develop-plugin

A four-phase workflow for creating a DMAP plugin from a team plan. It pauses for user approval after each phase.

In plain words
What is it for?
Use it to generate a DMAP-standard plugin, including its agents, skills, gateway files, directory structure, and README.
Why use it?
It gives plugin development a fixed sequence and checks each stage before continuing.

Skill for Claude CodeCodex

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 skills/unicorn-plugins/dmap/develop-plugin
Any agent
npx skills add unicorn-plugins/dmap --skill develop-plugin
Clone the repo
git clone --depth 1 https://github.com/unicorn-plugins/dmap

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 11,317 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00020 $0.11317
Opus 5 $0.00010 $0.05659
Sonnet 5 $0.00004 $0.02263
Haiku 4.5 $0.00002 $0.01132

Measured yesterday against content hash 1ac02f725e46, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

develop-plugin 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 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.

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} > .temp/{filename}'명령으로 저장하여 참조함
skills/develop-plugin/SKILL.md · 864 lines

How it starts

The opening of the file, as written. The whole thing — 864 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Develop Plugin

목표

사용자의 팀 기획서를 기반으로 DMAP 표준에 맞는 플러그인을 자동 생성함. 4-Phase 워크플로우를 순차 수행하며, 각 Phase 완료 시 사용자 승인을 받음.

Top


활성화 조건

사용자가 /dmap:develop-plugin 호출 시 또는 "플러그인 만들어줘", "DMAP 플러그인 개발" 키워드 감지 시.

Top


작업 환경 변수 로드

AGENTS.md에서 아래 환경변수 로드함. 없으면 '/dmap:team-panner'를 먼저 수행하도록 안내하고 종료.

  • AI_RUNTIME: 런타임 종류. Claude Code 또는 Claude CoWork
  • DMAP_PLUGIN_DIR: DMAP 플러그인의 루트 절대 경로
  • PLUGIN_DIR: 생성할 플러그인의 루트 절대 경로
  • PLUGIN_NAME: 생성할 플러그인 이름

Top


참조

문서 경로 용도
DMAP 빌더 표준 {DMAP_PLUGIN_DIR}/standards/plugin-standard.md 디렉토리 구조, 배포, 네임스페이스
Agent 표준 {DMAP_PLUGIN_DIR}/standards/plugin-standard-agent.md 에이전트 패키지 작성 규칙
Skill 표준 {DMAP_PLUGIN_DIR}/standards/plugin-standard-skill.md 스킬 작성 규칙, 유형별 템플릿
Gateway 표준 {DMAP_PLUGIN_DIR}/standards/plugin-standard-gateway.md install.yaml, runtime-mapping.yaml 작성
리소스 마켓플레이스 {DMAP_PLUGIN_DIR}/resources/plugin-resources.md 공유 자원 카탈로그 (office 카테고리에 pptx/xlsx/docx 가이드·템플릿·샘플 포함)
README 템플릿 {DMAP_PLUGIN_DIR}/resources/templates/plugin/README-plugin-template.md README.md 작성 참고
README 예제 {DMAP_PLUGIN_DIR}/resources/samples/plugin/README.md README.md 작성 예시
Publish 스킬 {DMAP_PLUGIN_DIR}/skills/publish/SKILL.md GitHub 배포 자동화

Top


Top


워크플로우

(중요) 특별한 언급이 없는 경우 한글로 작성함

Phase 1: 요구사항 수집

{PLUGIN_DIR/output/team-plan-{PLUGIN_NAME}.md} 팀 기획서를 분석하고, 부족한 정보를 사용자에게 문의하여 수집함.

Step 1. 요구사항 파악

사용자가 제공한 팀 기획서의 각 항목을 분석함.
팀 기획서 탐색 순서:

  1. {PLUGIN_DIR}/output/team-plan-{PLUGIN_NAME}.md 파일이 존재하면 자동 로드하여 사용
  2. 파일이 없거나 불완전하면, 사용자에게 /dmap:team-planner 스킬을 먼저 수행하도록 안내하고 종료
Step 2. 플러그인 적합여부 판단

요구사항이 DMAP 플러그인으로 구현하기 적합한지 판단함.

기준 적합 부적합
반복 가능성 반복 사용할 워크플로우 일회성 작업
역할 분리 2개 이상 전문가 역할 필요 단일 작업 수행
도구 의존성 외부 도구/API 연동 필요 순수 대화만으로 해결
도메인 지식 특정 도메인 가이드/참조 필요 범용 지식으로 충분

Read the full file on GitHub · 864 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. yesterday First seen · 864 lines · 20 tokens per session scan A 1ac02f725e46

Subscribe to this mod's changes

develop-plugin is a skill published in the GitHub repository unicorn-plugins/dmap (21 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 11,317 once invoked, about $0.0001 per session on Opus 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

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens