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/marcoturi/fastify-boilerplate/agents-mdgit clone --depth 1 https://github.com/marcoturi/fastify-boilerplateWrote 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/marcoturi/fastify-boilerplate/agents-md)<a href="https://agentmods.dev/instructions/marcoturi/fastify-boilerplate/agents-md"><img src="https://agentmods.dev/badge/instructions/marcoturi/fastify-boilerplate/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 | $0.02747 | $0.02747 |
| Opus 5 | $0.01373 | $0.01373 |
| Sonnet 5 | $0.00549 | $0.00549 |
| Haiku 4.5 | $0.00275 | $0.00275 |
Grade A, and why
fastify-boilerplate 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 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding assistants (Cursor, Claude Code, GitHub Copilot, etc.)
Project overview
A production-ready Fastify 5 boilerplate using Clean Architecture, CQRS, DDD, and functional programming. TypeScript strict mode, ESM-only, Node >= 24 (native TS execution, no build step).
Quick reference
| What | Where |
|---|---|
| Package manager | pnpm (never npm or yarn) |
| Linter + formatter | Biome (never ESLint or Prettier) |
| Validation after changes | pnpm check (runs biome check && tsc --noEmit) |
| Auto-fix formatting | pnpm format |
| Unit tests | pnpm test:unit (node:test) |
| E2E tests | pnpm test:e2e (Cucumber + Gherkin) |
| Architecture validation | pnpm deps:validate (dependency-cruiser) |
| DB migrations | pnpm db:migrate (DBMate) |
Always run pnpm check after making changes. If formatting fails, run pnpm format first, then pnpm check.
Architecture
Layer boundaries (CRITICAL)
The dependency flow is strictly inward: Route → Handler → Domain → Repository.
src/
├── instrumentation.ts ← OpenTelemetry setup (loaded via --import before the app)
├── modules/ ← Feature code (vertical slices)
│ └── <feature>/
│ ├── commands/ ← State-changing operations
│ ├── queries/ ← Data-retrieval operations (idempotent)
│ ├── database/ ← Repository port (interface) + adapter (implementation)
│ ├── domain/ ← Business logic, types, errors
│ └── dtos/ ← Shared response schemas
├── server/ ← Fastify setup, plugins, DI wiring
└── shared/ ← Cross-cutting: CQRS, DB, exceptions, utils
Never import from src/shared/db/ or database/ inside handler files.
Handlers interact with data exclusively through repository ports (interfaces).
SQL belongs in repository files only.
Module independence
Modules should avoid importing directly from other modules. Cross-module communication uses the CQRS buses:
- Commands/queries for request-response
- Events for fire-and-forget notifications
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 · 232 lines · 2,747 tokens per session scan A 288f2a5aae2d
fastify-boilerplate AGENTS.md is an instructions file published in the GitHub repository marcoturi/fastify-boilerplate (462 stars, last pushed 4d ago), licensed MIT. It adds 2,747 tokens to every session, about $0.0137 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
noddde CLAUDE.md
Instructions for dogganidhal/noddde, covering noddde — claude development guide, project overview, spec authority principle, monorepo layout (turborepo + yarn) and architecture.
copilot-instructions copilot-instructions.md
Instructions for SebastienDegodez/copilot-instructions, covering copilot instructions, language policy, development code generation and workflow implementation.
event-store-adapter-js AGENTS.md
AGENTS.md instructions for j5ik2o/event-store-adapter-js, covering agents.md, 言語, github pull request のモニタリング, $grill-me 実行時の作業判断 and 軽い作業の場合.
core-banking-prototype-laravel CLAUDE.md
Claude Code instructions for FinAegis/core-banking-prototype-laravel, covering claude.md, essential commands, code quality (run before commit), development and solana operations.
nestjs-hexagonal CLAUDE.md
Instructions for Softtor/nestjs-hexagonal, covering nestjs hexagonal plugin — instructions, entry point, architecture rules (enforced by all skills and agents), skills and agents (each loads its corresponding skill).
core-banking-prototype-laravel AGENTS.md
AGENTS.md instructions for FinAegis/core-banking-prototype-laravel, covering agents.md, project overview, quick start, clone and setup and database setup.