Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/paper-draft)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/paper-draft"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/paper-draft.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 | $0.00039 | $0.03667 |
| Opus 5 | $0.00019 | $0.01834 |
| Sonnet 5 | $0.00008 | $0.00733 |
| Haiku 4.5 | $0.00004 | $0.00367 |
Grade A, and why
paper-draft 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/paper-draft
从 /paper-plan 生成的 PAPER_PLAN.md 起草完整 LaTeX 论文。 逐 section 撰写:每个 section 从 wiki 读取 claims/experiments/papers/concepts 取材, 生成 LaTeX + figures + tables。BibTeX 从 DBLP/CrossRef 获取(遵循 citation-verification), 完成后执行 de-AI polish(遵循 academic-writing)。 可选逐 section Review LLM review。输出可编译的 paper/ 目录。
Inputs
plan:PAPER_PLAN.md 的路径(如wiki/outputs/paper-plan-sparse-lora-2026-04-08.md)--review(可选):启用逐 section Review LLM review--sections(可选):只写指定 section(如--sections 3,4只写 Method + Experiments),用于增量撰写
Outputs
paper/目录(在 wiki 项目根下):paper/main.tex— 主文件(include 各 section)paper/sections/introduction.texpaper/sections/related_work.texpaper/sections/method.texpaper/sections/experiments.texpaper/sections/conclusion.texpaper/sections/appendix.tex(若有)paper/figures/— 生成的 figures(PDF/PNG)paper/tables/— 独立 table 文件(可选)paper/math_commands.tex— 共享数学符号定义paper/references.bib— 验证的 BibTeX 条目
wiki/log.md— 追加日志
Wiki Interaction
Reads
wiki/outputs/paper-plan-*.md— PAPER_PLAN(章节大纲、evidence map、figure plan、citation plan)wiki/claims/*.md— target claims 的 Statement、Evidence summary、Conditionswiki/experiments/*.md— Results、Analysis、key_result、metrics 数据wiki/papers/*.md— Method、Results、Related(作为引用内容和 baseline 参考)wiki/concepts/*.md— Definition、Formal notation、Variants(支持 Method 撰写)wiki/topics/*.md— Overview、Timeline、SOTA tracker(支持 Introduction 上下文)wiki/ideas/*.md— Motivation、Hypothesis(支持 Introduction 的 gap 叙述)wiki/people/*.md— 人名和机构(引用格式)wiki/graph/edges.jsonl— 关系图(构建论证逻辑链)wiki/graph/open_questions.md— 已知局限(写 Limitations 和 Future Work).claude/skills/shared-references/academic-writing.md— 写作规范.claude/skills/shared-references/citation-verification.md— 引用纪律
Writes
paper/目录(所有文件)wiki/log.md— 追加操作日志
Graph edges created
- 无(paper-plan 已创建 derived_from 边)
Workflow
前置:确认工作目录为 wiki 项目根(包含 wiki/、raw/、tools/ 的目录)。
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 · 330 lines · 39 tokens per session scan A 255b10dbf620
paper-draft is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 3,667 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
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.
grant-proposal
Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an /interview-me spec, delegates the data-management plan to /data-management-plan and the facilities statement to /capture-environment, and emits a funder-requirements checklist. Use…
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…
capture-environment
Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt / environment.yml / uv.lock, Stata version + ado package list), records seeds and RNG kind, optionally writes a pinning…
data-management-plan
Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data description, formats/metadata, storage/backup, access/sharing, preservation/archiving, and roles. Use when user says "data…
power-analysis
Compute statistical power, required sample size, and minimum detectable effect (MDE) for a study design, then write a registry-ready power section. Handles two-arm RCTs (with clustering / ICC and unequal allocation), multiple-arm corrections, and a simulation-based power option for non-standard designs…