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/paiml/ruchy-book/gemini-mdgit clone --depth 1 https://github.com/paiml/ruchy-bookWrote 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/paiml/ruchy-book/gemini-md)<a href="https://agentmods.dev/instructions/paiml/ruchy-book/gemini-md"><img src="https://agentmods.dev/badge/instructions/paiml/ruchy-book/gemini-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 5.1 | $0.00642 | $0.00642 |
| Opus 5 | $0.00321 | $0.00321 |
| Sonnet 5 | $0.00128 | $0.00128 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
ruchy-book GEMINI.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 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Project Context
This document provides context for the Gemini AI assistant to understand the Ruchy Book project.
Project Overview
This project is the official book for the Ruchy programming language, developed with a strict Test-Driven Development (TDD) methodology. All code examples are first written as tests and verified before being included in the documentation. The book is built using mdbook.
The core philosophy is: "Test first, document what works, never promise what doesn't exist."
Technology Stack
- Ruchy (
ruchy): The programming language being documented. The project is pinned to a specific version of theruchycompiler. - mdBook (
mdbook): A utility to create books from Markdown files. Used to build the final HTML version of the book. - Rust: The integration test suite that validates all Ruchy code examples is written in Rust.
Cargo.tomldefines the testing dependencies. - Deno: Used for scripting various development and workflow tasks, such as extracting examples, running tests, and generating reports. Configuration is in
deno.json.
Development Workflow
The development process is centered around make and deno tasks.
Key Commands
- Run all tests:
make test - Build the book:
mdbook build - Serve the book locally:
mdbook serve - Run lint checks:
make dogfood-quick - Run Deno-based scripts:
(e.g.,deno task <task_name>deno task test-oneliners,deno task extract-examples)
TDD Process for New Content
- Write a test: Add a new
.ruchyfile in thetests/directory. - Verify the test: Run the test to ensure it works as expected.
- Document the feature: Add the explanation and code to a Markdown file in
src/. - Validate: Run
make validateto ensure all checks pass.
Project Structure
src/: Contains the Markdown source files for the book's chapters.tests/: Contains the Ruchy code examples, which double as integration tests.book/: The output directory for the built book (generated bymdbook).scripts/: Deno scripts for automation (testing, linting, reports).book.toml:mdbookconfiguration file.Cargo.toml: Rust project file for the test harness.deno.json: Deno configuration and task definitions.Makefile: Defines the main entry points for development tasks.INTEGRATION.md: The single source of truth for project status, test results, and quality metrics.
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 · 65 lines · 642 tokens per session scan A 3cb2b177b341
ruchy-book GEMINI.md is an instructions file published in the GitHub repository paiml/ruchy-book (11 stars, last pushed today), licensed MIT. It adds 642 tokens to every session, about $0.0032 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 2026-08-30.
Other instructions, from other repositories
deno CLAUDE.md
Claude Code instructions for denoland/deno, covering deno development guide, git workflow, high level overview, key directories and quick start.
compiler-explorer AGENTS.md
AGENTS.md instructions for compiler-explorer/compiler-explorer, covering agents.md, build & test commands, important workflow requirements, style guidelines and architecture guidelines.
moon AGENTS.md
AGENTS.md instructions for moonrepo/moon, covering agents.md, repository layout, prerequisites, rust workflow and conventions.
Better-Fullstack AGENTS.md
AGENTS.md instructions for Marve10s/Better-Fullstack, covering guidelines, web ui, workflow and bun.
pixtuoid CLAUDE.md
Claude Code instructions for IvanWng97/pixtuoid, covering claude.md, what this is, layout, build & test and workflow.
YSCV AGENTS.md
AGENTS.md instructions for enthropy7/YSCV, covering agents.md — rules for ai coding agents working on yscv, responsibility, 0. read these first, in order, 1. the five commandments and 2. the workflow.