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/setupgit clone --depth 1 https://github.com/fivetaku/idea-labWhat 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 | $0.00117 | $0.01175 |
| Opus 5 | $0.00059 | $0.00588 |
| Sonnet 5 | $0.00023 | $0.00235 |
| Haiku 4.5 | $0.00012 | $0.00118 |
Grade A, and why
setup 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 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.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- yesterday First seen · 76 lines · 117 tokens per session scan A 2a8bd6122c1c
setup is a command published in the GitHub repository fivetaku/idea-lab (2 stars, last pushed 1mo ago), with no licence file. It adds 117 tokens to every session and 1,175 once invoked, about $0.0006 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.
upgrade
Update EVC to the latest version, re-render templates with current config, and show what changed.
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.
content-plan
Weekly content planning for {{COMPANYNAME}}'s Monday-Friday social content. The brain of the content engine.