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/exp-eval)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/exp-eval"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/exp-eval.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 | $0.00034 | $0.03770 |
| Opus 5 | $0.00017 | $0.01885 |
| Sonnet 5 | $0.00007 | $0.00754 |
| Haiku 4.5 | $0.00003 | $0.00377 |
Grade A, and why
exp-eval 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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/exp-eval
将已完成实验的结果转化为 wiki 知识更新。 Review LLM 作为 impartial judge（遵循 cross-model-review），独立评估实验结果对目标 claim 的影响。 4 种判决路径：supported → claim↑ + idea validated / partially_supported → 补充实验 / not_supported → claim↓ + idea failed / inconclusive → debug。 自动更新 claims 的 confidence 和 evidence、ideas 的 status、graph edges。
Inputs
experiment：wiki/experiments/ 中的 slug（status 必须为completed）--auto（可选）：自动模式，不暂停等待用户确认 wiki 更新（用于 /research 调用）
Outputs
wiki/claims/{slug}.md— 更新 confidence、status、evidence 列表wiki/ideas/{slug}.md— 更新 status（validated/failed）、pilot_result、failure_reasonwiki/experiments/{slug}.md— 填充## Claim updatessectionwiki/graph/edges.jsonl— 新增 supports/invalidates 边wiki/graph/context_brief.md— 重建wiki/graph/open_questions.md— 重建wiki/log.md— 追加日志- VERDICT_REPORT（输出到终端）— 判决结果、wiki 变更摘要、下一步建议
Wiki Interaction
Reads
wiki/experiments/{slug}.md— 实验结果：outcome、key_result、metrics、Results sectionwiki/claims/{target-claim}.md— 目标 claim 当前状态：status、confidence、evidence 列表wiki/ideas/{linked-idea}.md— 关联 idea 当前状态wiki/experiments/*.md— 同一 claim 的其他实验结果（综合评估）wiki/graph/context_brief.md— 全局上下文.claude/skills/shared-references/cross-model-review.md— 审稿独立性原则
Writes
wiki/claims/{target-claim}.md— 更新 status、confidence、evidence、date_updatedwiki/ideas/{linked-idea}.md— 更新 status、pilot_result、failure_reason、date_resolvedwiki/experiments/{slug}.md— 填充## Claim updatessectionwiki/graph/edges.jsonl— 新增 supports 或 invalidates 边wiki/graph/context_brief.md— 重建wiki/graph/open_questions.md— 重建wiki/log.md— 追加操作日志
Graph edges created
supports：experiment → claim（实验支持该 claim）— verdict = supported 或 partially_supportedinvalidates：experiment → claim（实验否定该 claim）— verdict = not_supported
Workflow
前置：
- 确认工作目录为 wiki 项目根（包含
wiki/、raw/、tools/的目录） - 确认实验 status ==
completed（未完成的实验不能评判）
Step 1: 加载上下文
- 读取实验页面
wiki/experiments/{slug}.md：- outcome（succeeded/failed/inconclusive）
- key_result
- target_claim slug
- linked_idea slug
- metrics 和完整 Results section
- hypothesis
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 · 349 lines · 34 tokens per session scan A 03cf57585ccb
exp-eval 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 3,770 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…