libretto: Instructions file for Claude Code

CLAUDE.md

libretto CLAUDE.md is an instructions file for Claude Code from saffron-health/libretto. It costs 352 tokens per session, scanned A, original, MIT.

Repository instructions for Libretto, a monorepo—a project that keeps several related packages together. They explain how to release regular or experimental versions and keep duplicated files in sync.

In plain words
What is it for?
Use them when changing Libretto, preparing patch, minor, or major releases, publishing an experimental version, or synchronising skill files and README copies.
Why use it?
They reduce release mistakes, such as editing mirrored files or package versions by hand. They also make the release and publishing steps repeatable.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is saffron-health/libretto's own configuration. It tells Claude Code how to work on libretto itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything libretto configures →

Reuse

Borrowing it

Nothing to install: this file belongs to saffron-health/libretto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/saffron-health/libretto/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/saffron-health/libretto

Made for: Claude Code.

Wrote 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.

agentmods badge for libretto CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/saffron-health/libretto/claude-md/github.svg)](https://agentmods.dev/instructions/saffron-health/libretto/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/saffron-health/libretto/claude-md"><img src="https://agentmods.dev/badge/instructions/saffron-health/libretto/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for libretto CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/saffron-health/libretto/claude-md"><img src="https://agentmods.dev/badge/instructions/saffron-health/libretto/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 352 This file is loaded in full into every session.
When invoked 352 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00352 $0.00352
Opus 5 $0.00176 $0.00176
Sonnet 5 $0.00070 $0.00070
Haiku 4.5 $0.00035 $0.00035

Measured 9d ago against content hash 77cbdad712ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

libretto 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 9d 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.

CLAUDE.md · 41 lines

What it actually says

Libretto Monorepo

Releasing a New Version

Never manually edit packages/libretto/package.json version. Use the release script:

pnpm prepare-release [patch|minor|major]

This bumps the version, updates all SKILL.md files, syncs mirrors, validates parity, commits, pushes a release-v* branch, and opens a PR. The release CI workflow triggers automatically when the PR merges to main.

Publishing an Experimental Version

Temporarily set a pre-release version in packages/libretto/package.json and replace its workspace: and catalog: dependency ranges with published ranges. Then run:

pnpm publish:experimental

Approve npm's browser passkey prompt and verify the exact version installs in a clean project. Do not commit the temporary manifest edits.

Mirror System

Skill files and READMEs are mirrored across multiple locations. Do not hand-edit the mirrored copies. Edit source files only, then sync.

Source directories:

  • packages/libretto/skills/libretto/ — interactive Libretto skill (source of truth)
  • packages/libretto/skills/libretto-readonly/ — read-only diagnosis skill (source of truth)

Mirror targets (generated — never edit directly):

  • .agents/skills/libretto/ and .agents/skills/libretto-readonly/
  • .claude/skills/libretto/ and .claude/skills/libretto-readonly/

After any change to source skill files or READMEs:

pnpm sync:mirrors    # sync all mirrored files
pnpm check:mirrors   # validate everything is in sync
Changes

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.

  1. 9d ago First seen · 41 lines · 352 tokens per session scan A 77cbdad712ec

Subscribe to this mod's changes

libretto CLAUDE.md is an instructions file published in the GitHub repository saffron-health/libretto (889 stars, last pushed 18d ago), licensed MIT. It adds 352 tokens to every session, about $0.0018 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens