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/initnpx skills add Lambenthan/empiricalwiki --skill initgit 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/init)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/init"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/init.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 | $0.00031 | $0.04387 |
| Opus 5 | $0.00015 | $0.02194 |
| Sonnet 5 | $0.00006 | $0.00877 |
| Haiku 4.5 | $0.00003 | $0.00439 |
Grade A, and why
init 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 4d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/init
从
raw/搭建 wiki:先做确定性 prepare,再跑 planner-guided discovery;raw/notes/与raw/web/可种下 provisional scaffold;论文消化仍走并行/ingestfan-out / fan-in。
按需打开这些本地参考文件:
references/prepare-and-discovery.md— prepare 流程、最终选择、fetch 与 source-manifest 规则references/planner-policy.md— planner 行为与 LLM 裁剪期望references/parallel-ingest.md— worktree 隔离、子代理 prompt 合同、merge 与清理
Inputs
topic(可选):研究方向关键词;当raw/已定义 seed set 时可省略--no-introduction(可选):禁用外部发现;仅在用户明确要求时使用- 用户自有素材:
raw/papers/、raw/notes/、raw/web/
Outputs
wiki/骨架与 provisional 页面(Summary、topics、ideas、concepts、claims)raw/tmp/与raw/discovered/预处理来源- 并行
/ingest产出的最终论文页面 .checkpoints/init-*.json清单,用于恢复与重放- 更新后的
wiki/index.md、wiki/log.md、wiki/graph/*
Wiki Interaction
Reads
raw/papers/、raw/notes/、raw/web/.checkpoints/init-prepare.json与.checkpoints/init-sources.json,供 resume、planning 与 fan-out 使用wiki/index.md以及已有wiki/topics/、wiki/ideas/、wiki/concepts/、wiki/claims/
Writes
wiki/scaffold 与 provisional 页面raw/tmp/与raw/discovered/wiki/index.md、wiki/log.md、wiki/graph/*.checkpoints/init-prepare.json、.checkpoints/init-plan.json、.checkpoints/init-sources.json与init-sessioncheckpoint metadata
Graph edges created
/init本身只在 provisional 页面需要时写入少量 scaffold 级别的 edges- 论文驱动的 edges 全部委托给
/ingest
Workflow
前置条件:当前目录为项目根,且包含 wiki/、raw/、tools/。设 WIKI_ROOT=wiki/。先解析一次 PYTHON_BIN,并在整个 /init 流程里复用它,确保运行时使用与 setup.sh 安装依赖时相同的解释器:
# 通过 git 找到项目根,让 worktree 中的 subagent 也能定位 .venv。
# .venv 被 gitignore,subagent 的 cwd 在 ../.worktrees/<branch>/ 时本地没有
# .venv——若不解析项目根,PYTHON_BIN 会回退到系统 python3,既丢失 .env 里的
# API key,也丢失安装的依赖(deepxiv-sdk 等)。
# git rev-parse --git-common-dir 无论 cwd 位于哪个 worktree 都返回主仓库的
# .git 目录;其父目录即项目根。
GIT_COMMON_DIR=$(git rev-parse --git-common-dir 2>/dev/null || true)
PROJECT_ROOT=""
if [ -n "$GIT_COMMON_DIR" ]; then
PROJECT_ROOT=$(cd "$(dirname "$GIT_COMMON_DIR")" 2>/dev/null && pwd)
fi
if [ -x "$PROJECT_ROOT/.venv/bin/python" ]; then PYTHON_BIN="$PROJECT_ROOT/.venv/bin/python"
elif [ -x "$PROJECT_ROOT/.venv/Scripts/python.exe" ]; then PYTHON_BIN="$PROJECT_ROOT/.venv/Scripts/python.exe"
elif [ -x .venv/bin/python ]; then PYTHON_BIN=.venv/bin/python
elif [ -x .venv/Scripts/python.exe ]; then PYTHON_BIN=.venv/Scripts/python.exe
else PYTHON_BIN=python3
fi
export PYTHON_BIN
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 262 lines · 31 tokens per session scan A c4ce4242ae3c
init is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 4,387 once invoked, about $0.0002 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…
preregister
Draft a structured preregistration document (OSF, AsPredicted, or AEA RCT Registry style) from a research spec or free-form study description. Output is a Markdown file with hypotheses, design, sampling plan, analysis plan, exclusions, and inference criteria — annotated with MUST / SHOULD / MAY clarity flags. Use when…
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…
extract-tikz
Extract TikZ diagrams from Beamer .tex source, compile each to a standalone PDF, and convert to SVG with 0-based indexing. Use when user says "extract the tikz", "regenerate the diagrams", "rebuild the SVGs", "sync tikz to quarto", or after editing TikZ blocks in a Beamer deck that also has a Quarto mirror.
qa-quarto
Adversarial Quarto-vs-Beamer parity QA. A critic agent compares the Quarto HTML render to the Beamer PDF benchmark for content/visual parity; a fixer agent applies fixes; loops until APPROVED (max 5 rounds). Use when user says "qa the quarto", "check parity", "does the html match the pdf?", "quarto matches beamer?"…
compile-latex
Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when user says "compile", "build the slides", "rebuild the PDF", "run latex", "render the tex", or asks why a .tex file isn't producing a PDF. Operates on Slides/.tex.