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/newnpx skills add vedantggwp/grimoire --skill newgit 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/new)<a href="https://agentmods.dev/skills/vedantggwp/grimoire/new"><img src="https://agentmods.dev/badge/skills/vedantggwp/grimoire/new.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 | $0.00103 | $0.02973 |
| Opus 5 | $0.00051 | $0.01486 |
| Sonnet 5 | $0.00021 | $0.00595 |
| Haiku 4.5 | $0.00010 | $0.00297 |
Grade A, and why
new 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 4d 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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
new
Initialize a new Grimoire knowledge base. If run inside an existing project, intelligently discover context and pre-fill the questionnaire. Otherwise, run the full interactive flow.
Step 1 — Detect the Current Context
Before asking anything, look at the current working directory to understand what kind of environment Grimoire is being initialized in.
Check for project markers in the current directory:
| Marker | What it indicates |
|---|---|
.git/ |
A git repository |
package.json |
Node.js project |
pyproject.toml, setup.py, requirements.txt |
Python project |
Cargo.toml |
Rust project |
go.mod |
Go project |
Gemfile |
Ruby project |
pom.xml, build.gradle |
Java project |
README.md, README.rst |
Documented project |
CLAUDE.md |
Claude Code project with existing instructions |
docs/ directory |
Existing documentation |
Determine the context:
- Existing project — at least one project marker found
- Empty directory — no markers, fresh start
- Non-project directory — has files but no obvious project markers (e.g., Documents/Notes)
Step 2 — Offer the Onboarding Mode (CHECKPOINT)
Based on what was detected, present the user with a choice using AskUserQuestion.
If an existing project was detected
I see this is a {language} project ({project-name}). How would you like to start?
Options (use AskUserQuestion with these 4 options):
- Auto-discover context — "I'll read your README, CLAUDE.md, package.json, and docs/ to understand the project, then confirm each answer with you before scaffolding."
- Guided from scratch — "You answer all 7 questions manually. I won't peek at your project files."
- Hybrid — "I'll auto-discover, you review/edit each answer before I proceed."
- Tell me more first — "Show me what Grimoire does before I decide."
If the user picks option 4, briefly explain Grimoire's pipeline (scout → ingest → compile → present → serve) and re-ask.
What ships with it
8 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.
- assets/templates/archive-template.md 936 B
- assets/templates/article-template.md 1.6 KB
- assets/templates/design-config.md 3.9 KB
- assets/templates/index-template.md 977 B
- assets/templates/raw-template.md 695 B
- assets/templates/schema-template.md 3.6 KB
- assets/templates/update-config.md 1.7 KB
- references/questionnaire.md 4.7 KB
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.
- 4d ago First seen · 315 lines · 103 tokens per session scan A e2556b871385
new is a skill published in the GitHub repository vedantggwp/grimoire (2 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 2,973 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
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.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
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.