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/compilenpx skills add vedantggwp/grimoire --skill compilegit 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/compile)<a href="https://agentmods.dev/skills/vedantggwp/grimoire/compile"><img src="https://agentmods.dev/badge/skills/vedantggwp/grimoire/compile.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 | $0.00061 | $0.03567 |
| Opus 5 | $0.00030 | $0.01784 |
| Sonnet 5 | $0.00012 | $0.00713 |
| Haiku 4.5 | $0.00006 | $0.00357 |
Grade A, and why
compile 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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
compile
Audit the wiki graph, repair deterministic issues, surface gaps, and build serialized indexes for downstream skills (present, serve).
Prerequisites
- A grimoire workspace must exist — check for
SCHEMA.mdin the workspace root. If missing, tell the user to run/grimoire:newfirst. - The
wiki/directory must contain at least one article (not counting index.md, overview.md, or log.md). If empty, tell the user to run/grimoire:ingestfirst.
Step 1 — Locate the Grimoire
Find the grimoire workspace:
- Look for
SCHEMA.mdin the current directory first - If not found, ask the user: "Where is your grimoire? (path to the directory containing SCHEMA.md)"
- Confirm the
wiki/directory exists and contains markdown files - Read
SCHEMA.mdto understand the topic, scope, and taxonomy
Step 2 — Run the Compile Script
Execute the Papyr Core analysis script against the workspace root:
node ${CLAUDE_PLUGIN_ROOT}/dist/compile.js {workspace}
The script auto-detects the nested wiki/ directory. Passing
{workspace}/wiki directly also works and is treated identically.
This produces JSON artifacts in {workspace}/wiki/.compile/:
| File | Contents |
|---|---|
audit.json |
Link validation, orphan analysis, centrality, components, hubs, authorities |
graph.json |
Full graph structure (nodes, edges, backlinks, orphans, statistics) |
search-index.json |
Serialized FlexSearch index (used by serve and present) |
analytics.json |
Content analytics (word distribution, reading time, tag analysis, graph metrics) |
notes.json |
Lightweight manifest (slug, title, tags, word count, headings, links) |
overview-metadata.json |
Enforcement evidence for Step 5. Top-5 centrality articles, the required-citation slug list, coverage stats, and topic clusters (support pages filtered). Step 9 audits wiki/overview.md against this file |
taxonomy-proposal.json |
Enforcement trigger for Step 5.5. Conditional — present ONLY when all three Step 5.5 conditions are met (5+ content articles, 5+ unique tags, SCHEMA taxonomy not "defined"). Contains deterministic tag cooccurrence groupings. Absence = Step 5.5 can be skipped |
What ships with it
1 file 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 · 377 lines · 61 tokens per session scan A 092ac853f183
compile is a skill published in the GitHub repository vedantggwp/grimoire (2 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 3,567 once invoked, about $0.0003 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
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.
knowledge-base
Skill "knowledge-base" from Pinvou/pinvou-agent, covering ima knowledge base, operations, routing rules, examples and file upload guard.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
knowledge-base
Build and maintain a company knowledge base as a wiki of interlinked markdown notes in the workspace — a private, compounding Wikipedia. Use when the user wants to start or organize a knowledge base / wiki, ingest sources (URLs, documents, pasted notes) into it, ask questions answered from it, or audit (lint) it.…
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
plur-memory
Your memory stays on your machine. No cloud, no tracking, no API key. PLUR makes your OpenClaw remember — and shares that memory with every other tool you use.