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/setupnpx skills add Lambenthan/empiricalwiki --skill setupgit 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/setup)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/setup"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/setup.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 | $0.00034 | $0.02472 |
| Opus 5 | $0.00017 | $0.01236 |
| Sonnet 5 | $0.00007 | $0.00494 |
| Haiku 4.5 | $0.00003 | $0.00247 |
Grade B, and why
setup scanned grade B with 2 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 3d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
resp = requests.post('https://data.rag.ac.cn/api/register/sdk', json=payload, timeout=30) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
resp = requests.post('https://data.rag.ac.cn/api/register/sdk', json=payload, timeout=30) How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup
引导你完成 ΩmegaWiki 的可选 API key 配置。 读取当前
.env,展示已配置和未配置的内容,并帮助你逐步设置每个 key, 包括清晰解释每个 key 的作用和获取方式。 可随时重新运行,只更新你选择配置的 key。
Inputs
- 不需要任何参数
- 读取:
.env(当前配置状态) - 读取:
config/setup-guide.md(每个 key 的参考说明)
Outputs
- 更新后的
.env(包含新配置的 key) - 当前配置状态总结
Wiki Interaction
Reads
- 无(setup 在 wiki 创建之前运行)
Writes
- 无(不修改 wiki)
Workflow
Step 1:读取配置参考文档
读取 config/setup-guide.md,加载所有可配置 key 的完整参考信息,
包括每个 key 的作用、使用它的 skill、获取方式以及未配置时的降级行为。
Step 2:检测当前环境
运行以下命令检查已配置的内容:
python3 -c "
import sys, os
sys.path.insert(0, 'tools')
try:
import _env
except Exception:
pass
keys = {
'SEMANTIC_SCHOLAR_API_KEY': 'Semantic Scholar',
'DEEPXIV_TOKEN': 'DeepXiv',
'LLM_API_KEY': 'Review LLM(API key)',
'LLM_BASE_URL': 'Review LLM(base URL)',
'LLM_MODEL': 'Review LLM(模型名)',
}
for k, label in keys.items():
v = os.environ.get(k, '').strip()
print(f'SET:{k}' if v else f'UNSET:{k}')
"
同时检测 Python 环境和 .venv 状态:
ls .venv/ 2>/dev/null && echo "venv:present" || echo "venv:absent"
python3 --version
Step 3:展示配置状态
向用户展示清晰的状态总结,按状态分组:
ΩmegaWiki 配置状态
================================
✓ ANTHROPIC_API_KEY — 由 Claude Code 管理(claude login)
推荐配置:
✗ Semantic Scholar — 未配置(引用链扩展速度慢 3 倍,建议配置免费 key)
可选:
✗ DeepXiv — 未配置(语义搜索不可用)
✗ Review LLM — 未配置(跨模型 review 不可用)
询问用户:"您想配置哪些?(可以跳过任意一个或全部)"
Step 4:配置各 Key(用户决定)
对用户想要配置的每个 key,按以下子流程处理。
写入 .env 前必须向用户确认。
4a:Semantic Scholar API Key
解释:"Semantic Scholar 提供论文引用数据和检索功能。 被 /ingest、/init、/novelty、/ideate 使用。免费获取。 推荐配置 — 不配置的话,/init 速度慢 3 倍,引用链扩展效率大幅下降。"
引导获取:"访问 https://www.semanticscholar.org/product/api, 点击 'Get API Key',免费申请。"
询问:"您是否有 Semantic Scholar API key?(粘贴,或输入 'skip' 跳过)"
如果提供了 key,写入 .env:
使用 Edit 工具更新 .env:
- 若已有
SEMANTIC_SCHOLAR_API_KEY=(即使为空),替换该行 - 否则追加
SEMANTIC_SCHOLAR_API_KEY=<值>
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.
- 3d ago First seen · 280 lines · 34 tokens per session scan B f851b9ab388c
setup is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 2,472 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). 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。触发:/paper-workflow、帮我写一篇实证论文、 从选题到投稿、端到端 empirical paper、已有 proposal/数据/初稿要推进到投稿,或明确要求 用 Stata / R/fixest / Python-StatsPAI…
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.
chinese-code-review
中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。.
executing-plans
当你有一份书面实现计划需要在单独的会话中执行,并设有审查检查点时使用.
audit-reproducibility
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
data-analysis
End-to-end R data analysis pipeline — exploration → cleaning → regression → publication-ready tables and figures. Use when user says "analyze this dataset", "run a regression on X", "explore this CSV", "full analysis workflow", "get me summary stats and a regression", or points at a .csv/.rds/.dta and asks for…