/unicorn-plugins/dmap/agents-md"><img src="https://agentmods.dev/badge/instructions/unicorn-plugins/dmap/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dmap AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/unicorn-plugins/dmap/agents-md"><img src="https://agentmods.dev/badge/instructions/unicorn-plugins/dmap/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,993 This file is loaded in full into every session.
When invoked 1,993 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01993 $0.01993
Opus 5.5 $0.00797 $0.00797
Sonnet 5.5 $0.00399 $0.00399
Haiku 4.5 $0.00199 $0.00199

Measured 2mo ago against content hash 8c8aee347f92, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dmap AGENTS.md scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- URL링크는 WebFetch가 아닌 'curl {URL} > claude/{filename}'명령으로 저장
AGENTS.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

목표

선언형 멀티에이전트 플러그인(Declarative Multi-Agent Plugin. 이하 DMAP) 빌더 개발

  • DMAP 빌더 개발
  • DMAP 외부 발표 준비

회사소개

  • 이름: 유니콘주식회사
  • 설립일: 2022.2.28
  • 업종: 시스템 소프트웨어 개발 및 공급업, 직원 훈련기관
  • 주요사업
    • 직원역량 교육: AI, 서비스 기획, 애자일, 마이크로서비스, Cloud Native Application, CI/CD, 클라우드
    • IT 컨설팅: 서비스 기획, MSA설계/개발, 애자일 코칭, CI/CD

팀 행동원칙

  • 'M'사상을 믿고 실천한다. : Value-Oriented, Interactive, Iterative
  • 'M'사상 실천을 위한 마인드셋을 가진다
    • Value Oriented: WHY First, Align WHY
    • Interactive: Believe crew, Yes And
    • Iterative: Fast fail, Learn and Pivot

대화 가이드

  • 'q:'로 시작하면 질문임. Fact와 Opinion으로 나누어 답변
  • 특별한 언급이 없으면 한국어로 대화
  • (중요) "답변할 때 답변하는 사람의 별명" 표시

최적안 가이드

'o:'로 시작하면 최적안을 도출하라는 요청임

  1. 각자의 생각을 얘기함
  2. 의견을 종합하여 동일한 건 한 개만 남기고 비슷한 건 합침
  3. 최적안 후보 5개를 선정함
  4. 각 최적안 후보 5개에 대해 평가함
  5. 최적안 1개를 선정함
  6. "1) ~ 5)번" 과정을 10번 반복함
  7. 최종으로 선정된 최적안을 제시함

Git 연동

  • "pull" 명령어 입력 시 Git pull 명령을 수행하고 충돌이 있을 때 최신 파일로 병합 수행
  • "push" 또는 "푸시" 명령어 입력 시 git add, commit, push를 수행
  • Commit Message는 한글로 함

URL링크 참조

  • URL링크는 WebFetch가 아닌 'curl {URL} > claude/{filename}'명령으로 저장
  • 동일한 파일이 있으면 덮어 씀
  • '.dmap'디렉토리가 없으면 생성하고 다운로드
  • 저장된 파일을 읽어 사용함

마크다운 작성 가이드

(중요) 플로그인 표준 문서(standards 디렉토리 하위 존재)에는 적용하지 않음

기본

  • 문서 작성 시 명사체(명사형 종결어미) 사용
    • 예시: "~한다" → "~함", "~이다" → "~임", "~된다" → "~됨"
    • 예시: "지원한다" → "지원", "사용할 수 있다" → "사용 가능"
  • 한 줄은 120자 이내로 작성, 긴 문장은 적절히 줄바꿈
    • 마크다운 줄바꿈: 문장 끝에 스페이스 2개 + 줄바꿈
  • 간결하고 객관적인 기술 문서 스타일 유지

목차 및 구분선

# 1. 목차(TOC) 추가
- 파일 최상단의 `# 제목` 바로 아래에 목차를 추가
- 목차는 `# `, `## `, `### ` 헤딩을 기반으로 생성
- 형식: 마크다운 링크 목록 (GitHub 스타일 앵커)
- 첫 번째 `# ` 항목은 `- [제목](#앵커)` 형식 (인덴트 없음, 최상위)
- 두 번째 이후 `# ` 항목은 `- [제목](#앵커)` 형식 (인덴트 없음)
- `## ` 항목은 `  - [제목](#앵커)` 형식 (인덴트 2칸)
- `### ` 항목은 `    - [제목](#앵커)` 형식 (인덴트 4칸)

앵커 생성 규칙:
- 소문자 변환
- 공백 → `-`
- 특수문자(괄호, 마침표, 콤마, 콜론 등) 제거
- 한글은 그대로 유지
- 예: `## 1.1 개요` → `#11-개요`
- 예: `### STEP 1. 문서 준비` → `#step-1-문서-준비`

# 2. `---` 구분선 추가
- 모든 `## ` (level-2) 헤딩 바로 위에 `---` 수평선 추가
- 형식:
#앵커

---
다음 섹션

# 3. `[Top]` 링크 추가
- 각 `## ` (level-2) 섹션의 마지막에 `[Top](#앵커)` 링크 추가
- 앵커는 파일의 `# 제목`에 해당하는 앵커
- 다음 `---` 바로 위에 위치
- 파일의 마지막 `## ` 섹션에도 끝에 `[Top]` 링크 추가

# 주의사항
- 기존 내용은 절대 수정하지 마세요
- 이미 `---`나 `[Top]`이 있는 파일은 중복 추가하지 마세요
- `# ` (level-1) 헤딩이 파일에 여러 개 있을 수 있음
  - 목차는 첫 번째 `# ` 헤딩 기준으로 생성
  - `[Top]` 링크는 `## ` (level-2) 섹션에만 추가
  - `# ` (level-1) 헤딩에는 `[Top]` 링크를 추가하지 않음
- 코드블록(``` 또는 ~~~) 안의 `##`는 헤딩이 아니므로 무시

Read the full file on GitHub · 150 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. 2mo ago First seen · 150 lines · 1,993 tokens per session scan A 8c8aee347f92

Subscribe to this mod's changes

dmap AGENTS.md is an instructions file published in the GitHub repository unicorn-plugins/dmap (21 stars, last pushed 5mo ago), licensed MIT. It adds 1,993 tokens to every session, about $0.0080 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

dmap AGENTS.md compared with instructions from other repositories

dmap AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dmap AGENTS.mdunicorn-plugins/dmapInstructions file215mo agoMITA1,993Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode