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 commands/fivetaku/idea-lab/idea-checkgit clone --depth 1 https://github.com/fivetaku/idea-labWrote 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/commands/fivetaku/idea-lab/idea-check)<a href="https://agentmods.dev/commands/fivetaku/idea-lab/idea-check"><img src="https://agentmods.dev/badge/commands/fivetaku/idea-lab/idea-check.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.00533 |
| Opus 5 | $0.00049 | $0.00267 |
| Sonnet 5 | $0.00020 | $0.00107 |
| Haiku 4.5 | $0.00010 | $0.00053 |
Grade A, and why
idea-check 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 4d 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.
What it actually says
/idea-check
아이디어 하나를 10-criteria/my-criteria.md에 대조해 진행·보류·기각으로 판정합니다.
실행 흐름
Step 1: 중복 확인
40-ideas/backlog.md에 같거나 비슷한 아이디어가 있는지 먼저 확인하고, 있으면 그 상태(진행·보류·기각)와 사유부터 말합니다.
Step 2: 기준 대조
기준을 하나씩 대조합니다. 걸리는 기준이 있으면 어느 지점이 어느 기준에 걸리는지 지목합니다. (기준 문서가 비어 있으면 /setup을 먼저 하자고 안내합니다.) 20-knowledge/_index.md·30-research/에 판단에 쓸 근거가 있으면 해당 파일만 읽고 인용합니다.
Step 3: 판정과 대안
- 기각: 사유(기준 번호) + 이 아이디어를 살리려면 무엇을 바꿔야 하는지 1가지
- 보류: 사유 + 재검토 조건·시점
- 진행: 다음 액션 1개 (기획서로 갈 아이디어면
/draft안내)
동의할 근거가 없는데 동의하지 않습니다. 반대할 때는 반드시 기준 번호를 댑니다.
Step 4: 기록은 미루기
이 단계에서 파일을 고치지 않습니다. 판정 결과는 아이데이션이 끝날 때 /ideation-wrap에서 한 번에 반영합니다.
(단, 사용자가 "지금 백로그에 넣어줘"라고 명시하면 바로 반영합니다.)
출력 형식
## 판정: 진행 / 보류 / 기각
- 근거: 기준 N — (걸린 지점)
- 대안: ...
참조
10-criteria/my-criteria.md40-ideas/backlog.md
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.
- 4d ago First seen · 44 lines · 99 tokens per session scan A be653a716fd8
idea-check is a command published in the GitHub repository fivetaku/idea-lab (2 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 533 once invoked, about $0.0005 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 2026-08-31.
Other commands, from other repositories
test-changed
Run the full quality gate on only the files changed since branching from main.
lesson-capture
Record structured lessons after significant tasks. Builds a persistent knowledge base that improves future agent performance. Run with an optional summary or use review to read past lessons.
export-clean
Strip internal-only elements (version drawer, review notes) from a staging HTML file to produce a clean export ready for CMS upload or public sharing.
redbeacon-diagnose
诊断 — 「这期文案/图不行」时，反推问题出在定位/选题/文案预设/图片哪个节点，再对话调准.
intel-scan
Weekly intelligence gathering for the {{COMPANYNAME}} content engine. Run on Sunday evening or Monday morning before content planning.
growth-plan
Turn diagnosis into a sized greenfield opportunity map + a sequenced, mechanism-driven capture plan to overtake competitors.