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/resetnpx skills add Lambenthan/empiricalwiki --skill resetgit 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/reset)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/reset"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/reset.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 | $0.00036 | $0.01193 |
| Opus 5 | $0.00018 | $0.00596 |
| Sonnet 5 | $0.00007 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00119 |
Grade A, and why
reset 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 5d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/reset
按 scope 重置 wiki 到干净 scaffold。设计目的是开发迭代和 setup 失败恢复 — 不是日常操作。
Trigger
手动:/reset --scope wiki / --scope raw / --scope log / --scope checkpoints / --scope all。可用逗号组合多个 scope:--scope wiki,log。
Inputs
--scope(必填):取值wiki— 删除wiki/<entity>/与wiki/outputs/下所有*.md,同时删除wiki/index.md、wiki/log.md和wiki/graph/下的文件。保留.gitkeep和wiki/CLAUDE.md。raw— 删除raw/papers/、raw/discovered/、raw/tmp/、raw/notes/、raw/web/下所有条目(保留.gitkeep)。log— 重置wiki/log.md为空模板。checkpoints— 通过research_wiki.py checkpoint-clear清除批处理状态。all— 以上全部。
Outputs
- 磁盘上清空 / 重置后的文件。
- 控制台摘要:已删除文件数、已重置文件数。
Wiki Interaction
读取
- 所有
wiki/<entity>/*.md(用于枚举删除清单)。 raw/<sub>/*(用于枚举 raw 删除清单)。
写入
- 删除
wiki/<entity>/*.md(保留.gitkeep)。 - 重写
wiki/index.md、wiki/graph/*,可选地重写wiki/log.md。 - 删除
raw/<sub>/*(保留.gitkeep)。
Workflow
前置条件:当前目录包含 wiki/、tools/。WIKI_ROOT=wiki/。
Step 1: 构造删除计划(dry-run)
python3 tools/reset_wiki.py --scope <scope>
该命令打印 JSON 计划,列出将要删除或重置的全部文件,不修改任何东西。按 scope 分组展示给用户(wiki entity 目录、raw 子目录、log、checkpoints)。
Step 2: 与用户确认
打印计划摘要并请求显式确认:
About to delete N files and reset M files. Continue? [y/N]
用户拒绝则退出。未经明确许可不得执行 — /reset 是破坏性操作,raw/ 的删除不可恢复。
Step 3: 执行
python3 tools/reset_wiki.py --scope <scope> --yes
工具打印 JSON 状态报告({deleted_files, reset_files})。
Step 4: 记录日志(除非已重置 log)
若执行的 scope 不包含 log,追加一条日志:
python3 tools/research_wiki.py log wiki/ "reset | scope: <scope>"
Step 5: 报告
打印结果并建议下一步:
## Reset complete — scope: <scope>
Deleted: N files
Reset: M files
Next steps:
- /init — 从 raw/ 引导 wiki
- /prefill — 沉淀基础背景知识
- /ingest — 手动添加单个来源
Constraints
- 破坏性操作前必须确认:禁止在未展示计划并征得用户同意前调用
--yes。 - 保留:
.gitkeep占位、wiki/CLAUDE.md、.claude/(skill 永不被触碰)。 raw/删除不可逆:PDF 不在 git 中。执行raw或allscope 前必须警告用户。/reset不触碰tools/、mcp-servers/、i18n/、.env或 git 状态。- scope 必填:无默认行为(
/reset不带参数时提示用户选择 scope,而非猜测)。
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.
- 5d ago First seen · 113 lines · 36 tokens per session scan A b47f0f4b133c
reset is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 1,193 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…
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
statsmodels
Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use…
seven-pass-review
Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manuscripts. Spawns 7 forked subagents in parallel (abstract, intro, methods, results, robustness, prose, citations), then synthesizes a prioritized revision checklist. Use for submission-ready or R&R-stage papers where single-pass review…
slide-excellence
Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for…
triage-inbox
Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) into a prioritized digest plus a referee-obligations tracker — classifying referee requests, R&R and editor correspondence, co-author threads, seminar and conference invites, and grant/admin deadlines, and proposing a human-gated action…