Borrowing it
Nothing to install: this file belongs to Lambenthan/empiricalwiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Lambenthan/empiricalwiki/main/.claude/skills/exp-run/SKILL.mdgit 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/exp-run)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/exp-run"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/exp-run.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 | $0.00026 | $0.04733 |
| Opus 5 | $0.00013 | $0.02367 |
| Sonnet 5 | $0.00005 | $0.00947 |
| Haiku 4.5 | $0.00003 | $0.00473 |
Grade A, and why
exp-run 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 8d 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 — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/exp-run
执行 wiki/experiments/ 中已规划的实验。 三种运行模式,适应不同场景:
- 默认(deploy):仅 Phase 1-2,部署后立即返回,适合需要数小时/天的实验。
--collect:仅 Phase 3-4,检查已部署实验是否完成,完成则收集结果(--check为 alias)。--full:完整 Phase 1-4,适合几分钟内即可完成的本地快速实验。推荐流程:
/exp-run <slug>部署 →/exp-status监控 →/exp-run <slug> --collect收集。
Inputs
experiment:wiki/experiments/ 中的 slug- deploy 模式:status 必须为
planned - --collect 模式:status 必须为
running - --full 模式:status 必须为
planned
- deploy 模式:status 必须为
--review(可选):Phase 1 中启用 Review LLM code review 审查实验代码(deploy / full 模式有效)--collect(可选):collect 模式——检查实验是否完成,完成则收集结果;--check是 alias--full(可选):完整模式——执行全部 4 个 Phase(适合快速本地实验)--env local|remote(可选,默认local):部署环境local:本机 GPU 直接运行remote:通过 SSH 部署到远程机器(需config/server.yaml)
Outputs
- deploy 模式:
- 实验代码:
experiments/code/{slug}/(Phase 1 生成) wiki/experiments/{slug}.md— status: planned → running- DEPLOY_REPORT(输出到终端)— 部署确认、session 信息、下一步指引
wiki/log.md— 追加部署日志
- 实验代码:
- collect 模式(实验已完成时):
wiki/experiments/{slug}.md— status: running → completed,填充 outcome/key_result/date_completed- RUN_REPORT(输出到终端)— 结果摘要、metrics 对比、下一步建议
wiki/log.md— 追加收集日志
- collect 模式(实验仍在运行时):
- 仅输出进度报告到终端,不修改 wiki
- full 模式:同 deploy + collect 的全部输出
Wiki Interaction
Reads
wiki/experiments/{slug}.md— 实验配置:setup、metrics、baseline、hypothesis、target_claimwiki/claims/{target-claim}.md— 目标 claim 的上下文(理解实验目的)wiki/ideas/{linked-idea}.md— 关联 idea 的 approach sketch(指导代码实现)wiki/papers/*.md— 相关论文的方法细节和超参数(参考实现)wiki/experiments/*.md— 同一 claim 的其他实验(参考 setup、避免重复错误)
Writes
experiments/code/{slug}/— 实验代码目录(Phase 1 生成,deploy / full 模式)experiments/code/{slug}/train.py— 主训练/推理脚本experiments/code/{slug}/config.yaml— 超参数配置文件experiments/code/{slug}/run.sh— 启动封装脚本(含 CUDA_VISIBLE_DEVICES 等)experiments/code/{slug}/requirements.txt— 依赖(若与主项目不同)
wiki/experiments/{slug}.md— 更新 status、outcome、key_result、date_completed、run_log、remote 块wiki/log.md— 追加操作日志
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.
- 8d ago First seen · 404 lines · 26 tokens per session scan A 2d6654112525
exp-run is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 4,733 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
review-paper
Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated peer-review pipeline (editor + 2 dispositioned referees + editorial decision, calibrated to a target journal). R&R continuation via --peer --r2/--r3; hostile-editor stress test via…
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.
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…
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…
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…