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/vedantggwp/grimoire/servenpx skills add vedantggwp/grimoire --skill servegit clone --depth 1 https://github.com/vedantggwp/grimoireWrote 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/vedantggwp/grimoire/serve)<a href="https://agentmods.dev/skills/vedantggwp/grimoire/serve"><img src="https://agentmods.dev/badge/skills/vedantggwp/grimoire/serve.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 | $0.00073 | $0.02140 |
| Opus 5 | $0.00036 | $0.01070 |
| Sonnet 5 | $0.00015 | $0.00428 |
| Haiku 4.5 | $0.00007 | $0.00214 |
Grade A, and why
serve 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
serve
Expose a grimoire through a custom MCP server with 7 query tools over stdio.
Prerequisites
- A grimoire workspace must exist — check for
SCHEMA.md. If missing, tell the user to run/grimoire:newfirst. - The
wiki/.compile/directory must exist with JSON artifacts. If missing, tell the user to run/grimoire:compilefirst.
Step 1 — Locate the Grimoire
- Look for
SCHEMA.mdin the current directory first - If not found, ask the user for the workspace path
- Verify
wiki/.compile/exists and containsnotes.json,graph.json,analytics.json,search-index.json - Check if any
wiki/*.mdfile is newer thanwiki/.compile/graph.json. If so, warn: "Your wiki has been updated since the last compile. Run/grimoire:compilefirst for accurate results, or continue with the current index?" Wait for user response before proceeding.
Step 2 — MCP Server Invocation Shape
The MCP server runs as a long-lived process over stdio. It is launched by the MCP client (Claude Desktop, Claude Code, or any MCP-compatible tool), not from this skill directly. The invocation shape is:
node {absolute-serve-js-path} {absolute-workspace-path}
At startup the server loads:
wiki/.compile/notes.json— article manifestwiki/.compile/graph.json— graph structurewiki/.compile/analytics.json— content analyticswiki/.compile/search-index.json— FlexSearch index (imported via papyr-core)wiki/overview.md— for open questions extractionwiki/*.md— for full article retrievalSCHEMA.md— topic and scope metadata
And exposes 7 MCP tools:
| Tool | Purpose | Token Cost |
|---|---|---|
grimoire_query |
Synthesize an answer from wiki articles | Medium |
grimoire_list_topics |
Return taxonomy with article counts | Low |
grimoire_get_article |
Return a specific article by slug (auto/full/summary) | Low–Medium |
grimoire_get_section |
Return a single heading-level section of an article | Low |
grimoire_open_questions |
Return unresolved questions from overview | Low |
grimoire_coverage_gaps |
Return topics with thin or missing coverage | Low |
grimoire_search |
Full-text search across all content | Medium |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 259 lines · 73 tokens per session scan A c8ed3a94712c
serve is a skill published in the GitHub repository vedantggwp/grimoire (2 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 2,140 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
linkly-ai
Search, browse, read, and take notes across the user's documents indexed by Linkly AI — local files and linked cloud libraries. Use when the user asks to 'search my documents', 'find files about a topic', 'read a local document', 'what's in this folder', 'list the files in that library', 'browse document outlines'…
vault-for-llm
Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.
memobase
База знаний по документам — загрузка источников, ответы с цитатами, честный отказ.
dws
【何时用:仅当用户明确指向钉钉/DingTalk(钉钉文档、钉钉日程等)时使用;泛指做文档/表格/待办/审批默认走本地工具,不要误用钉钉】用 dws CLI 管理钉钉:AI表格/AI搜问(找人首选)/目标管理(Agoal)/组织大脑/日历/通讯录/群聊与机器人消息/待办/审批/考勤/日志(日报周报)/DING消息/钉钉文档/云盘/Markdown文件/AI听记/邮箱/在线电子表格(axls)/知识库/白板/开放平台文档/个人IM与OA事件订阅。用户要求操作上述钉钉产品时使用。.
package-author
当用户要把手头的工具打包/标准化成 pinvou 插件包时使用——包括纯技能(SKILL.md)、纯 MCP 服务或它们的组合包。用户说"打包/做成插件包/标准化这个工具/给我一个能上传的标准包/写 plugin.json/加个图标"等，或给了散乱脚本/目录要整理成可上传 zip 时，用本技能把内容规范成 plugin-protocol 标准包（补 plugin.json、补 mcp/manifest.json、补 SKILL.md、补图标、校验命名）。.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.