idea

idea is a skill for Claude Code, Codex from Insajin/autopus-adk. It costs 17 tokens per session (4,186 once invoked), scanned A, original, MIT.

A structured idea-discussion workflow that uses multiple AI providers to generate, compare, and judge ideas. It supports different discussion strategies, clarification levels, dissent tracking, and saving brainstorm results for later planning.

In plain words
What is it for?
Use it to brainstorm product or engineering ideas, compare perspectives, preserve disagreements, and pass a saved brainstorm into a planning workflow.
Why use it?
It helps turn an early, loosely defined idea into an organized starting point for a plan. Separate rounds and judging reduce the chance that one initial response determines the whole direction.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to brainstorm product or engineering ideas, compare perspectives, preserve disagreements, and pass a saved brainstorm into a planning workflow.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/insajin/autopus-adk/idea
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.

Any agent
npx skills add Insajin/autopus-adk --skill idea
Clone the repo
git clone --depth 1 https://github.com/Insajin/autopus-adk

Made for: Claude Code, Codex.

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 idea

README.md
[![agentmods](https://agentmods.dev/badge/skills/insajin/autopus-adk/idea/github.svg)](https://agentmods.dev/skills/insajin/autopus-adk/idea)
Your own site
<a href="https://agentmods.dev/skills/insajin/autopus-adk/idea"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/idea/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 idea

Your own site · 80×15
<a href="https://agentmods.dev/skills/insajin/autopus-adk/idea"><img src="https://agentmods.dev/badge/skills/insajin/autopus-adk/idea.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,186 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00017 $0.04186
Opus 5 $0.00009 $0.02093
Sonnet 5 $0.00003 $0.00837
Haiku 4.5 $0.00002 $0.00419

Measured 8d ago against content hash 69e27bd9d35f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

idea 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 8d 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.

.omp/skills/idea/SKILL.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Idea Skill

멀티 프로바이더 오케스트라를 활용해 아이디어를 구조화하고 발산 후 BS 파일로 저장합니다.

Canonical Semantic Contract

{
  "schema": "orchestration-contract.v1",
  "workflow": "idea",
  "semantics": {
    "forward_strategy_and_providers": true,
    "minimum_rounds": 2,
    "fallback_minimum_rounds": 2,
    "blind_separate_judge": true,
    "fresh_judge_session": true,
    "preserve_dissent": true
  }
}

사용법

/auto idea "설명" [--strategy debate|consensus|pipeline|fastest] [--providers list] [--auto] [--deep-clarify]

플래그:

  • --strategy — 오케스트레이션 전략 지정 (기본값: debate)
  • --providers — 사용할 프로바이더 목록 (기본값: orchestra 설정 전체)
  • --auto — clarification 질문 0개, inferred rows는 assumed/deferred로 기록, 완료 후 /auto plan --from-idea BS-{ID} 자동 체이닝
  • --deep-clarify — 기본 1문항 대신 최대 3문항까지 clarification 허용

저장 위치 규칙

BS 파일은 대상 모듈 기준으로 저장합니다.

  1. 아이디어 설명에서 관련 코드를 검색하여 대상 서브모듈을 자동 감지
  2. 단일 모듈 대상: {target-module}/.autopus/brainstorms/에 BS 파일 생성
  3. 크로스-모듈 (2+ 모듈): 루트 .autopus/brainstorms/에 BS 파일 생성 (meta repo 커밋 대상)
  4. 감지 실패 시 루트 .autopus/brainstorms/에 저장
  5. BS ID는 프로젝트 전체에서 유일해야 함: .autopus/brainstorms/BS-* AND */.autopus/brainstorms/BS-* 스캔

Ref: .omp/rules/autopus-doc-storage.md for full storage rules.

5단계 파이프라인

Step 1: Parse Input and Flags

# Parse user input
input = args[0]            # required: idea description
strategy = flags.strategy  # default: "debate"
providers = flags.providers # default: all configured providers
auto_chain = flags.auto    # default: false
deep_clarify = flags.deep_clarify # default: false

Step 2: Clarification Ledger Gate + What/Why/Who/When

오케스트라 실행 전에 Deep Interview-inspired clarification gate를 수행하고 Clarification Ledger를 만듭니다.

Clarification Ledger Contract

Ledger rows are exactly these fields, in this order:

Field Default impact weight Plan Handoff
goal 8 requirement seed
scope_boundary 8 explicit non-goal
constraints 5 constraint or risk seed
done_evidence 9 acceptance seed
brownfield_impact 6 reviewer focus

Read the full file on GitHub · 349 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. 8d ago First seen · 349 lines · 17 tokens per session scan A 69e27bd9d35f

Subscribe to this mod's changes

idea is a skill published in the GitHub repository Insajin/autopus-adk (111 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 4,186 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 2026-09-03.