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 instructions/gmoigneu/grimoire/claude-mdgit clone --depth 1 https://github.com/gmoigneu/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/instructions/gmoigneu/grimoire/claude-md)<a href="https://agentmods.dev/instructions/gmoigneu/grimoire/claude-md"><img src="https://agentmods.dev/badge/instructions/gmoigneu/grimoire/claude-md.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 | $0.00534 | $0.00534 |
| Opus 5 | $0.00267 | $0.00267 |
| Sonnet 5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
grimoire CLAUDE.md 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
GRIMOIRE (Global Repository and Index for Model Operations, Instructions and Response Engineering) is a terminal user interface (TUI) application built in Rust using ratatui. It helps users manage their prompts, agents, and skills configuration.
Build Commands
cargo build # Build debug version
cargo build --release # Build release version
cargo run # Run the application
cargo test # Run all tests
cargo test <test_name> # Run a single test
cargo clippy # Lint the code
cargo fmt # Format the code
Dependencies
- ratatui: TUI framework for building the terminal interface
- crossterm: Terminal handling (re-exported by ratatui)
- color-eyre: Error handling
Architecture Notes
This project uses Rust 2024 edition. The application should follow the typical ratatui application pattern:
use color_eyre::Result;
use ratatui::{DefaultTerminal, crossterm::event::{self, Event, KeyCode}};
fn main() -> Result<()> {
color_eyre::install()?;
let terminal = ratatui::init();
let app_result = App::default().run(terminal);
ratatui::restore();
app_result
}
struct App {
should_exit: bool,
// state fields
}
impl App {
fn run(mut self, mut terminal: DefaultTerminal) -> Result<()> {
while !self.should_exit {
terminal.draw(|frame| frame.render_widget(&mut self, frame.area()))?;
if let Event::Key(key) = event::read()? {
self.handle_key(key);
}
}
Ok(())
}
}
Key components:
ratatui::init()/ratatui::restore()for terminal setup/cleanup- Event loop polling with
event::read() terminal.draw(|frame| ...)for renderingLayout::vertical/horizontalwith constraints for arranging widgets- Common widgets:
List,Paragraph,Block,Table
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 · 73 lines · 534 tokens per session scan A c9b88dca5260
grimoire CLAUDE.md is an instructions file published in the GitHub repository gmoigneu/grimoire (6 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 534 tokens to every session, about $0.0027 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.