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-status/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-status)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/exp-status"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/exp-status/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/exp-status"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/exp-status.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.02540 |
| Opus 5 | $0.00010 | $0.01270 |
| Sonnet 5 | $0.00004 | $0.00508 |
| Haiku 4.5 | $0.00002 | $0.00254 |
Grade A, and why
exp-status 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 9d 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/exp-status
统一的实验状态监控入口。 扫描所有
running实验,对每个实验执行实时状态检查(screen session / SSH), 输出状态表(alive / anomaly / completed),引导用户下一步操作。与
/research --auto配合时作为 CronCreate 调度的定期检查器: 当 pipeline 的所有实验都完成时,自动触发/research --start-from stage4。
Inputs
- 无参数(默认):检查所有
running实验,输出状态表 --pipeline <slug>(可选):只检查属于指定 pipeline 的实验,额外输出 pipeline 整体进度--collect-ready(可选):对所有"session 已消失"的实验自动调用/exp-run --collect收集结果--auto-advance(可选,需配合--pipeline <slug>):若 pipeline 所有实验均已completed, 自动触发/research --start-from stage4,无需用户手动运行
Outputs
- 状态报告(终端输出,所有模式):running/anomaly/completed 三种状态的实验列表
wiki/experiments/{slug}.md—--collect-ready触发 Phase 4 时更新(outcome/key_result/status)wiki/outputs/pipeline-progress.md—--auto-advance时更新 current_stage → stage4(由 /research --start-from stage4 内部完成)wiki/log.md— 追加状态检查日志
Wiki Interaction
Reads
wiki/experiments/*.md— status、remote frontmatter(server/session/started)、date_plannedwiki/outputs/pipeline-progress.md—--pipeline模式下识别目标实验和 monitoring_cron_id
Writes
wiki/experiments/{slug}.md—--collect-ready模式下通过 /exp-run --collect 触发更新wiki/outputs/pipeline-progress.md—--auto-advance触发 Stage 4 时由 /research 更新wiki/log.md— 追加状态检查日志
Graph edges created
- 无(通过 /exp-run --collect 间接触发的结果写入不产生新 edges)
Workflow
前置:确认工作目录为 wiki 项目根(包含 wiki/、raw/、tools/ 的目录)。
Step 1: 收集目标实验列表
-
确定检查范围:
- 若指定
--pipeline <slug>:- 读取
wiki/outputs/pipeline-progress.md,提取stage3a_deployed字段的 slug 列表 - 若文件不存在或 slug 不匹配:报错,建议先运行
/research或手动指定
- 读取
- 否则:
- 用 Glob 扫描
wiki/experiments/*.md,过滤status == running的实验
- 用 Glob 扫描
- 若指定
-
若无 running 实验:
- 输出友好提示:
No running experiments found. - To start an experiment: /exp-run <slug> - To see all experiments: check wiki/experiments/ - 返回
- 输出友好提示:
Step 2: 逐实验状态检查
对每个目标实验并行(或依次)执行:
- 读取实验页面:从
wiki/experiments/{slug}.md获取:remote块(有则为 remote 实验)run_log路径started(来自remote.started或date_planned,用于计算 elapsed)- 部署环境(有 remote 块 → remote,否则 → local)
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.
- 9d ago First seen · 230 lines · 19 tokens per session scan A 2a8cb4214ef3
exp-status is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 2,540 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…