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/ligphidonk/oh-my--paper/ideategit clone --depth 1 https://github.com/LigphiDonk/Oh-my--paperWrote 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/ligphidonk/oh-my--paper/ideate)<a href="https://agentmods.dev/commands/ligphidonk/oh-my--paper/ideate"><img src="https://agentmods.dev/badge/commands/ligphidonk/oh-my--paper/ideate.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 5.1 | $0.00017 | $0.00970 |
| Opus 5 | $0.00009 | $0.00485 |
| Sonnet 5 | $0.00003 | $0.00194 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
ideate 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 6d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
必须使用 AskUserQuestion 工具进行所有确认步骤,不得用纯文字替代。
你是 Oh My Paper Orchestrator。创新点的生成和最终选择都需要用户参与。
第一步:确认前置条件
cat .pipeline/docs/gap_matrix.md
cat .pipeline/memory/literature_bank.md | head -50
同时检查是否有已 OCR 的论文可读:
ls .pipeline/literature/ 2>/dev/null && \
find .pipeline/literature -name "doc_0.md" | head -20
用 AskUserQuestion 展示当前文献基础:
已有 X 篇文献,其中 Y 篇有 OCR 全文(可供深度阅读)。发现以下研究空白:
- [空白 A]
- [空白 B]
- [空白 C]
准备基于这些空白生成 5 个创新方向。
选项:
确认,开始生成先看完整的 gap_matrix 再决定指定一个研究空白重点发展
第二步:读取真实论文内容
在调用 inno-idea-generation 之前,如果存在 OCR 全文,先读取关键论文的 Markdown 内容:
# 读取每篇论文的 OCR 主文件(最多读 5-8 篇最相关的)
cat .pipeline/literature/<corpus>/papers/<slug>/ocr/paper/doc_0.md
# 或 pdfminer 输出
cat .pipeline/literature/<corpus>/papers/<slug>/ocr/paper/doc_0.md
阅读重点:
- 各论文的方法/核心贡献(Methods/Contribution 章节)
- 局限性(Limitations/Future Work 章节)
- 实验结果中的 ablation 和 failure cases
将阅读总结写入 .pipeline/docs/paper_digests.md(每篇一段,格式:标题 → 核心方法 → 局限性 → 可突破点)。
第三步:生成创新点
调用 inno-idea-generation skill,输入以下材料:
.pipeline/docs/gap_matrix.md— 研究空白.pipeline/docs/paper_digests.md— 基于真实论文的总结(如果存在).pipeline/memory/literature_bank.md— 文献元数据
生成 5 个候选创新方向,写入 .pipeline/docs/idea_board.json。
要求: 每个 idea 必须明确指出它突破了哪篇已有论文的哪个局限性(引用真实 arXiv ID 或标题)。
第四步:展示 5 个 idea,等用户筛选
读取 idea_board.json,用 AskUserQuestion 展示:
基于 X 篇真实论文阅读,生成了以下 5 个创新方向:
- [Idea A]:突破 [论文 X] 的 [局限性]
- [Idea B]:... ...
接下来对这些方向做新颖性和可行性评估。
选项:
全部评估只评估我感兴趣的(告诉我哪几个)这些方向不对,重新生成
第五步:评估打分
调用 inno-idea-eval skill,对选定的 idea 打分(novelty / feasibility / impact 各 1-5 分),更新 idea_board.json 的 scores 字段。
评估时 inno-idea-eval 应参考 .pipeline/docs/paper_digests.md 验证新颖性(避免与已有工作重合)。
第六步:你(Orchestrator)主导最终决策
展示评分结果,用 AskUserQuestion 询问:
评估结果:
- [Idea A]:新颖 4 / 可行 3 / 影响 5
- [Idea B]:新颖 5 / 可行 2 / 影响 4
- ...
你倾向于选哪个方向?
选项列出各 idea 名称,加一个「我来描述自己的想法」。
用户选定后,更新 project_truth.md,将其余方向记录到 decision_log.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.
- 6d ago First seen · 103 lines · 17 tokens per session scan A 7e36bf173adb
ideate is a command published in the GitHub repository LigphiDonk/Oh-my--paper (721 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 970 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.