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/variable-mapnpx skills add Lambenthan/empiricalwiki --skill variable-mapgit clone --depth 1 https://github.com/Lambenthan/empiricalwikiWhat 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 | $0.00028 | $0.00499 |
| Opus 5 | $0.00014 | $0.00249 |
| Sonnet 5 | $0.00006 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
variable-map 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 2d 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
/variable-map
把分散在文献卡片里的变量信息整理成可执行的变量字典。适合回答“耐心资本怎么测算”“管理者短视有哪些口径”“ESG 用哪个数据源”。
Workflow
Step 1: Locate Relevant Pages
读取：
wiki/variables/*.mdwiki/papers/*.mdwiki/datasets/*.mdwiki/models/*.md- 当前项目的
README.md、raw/notes/research-intent.md（如果存在）
按变量名称、别名、构念、角色、标签和 source_papers 匹配。
Step 2: Build the Comparison Table
输出表格至少包含：
| 字段 | 含义 |
|---|---|
| 变量/构念 | 如耐心资本、ESG、管理者短视 |
| 模型角色 | 被解释变量、核心解释变量、中介、调节、控制等 |
| 测算口径 | 公式或文本描述 |
| 数据来源 | 数据库、表名、项目路径 |
| 样本频率 | firm-year、quarter 等 |
| 来源文献 | wiki paper slug |
| 优点 | 为什么可用 |
| 风险 | 内生性、口径争议、缺失值、复现难点 |
| 项目可用性 | 已有 / 缺失 / 需要手工整理 |
Step 3: Archive
生成：
wiki/outputs/variable-map-{slug}-{YYYY-MM-DD}.md
并追加日志：
python3 tools/research_wiki.py log wiki "variable-map | <variable> | output: outputs/<file>"
Constraints
- 只比较 wiki 或本地项目中已有证据，不凭常识补数据库表名。
- 不把不同口径强行合并；口径不同就分行。
- 如果信息来自论文但本地数据没有，明确写“项目暂缺”。
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.
- 2d ago First seen · 59 lines · 28 tokens per session scan A ed93d4bc167e
variable-map 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 499 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
fin-paper-convert
Compile LaTeX to PDF and convert to target journal format.
fin-paper-figure
Generate academic-quality figures (>=300 DPI) for economics and finance papers.
fin-full-pipeline
经济金融研究端到端完整流程。从研究想法到可投稿论文，覆盖文献综述、想法生成、新颖性验证、实证方法设计、论文大纲、正文写作、图表生成、LaTeX编译和投稿前检查。.
fin-paper-draft
经济金融论文正文写作。根据PAPEROUTLINE.md大纲和REFINEDDESIGN.md研究设计，生成完整的论文正文草稿（英文/中文），覆盖Introduction到Conclusion所有章节。.
fin-paper-plan
Generate structured paper outline adapted to target journal.
fin-experiment-design
经济金融实证方法设计。根据研究想法和REFINEDDESIGN.md，生成完整的实证研究设计方案，覆盖识别策略选择、样本构建、变量定义、稳健性检验清单和内生性处理方案。.