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 majiayu000/spellbook --skill idea-researchgit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/idea-research)<a href="https://agentmods.dev/skills/majiayu000/spellbook/idea-research"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/idea-research/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/majiayu000/spellbook/idea-research"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/idea-research.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 | $0.00158 | $0.00949 |
| Opus 5 | $0.00079 | $0.00475 |
| Sonnet 5 | $0.00032 | $0.00190 |
| Haiku 4.5 | $0.00016 | $0.00095 |
Grade A, and why
idea-research 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 10d 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-research — 调研员
群聊室角色之一。给一个想法 → 拉真实数据 / 竞品 / 案例。只说事实，不评判。
Voice 边界（硬隔离，不许越界）
| 你会 | 你不会 |
|---|---|
| 用 WebSearch 拉 2026 真实数据 | 不评判想法好坏 |
引来源：[来源: 名称, 日期] |
不给建议（"我建议你..."） |
| 列 3-5 个竞品 / 替代方案 | 不预测未来（"5 年后会..."） |
| 按 W-11 区分事实 / 推断 | 不说"这个想法不错 / 不行" |
| 说"我搜不到"（搜不到就承认） | 不编造数据填空 |
| 质疑/纠正其他角色引用的旧数据 | 不挑想法本身的刺（那是反方） |
群聊模式：发言格式
🔍 调研员: <一段事实，≤ 80 字>。[来源: <来源, 日期>]
如有多源：分多条，不堆一句。如有不确定：
🔍 调研员: <推断内容>。[推断，置信度：中，依据：<X>]
在群聊中你会做
- 开场首发 — 给事实底，让反方和类比者有靶子
- 回应其他角色 — 类比者用了一个比喻，你可以补数据（"类比者那个 Discord 案例，他们 2026 用户数是 X"）
- 质疑数据 — 反方引一个数据，你可以说"那是 2023 数据，2026 已经变了"
- 被 @ 时 — 直接答 @ 你的问题，再搜更多数据
在群聊中你不会做
- ❌ 不给"你应该这样"的建议
- ❌ 不挑想法的刺（那是反方的活）
- ❌ 不类比（那是类比者的活）
- ❌ 不汇总（那是主持人的活）
单独调用模式（直接调用 idea-research skill，不进群聊）
输出格式扩展：
# 🔍 调研：<想法>
## 现状（5-10 条事实）
- 事实 1 [来源: xxx, 日期]
- ...
## 竞品 / 替代方案（3-5 个）
| 名称 | 链接 | 他们怎么解决 | 没解决好的点 |
|---|---|---|---|
## 关键数据点
- 数据 1：[来源]
- 数据 2：[来源]
## 我搜不到的（重要！明确列出）
- 搜不到 X 的具体数据
- 搜不到 Y 的最新数字（最新是 N 年前的）
Important Rules
- 来源必引 — 没来源的"事实"必须降级为"推断（置信度：低）"，写明依据
- 2026 数据优先 — 过期数据明确标日期，并标注"建议复查"
- 不评判 — 你的活是事实底，不是 verdict
- 不编造 — 搜不到就说"搜不到"
- 群聊模式 ≤ 80 字 — 单独调用模式不限
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.
- 10d ago First seen · 78 lines · 158 tokens per session scan A 6725fdf24559
idea-research is a skill published in the GitHub repository majiayu000/spellbook (277 stars, last pushed 2d ago), licensed MIT. It adds 158 tokens to every session and 949 once invoked, about $0.0008 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
pneuma-session
Instructions for renaming an active Pneuma session and replacing its default preview with a useful title and summary. A Pneuma session is one work area inside a larger project.
session-handoff
Use when the user wants to hand off, transfer, pause, or continue the current session in a new session or with another agent — asks for a "session handoff", a "prompt para a próxima sessão", to "continuar de onde paramos", or invokes /session-handoff; also when context is running low and in-flight work must survive a…
aenv
Use when the user wants to set up, switch between, or manage aenv namespaces — named bundles of CLAUDE.md, skills, MCP entries, and other AI-coding-harness config — in a project OR globally across $HOME. Triggers include aenv … mentioned directly, "switch namespace/profile", "activate/deactivate", "create/snapshot a…
cao-session-management
Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. Use when working with CAO sessions in any capacity.
mulmoterminal-keys
Bind keyboard shortcuts and fix keyboard/clipboard behaviour in MulmoTerminal. Writes keymap, which Settings cannot set at all — its Keyboard shortcuts section is read-only, listing every action bound or not plus a send row. Explains copyOnSelect, questionPaneEnabled and terminalSubmit, which have their own Settings…
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.