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.
npx agentmods add skills/unicorn-plugins/dmap/helpnpx skills add unicorn-plugins/dmap --skill helpgit clone --depth 1 https://github.com/unicorn-plugins/dmapWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00009 | $0.01068 |
| Opus 5 | $0.00005 | $0.00534 |
| Sonnet 5 | $0.00002 | $0.00214 |
| Haiku 4.5 | $0.00001 | $0.00107 |
Grade A, and why
help 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help
[HELP 활성화]
목표
DMAP 빌더 플러그인의 사용 가능한 명령과 자동 라우팅 규칙을 안내함. 런타임 상주 파일(AGENTS.md)에 라우팅 테이블을 등록하는 대신, 이 스킬이 호출 시에만 토큰을 사용하여 사용자 발견성을 제공함.
활성화 조건
사용자가 /dmap:help 호출 시 또는 "도움말", "뭘 할 수 있어", "DMAP 사용법" 키워드 감지 시.
워크플로우
중요: 추가적인 파일 탐색이나 에이전트 위임 없이, 아래 내용을 즉시 사용자에게 출력하세요.
사용 가능한 명령
| 명령 | 설명 |
|---|---|
/dmap:develop-plugin |
DMAP 플러그인 개발 (4-Phase 워크플로우) |
/dmap:team-planner |
팀 기획서 작성 지원 (AI 자동 완성) |
/dmap:publish |
개발 완료된 플러그인을 GitHub에 배포 |
/dmap:help |
사용 안내 (현재 보고 있는 화면) |
자동 라우팅
다음과 같은 요청은 자동으로 DMAP 빌더가 처리함:
- "플러그인 만들어줘", "DMAP 플러그인 개발" →
/dmap:develop-plugin - "팀 기획", "기획서 작성", "팀 기획서" →
/dmap:team-planner - "DMAP 설정", "빌더 설정" →
/dmap:setup - "배포해줘", "publish", "GitHub에 올려줘", "플러그인 등록" →
/dmap:publish - "도움말", "뭘 할 수 있어" →
/dmap:help
팀 기획서 작성
/dmap:team-planner로 팀 기획서를 AI 도움으로 작성 가능:
- 필수 항목(기본정보, 핵심기능, 사용자 플로우)만 입력하면 AI가 자동 완성
- 에이전트 구성 힌트, 참고 공유 자원을 자동 추천
- 완성된 기획서는
/dmap:develop-plugin에서 바로 활용 가능
플러그인 개발 워크플로우
/dmap:develop-plugin 실행 시 다음 4단계를 순차 수행함:
Phase 1: 요구사항 수집 ──→ 사용자 확인
Phase 2: 설계 및 계획 ──→ 사용자 확인
Phase 3: 플러그인 개발 ──→ 사용자 확인
Phase 4: 검증 및 완료 ──→ 사용자 확인
└──→ (선택) GitHub 배포 ──→ /dmap:publish
참조 문서
| 문서 | 경로 |
|---|---|
| DMAP 빌더 표준 | {DMAP_PLUGIN_DIR}/standards/plugin-standard.md |
| Agent 표준 | {DMAP_PLUGIN_DIR}/standards/plugin-standard-agent.md |
| Skill 표준 | {DMAP_PLUGIN_DIR}/standards/plugin-standard-skill.md |
| Gateway 표준 | {DMAP_PLUGIN_DIR}/standards/plugin-standard-gateway.md |
| 리소스 마켓플레이스 | {DMAP_PLUGIN_DIR}/resources/plugin-resources.md |
| 플러그인 개발 가이드 | {DMAP_PLUGIN_DIR}/resources/guides/plugin/plugin-dev-guide.md |
MUST 규칙
| # | 규칙 |
|---|---|
| 1 | 추가적인 파일 탐색이나 에이전트 위임 없이 즉시 출력 |
| 2 | 사용 가능한 모든 명령을 빠짐없이 나열 |
| 3 | 자동 라우팅 키워드를 정확히 안내 |
MUST NOT 규칙
| # | 금지 사항 |
|---|---|
| 1 | 파일 읽기/탐색 수행 금지 — 하드코딩된 내용만 출력 |
| 2 | 에이전트 위임 금지 |
| 3 | 표준 문서 내용을 해석/요약하여 출력 금지 — 경로 안내만 |
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.
- yesterday First seen · 122 lines · 9 tokens per session scan A a02a1936f940
help is a skill published in the GitHub repository unicorn-plugins/dmap (21 stars, last pushed 3mo ago), licensed MIT. It adds 9 tokens to every session and 1,068 once invoked, about $0.0000 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…