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/updatenpx skills add vedantggwp/grimoire --skill updategit 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/update)<a href="https://agentmods.dev/skills/vedantggwp/grimoire/update"><img src="https://agentmods.dev/badge/skills/vedantggwp/grimoire/update.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 | $0.00096 | $0.03774 |
| Opus 5 | $0.00048 | $0.01887 |
| Sonnet 5 | $0.00019 | $0.00755 |
| Haiku 4.5 | $0.00010 | $0.00377 |
Grade A, and why
update 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 3d 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
update
The scheduled editorial pass. Find what's new since the last run, ingest the best of it under policy, mine new connections between existing articles, detect staleness, and ship everything as a reviewable digest + pull request.
This is the "maintained" half of the LLM-maintained wiki: run builds a
grimoire, update keeps it alive.
Headless contract (read first)
NEVER use AskUserQuestion in this skill. Never pause for approval.
This skill is invoked by schedulers (GitHub Actions cron, local cron) where no
human can answer. The policy file _config/update.md is the substitute for
human judgment; PR review is the substitute for taste checkpoints. On any
ambiguity, choose the conservative option and record the decision in the
digest's "Attention Needed" section. All progress is communicated through
printed status lines and the digest — never through questions.
The two principles that survive automation:
- The human stays in control — control relocates from blocking checkpoints to (a) the authored policy and (b) async PR review. The engine never commits to the default branch.
- Plain text is the interface — every decision this skill makes is visible in the digest, the PR diff, and the policy file.
Prerequisites
- An existing grimoire workspace (
SCHEMA.mdpresent). If missing, print an error directing the user to/grimoire:new— never scaffold from here. - The plugin's compiled runtime:
${CLAUDE_PLUGIN_ROOT}/dist/compile.js(anddist/present.jswhen a site exists).
Flags
Parsed from natural language, like run:
| Flag | Behavior |
|---|---|
--dry-run |
Full analysis, zero writes: no raw/ files, no wiki edits, no source-file changes, no git operations. Derived .compile/ artifacts may regenerate (they're gitignored). Digest printed to stdout with a DRY RUN banner instead of written to _updates/. |
--workspace <path> |
Workspace root when not the current directory. |
--setup |
Install the scheduling adapter instead of running an update — see Step 12. |
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.
- 3d ago First seen · 318 lines · 96 tokens per session scan A 8deaed471fac
update is a skill published in the GitHub repository vedantggwp/grimoire (2 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 3,774 once invoked, about $0.0005 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'…
my-wiki
Manage local OKF-compatible Markdown My Wiki vaults with an AI agent. Use for capturing webpages, PDFs, Office documents, notes, images, folders, and ZIP bundles as References; maintaining Reference-to-Concept evidence links; searching or answering from a vault; checking or repairing vault health; switching among…
update-changelog
Update Starcat changelog documents in supports/starcat-pro/ by reading ALL git commits from the main Starcat project and generating categorized release notes in both English and Chinese. Use this skill whenever the user wants to update changelog, release notes, update records, or sync the changelog with recent…
moore-wechat-article-downloader
统一入口优先。wizard 返回以下 gate 时按表处理，不要立刻降级为底层命令：.
starcat-localization-sync
Starcat 本地化生产、同步与发布门禁流程。用于同步 Localizable.xcstrings 与 supports/starcat-localization 的 xcloc、生成或修复 AI 初稿、人工审核或维护者明确接受 AI 翻译、导入已批准翻译、审计 18 种语言、调整 draft/released、扩展 AppLocale，以及排查 key、状态、占位符、技术字面量、UI 或 RTL 问题。.
starcat-release
Starcat macOS App 专用双渠道发版流程。用于用户要发布或排查 App Store archive、Direct 分发、DMG 打包、Sparkle appcast 生成或上传、starcat.ink 官网与 changelog 部署、notarization、公版 tag 处理，或询问 scripts/package-appstore.sh、scripts/release-direct.sh、scripts/package-direct.sh、legacy release-store.sh 应该如何选择和运行的场景。.