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 skills/lambenthan/empiricalwiki/ideatenpx skills add Lambenthan/empiricalwiki --skill ideategit clone --depth 1 https://github.com/Lambenthan/empiricalwikiWrote 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/lambenthan/empiricalwiki/ideate)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/ideate"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/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 | $0.00028 | $0.05299 |
| Opus 5 | $0.00014 | $0.02649 |
| Sonnet 5 | $0.00006 | $0.01060 |
| Haiku 4.5 | $0.00003 | $0.00530 |
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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ideate
基于 wiki 知识库和外部搜索,通过 5 阶段管道生成高质量研究 idea。 Phase 1 扫描研究景观(wiki + WebSearch + S2),Phase 2 双模型脑暴(Claude + Review LLM 独立生成), Phase 3 初步筛选(可行性 + 快速 novelty),Phase 4 深度验证(调用 /novelty + /review), Phase 5 写入 wiki(ideas/ + graph edges),包括被淘汰的 ideas(记录原因作为 anti-repetition 记忆)。
Inputs
direction(可选):研究方向、关键词或具体问题描述。若不指定,则从 open_questions.md 自动选择最有价值的方向。--max-ideas N(可选,默认 3):最终写入 wiki 的 idea 数量上限--skip-validation:跳过 Phase 4 深度验证(快速模式,仅做 Phase 1-3 + Phase 5)--auto:全自动模式,不暂停等待用户确认(用于 /research 调用)
Outputs
wiki/ideas/{slug}.md— 每个 idea 一个页面(status: proposed),包含 top ideas 和被淘汰的 ideaswiki/graph/edges.jsonl— 新增 idea → claim/gap 的关系边wiki/graph/context_brief.md— 重建后的压缩上下文wiki/graph/open_questions.md— 重建后的知识缺口图- IDEA_REPORT(输出到终端)— 管道执行摘要、排名结果、novelty 评分
Wiki Interaction
Reads
wiki/graph/context_brief.md— 全局上下文wiki/graph/open_questions.md— 知识缺口,驱动 idea 方向wiki/ideas/*.md— 已有 ideas,特别是 status=failed 的 ideas 及 failure_reason(banlist)wiki/claims/*.md— 当前 claims 状态,识别 weakly_supported 和 challenged claimswiki/papers/*.md— 已有论文方法和结果wiki/concepts/*.md— 技术概念,寻找跨领域组合机会wiki/topics/*.md— 研究方向地图,SOTA 和 open problemswiki/experiments/*.md— 已有实验结果,避免重复
Writes
wiki/ideas/{slug}.md— 创建新 idea 页面wiki/graph/edges.jsonl— 添加 idea → claim/gap 的关系边(addresses_gap, inspired_by)wiki/graph/context_brief.md— 重建wiki/graph/open_questions.md— 重建wiki/log.md— 追加操作日志
Graph edges created
addresses_gap:idea → claim/topic(idea 针对的知识缺口)inspired_by:idea → paper/concept(idea 的灵感来源)
Workflow
前置:
- 确认工作目录为 wiki 项目根(包含
wiki/、raw/、tools/的目录) - 检查 wiki 成熟度:
根据 maturity level 调整后续行为:python3 tools/research_wiki.py maturity wiki/ --json- cold:Phase 1 外部搜索扩展(WebSearch 查询从 5 增至 8,S2/DeepXiv limit 从 20 增至 30), 跳过 wiki 内部上下文加载(为空无意义),标注 "cold-start mode: heavier external search"
- warm:标准行为(当前默认)
- hot:Phase 1 外部搜索缩减(WebSearch 查询从 5 降至 2,S2/DeepXiv limit 从 20 降至 10), Phase 3 gap_alignment_bonus 从 +2 提升到 +3,优先解决 wiki 中已有的 weak claims
- Snapshot wiki 状态(用于结束时的 Growth Report):
保存 maturity 返回的 JSON 到内存变量
maturity_before
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 · 402 lines · 28 tokens per session scan A a428ef696c3f
ideate is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 5,299 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 skills, from other repositories
paper-workflow
经管 / 社科实证论文全流程 meta-orchestrator:把选题、设计、数据、估计、方法闸门、 表图、写作、去 AI 味、质量门、修订、投稿与复盘编排成 Stage 0–9 可断点续跑流水线。 本 skill 不重复实现子能力,而是按阶段调用既有 skill 或并行 subagent,并在 Stage 3–4 路由 Python/StatsPAI、Stata、R 三种分析后端,Stage 9 交付一份含正文+表+图+参考文献的 Word 全文定稿(09submission/main.docx,另可出 .tex)。触发:/paper-workflow、 帮我写一篇实证论文、从选题到投稿、端到端 empirical…
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
seven-pass-review
Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manuscripts. Spawns 7 forked subagents in parallel (abstract, intro, methods, results, robustness, prose, citations), then synthesizes a prioritized revision checklist. Use for submission-ready or R&R-stage papers where single-pass review…
slide-excellence
Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for…
triage-inbox
Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) into a prioritized digest plus a referee-obligations tracker — classifying referee requests, R&R and editor correspondence, co-author threads, seminar and conference invites, and grant/admin deadlines, and proposing a human-gated action…
scaffold-exercises
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key"…