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/saffron-health/libretto/agents-mdgit clone --depth 1 https://github.com/saffron-health/librettoWrote 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/saffron-health/libretto/agents-md)<a href="https://agentmods.dev/instructions/saffron-health/libretto/agents-md"><img src="https://agentmods.dev/badge/instructions/saffron-health/libretto/agents-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 | $0.01532 | $0.01532 |
| Opus 5 | $0.00766 | $0.00766 |
| Sonnet 5 | $0.00306 | $0.00306 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
libretto AGENTS.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 6d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines
Background Context
Libretto is an open-source toolkit for building robust web integrations. It gives coding agents a live browser and a token-efficient CLI to inspect pages, capture network traffic, record user actions, and replay them as automation scripts.
Package Structure
This is a pnpm monorepo.
packages/libretto— the main Libretto package (runtime, CLI, tests)- CLI source:
packages/libretto/src/cli/ - Tests:
packages/libretto/test/*.spec.ts
- CLI source:
apps/website— marketing site (Vite / vite-plus)docs/— user-facing Mintlify documentation sitepackages/libretto/docs/— internal package documentation for implementation notes and maintainer referencesbenchmarks/— benchmark suite (imports frompackages/libretto/src/)evals/— eval suite
Important Commands
Root (runs across all packages):
pnpm -s type-check
pnpm -s test
pnpm -s lint
pnpm -s cli
-
Prefer
pnpm -s <script>(orpnpm --silent ...) for routine scripted commands when you want less pnpm noise in logs. -
Do not pipe test commands through
grep,tail, or other filters. The test reporter is minimal and token-efficient by default. -
Use
pnpm -s clito build and run the local development version of libretto.
Code Quality
- TypeScript strict mode is enabled. Do not use
any— use proper types orunknown. - Use
.jsextensions in import paths (ESM resolution requires it). - Do not add barrel files (
index.tsre-exports). Import directly from source files within the same package. - Do not add new dependencies without asking.
- Do not remove or comment out code to "clean up" without asking — it may be there for a reason.
- When code prints user-facing Libretto CLI commands, use the native
librettocommand in examples and guidance. - Errore adoption is incremental. Do not use Errore by default. Use it only when a task or existing code path explicitly opts in; the browser-tools auth-profile work and the libretto daemon startup path (
packages/libretto/src/cli/core/daemon/daemon.ts) are currently opted in. Before editing an opted-in path, read theerroreskill. Keep existing public thrown-error contracts unless the task explicitly changes them.
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.
- 6d ago First seen · 112 lines · 1,532 tokens per session scan A 42b2ccdd0949
libretto AGENTS.md is an instructions file published in the GitHub repository saffron-health/libretto (886 stars, last pushed 16d ago), licensed MIT. It adds 1,532 tokens to every session, about $0.0077 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
leaderboard AGENTS.md
AGENTS.md instructions for steel-dev/leaderboard, covering repository guidelines, project structure & module organization, build, test, and development commands, maintainer skills and coding style & naming conventions.
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).
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.
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).
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.
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.