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 skills add Insajin/autopus-adk --skill auto-plangit clone --depth 1 https://github.com/Insajin/autopus-adkWrote 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.
[](https://agentmods.dev/skills/insajin/autopus-adk/auto-plan)<a href="https://agentmods.dev/skills/insajin/autopus-adk/auto-plan"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/auto-plan/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.
<a href="https://agentmods.dev/skills/insajin/autopus-adk/auto-plan"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/auto-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.06996 |
| Opus 5 | $0.00013 | $0.03498 |
| Sonnet 5 | $0.00005 | $0.01399 |
| Haiku 4.5 | $0.00003 | $0.00700 |
Grade A, and why
auto-plan 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.
How it starts
The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auto-plan — SPEC 작성 스킬
OMP Invocation
/auto plan .../auto-plan ...- Load detail skill
auto-planfor either entrypoint.
Context Profile: plan
- Required: core,architecture,relevant_spec
- Optional: signature,learning
- Excluded: test,canary
Context Mapping
relevant_spec means relevant SPEC evidence for the current plan.
프로젝트: autopus-adk | 모드: full
설명
단순 템플릿 생성이 아닌, 실제 코드베이스를 분석하고 컨텍스트를 수집한 후 SPEC 문서를 생성합니다. 요구사항을 EARS 형식으로 분해하고 기술 설계를 수행합니다.
사용법
/auto plan "기능 설명"
/auto plan "기능 설명" --skip-prd
/auto plan "기능 설명" --prd-mode minimal
/auto plan --from-idea BS-001 --target autopus-adk
플래그
| Flag | Description |
|---|---|
--from-idea <BS-ID> |
브레인스토밍 결과, Outcome Lock, Clarification Ledger를 컨텍스트로 사용합니다. |
--skip-prd |
PRD 생성 건너뛰고 바로 SPEC 작성. MEDIUM 난이도 권장. |
--prd-mode <mode> |
PRD 모드: standard (10섹션, 기본값) 또는 minimal (5섹션). |
--strategy <value> |
멀티 프로바이더 리뷰 전략. --multi와 함께 사용합니다. |
--target <module> |
SPEC 저장 대상 모듈을 강제합니다. |
공통 플래그
--auto: 확인 단계 생략--multi: 명시적 top-level 요청일 때 pre-authoring plan advisory를 한 번 실행하고, SPEC 생성 후 별도의 멀티 프로바이더 리뷰를 활성화--quality <mode>: 하위 에이전트 품질 모드 지정
OMP 기본 실행 모델
- OMP에서는
plan도taskbatch 기반 subagent-first로 진행합니다. - 메인 세션은 최종 SPEC 구조, 게이트 판단, 저장을 담당합니다.
- 코드베이스 스캔, 레퍼런스 탐색, 초안 작성은
explorer,planner,spec-writer같은 서브에이전트로 분담합니다. - 현재 OMP 런타임 정책이 암묵적
taskbatch 호출을 제한하면, 하네스 기본값과 제약을 명시적으로 알린 뒤 사용자에게 서브에이전트 진행 여부 또는--solo성격의 단일 세션 진행을 확인받습니다. - 단순한 한 파일 수준 문서 작업이면 메인 세션에서 직접 처리할 수 있습니다.
전체 라우팅/리뷰게이트 규칙은 /auto plan ... 라우터를 우선합니다.
실행 순서
Step 1: 플래그 파싱
다음 plan 전용 플래그를 먼저 해석합니다.
--from-idea <BS-ID>→ brainstorm 컨텍스트 로드--skip-prd--prd-mode <mode>--strategy <value>--target <module>- 글로벌
--multi/--auto/--quality
Step 1.25: Direct Intent Ledger Gate
--from-idea가 없으면 PRD 생성 전에 inline Clarification Ledger를 만듭니다. 이 gate는 auto idea의 Ledger와 같은 field/column/handoff contract를 사용합니다.
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.
- 6d ago Changed aaddc8a4644e
- 10d ago First seen · 430 lines · 25 tokens per session scan A 0045365909a6
auto-plan is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 6,996 once invoked, about $0.0001 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
automations
Create, inspect, edit, archive, delete, run, and search scheduled or executable automation assets.
job
Execution behavior for one saved automation job running in a fresh agent conversation.
api-interface-design
Use when designing public APIs, module boundaries, provider adapters, tool schemas, or data contracts.
Using OmniForge Framework
Primary guide for using OmniForge CLI, MCP Server, workflows, and agent skills effectively.
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
windows-deployment
Deploy FastAPI + React/Vite apps to Windows Server with NSSM services, reverse proxy (IIS or nginx), and git-pull workflow. Use when deploying any web app to a Windows prod server, setting up NSSM services, configuring IIS or nginx reverse proxy, making code environment-aware for dev/prod, or troubleshooting prod…