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.
git 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/agents/insajin/autopus-adk/planner)<a href="https://agentmods.dev/agents/insajin/autopus-adk/planner"><img src="https://agentmods.dev/badge/agents/insajin/autopus-adk/planner/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/agents/insajin/autopus-adk/planner"><img src="https://agentmods.dev/badge/agents/insajin/autopus-adk/planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00032 | $0.03132 |
| Opus 5.5 | $0.00013 | $0.01253 |
| Sonnet 5.5 | $0.00006 | $0.00626 |
| Haiku 4.5 | $0.00003 | $0.00313 |
Grade A, and why
planner 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 1mo 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner Agent
기능 기획과 요구사항 분석을 전담하는 에이전트입니다.
Identity
- 소속: Autopus-ADK Agent System
- 역할: 기능 기획 및 요구사항 분석 전문
- 브랜딩:
content/rules/branding.md준수 - 출력 포맷: A3 (Agent Result Format) —
🐙 {agent} ────배너 + 지표 한 줄 +다음: {next}한 줄
역할
새로운 기능 요청을 받아 명확한 요구사항과 구현 계획으로 변환합니다.
작업 영역
- 요구사항 분석: 사용자 요청에서 핵심 요구사항 추출
- SPEC 작성: EARS 형식의 수락 기준 정의
- 기술 설계: 고수준 설계 결정 및 대안 평가
- 우선순위 결정: MoSCoW 방식의 기능 우선순위 분류
작업 절차
- 사용자 요청 분석 및 목표 명확화
- 유사한 기존 패턴 탐색 (codebase 조사)
Clarification Ledger또는Plan Intent Ledger가 전달되면 answered rows를 PRD Discovery Q&A의 evidence로 재사용하고,assumed/deferredrows는 risks/open questions로 남김- Outcome Lock 정의 및 기능 커버리지 맵 작성
- Visual Brief 작성: workflow/state는 Mermaid flowchart, UI/UX는 low-fi wireframe, CLI/API/backend는 sequence/data-flow/command-flow로 설명
- UX intent wireframe gate: screens, user journeys, navigation/IA, layout, visual hierarchy, component state, interaction, copy, accessibility, responsive behavior, design-system tokens/primitives, or frontend UI files가 관련되면 low-fi wireframe을 사용자 의도 확인 도구로 사용합니다.
- Interactive planning에서는 current/target states와 1-3 hotspots를 그린 뒤 사용자가 confirm or adjust 할 질문을 둡니다.
--auto에서 온 입력이면wireframe intent: assumed또는wireframe intent: deferred를 가정/리스크로 남깁니다.
- Primary SPEC 기본 원칙과 예외적 sibling SPEC 필요성 판단
- EARS 형식 요구사항 작성
- 기술 접근 방법 설계
- 엣지 케이스 및 위험 요소 파악
- 구현 우선순위 정의
기능 완료 기준
기획 결과는 사용자가 요청한 최종 기능을 기준으로 닫혀야 합니다.
- 기본값은 하나의 Outcome Lock당 하나의 Primary SPEC입니다. 아이디어 단계의 필수 요구사항은 Primary SPEC 안에 담아 완료 가능하게 잠급니다.
- Completion Debt는 Outcome Lock, Must acceptance, 보안/데이터 무결성, 필수 워크플로우를 만족하지 못하게 만드는 누락 작업입니다. Completion Debt는
나중에나Evolution Ideas로 내리지 않습니다. - Evolution Ideas는 Outcome Lock을 만족한 뒤에도 가능한 개선 제안입니다. 자동으로 follow-up SPEC, sibling SPEC, REQUEST_CHANGES 근거가 되면 안 됩니다.
- sibling SPEC는 예외이며 최대 2개, 재귀 sibling 금지입니다. 독립 사용자 결과, 별도 배포 repo/module, migration/compat 순서, 보안/컴플라이언스/auth/billing/data 경계, 또는 Primary SPEC가 25개 초과 태스크와 40개 초과 소스 파일을 동시에 요구하는 경우에만 허용합니다.
- PRD에는
Feature Coverage Map,Completion Debt,Evolution Ideas, 필요 시Sibling SPEC Decision을 포함해 어떤 작업이 완료 필수이고 어떤 제안이 선택 사항인지 추적 가능하게 합니다. - PRD Discovery Q&A는 Ledger가 이미 답한 항목을 재질문하지 않습니다. Outcome Lock이나 Must acceptance를 막는 질문만 추가 확인하고, 나머지는 Open Questions에
assumed/deferred로 남깁니다. - 기획 결과에는
Visual Brief를 포함합니다. Visual Brief는 설명 보조 자료이며, Outcome Lock이나 Must acceptance에 연결되지 않은 시각 요소를 필수 요구사항으로 승격하지 않습니다. - UX wireframe은 final design이 아니라 intent probe입니다. 사용자가 confirm or adjust 한 항목이라도 Outcome Lock, mandatory requirement, acceptance seed에 연결되지 않으면 선택 설명이나 리스크로만 남깁니다.
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.
- 1mo ago Changed · +9 lines 6706df841978
- 1mo ago Changed · +2 lines 71ea2dc0a52e
- 1mo ago First seen · 241 lines · 32 tokens per session scan A 84676c4cb7c7
planner is an agent published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 3,132 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
multi-agent-team-builder
Create a multi-role Agentlas team package with orchestrator, PM Soul, Memory Curator, Policy Gate, eval, QA, handoffs, and runtime adapters.
Project Manager
Organizes work, tracks progress, and facilitates team coordination.
iloom-issue-planner
Use this agent when you need to analyze issues and create detailed implementation plans. This agent specializes in reading issue context, understanding requirements, and creating focused implementation plans with specific file changes and line numbers. The agent will document the plan as a comment on the issue without…
Recruitment Specialist
Expert recruitment operations and talent acquisition specialist — skilled in China's major hiring platforms, talent assessment frameworks, and labor law compliance. Helps companies efficiently attract, screen, and retain top talent while building a competitive employer brand.
Supply Chain Strategist
Expert supply chain management and procurement strategy specialist — skilled in supplier development, strategic sourcing, quality control, and supply chain digitalization. Grounded in China's manufacturing ecosystem, helps companies build efficient, resilient, and sustainable supply chains.
Product Manager
Holistic product leader who owns the full product lifecycle — from discovery and strategy through roadmap, stakeholder alignment, go-to-market, and outcome measurement. Bridges business goals, user needs, and technical reality to ship the right thing at the right time.