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/wasp-lang/wasp/agents-mdgit clone --depth 1 https://github.com/wasp-lang/waspWrote 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/wasp-lang/wasp/agents-md)<a href="https://agentmods.dev/instructions/wasp-lang/wasp/agents-md"><img src="https://agentmods.dev/badge/instructions/wasp-lang/wasp/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 | $0.00929 | $0.00929 |
| Opus 5 | $0.00464 | $0.00464 |
| Sonnet 5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
wasp 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wasp Monorepo
Wasp is a full-stack web framework that compiles TypeScript config (main.wasp.ts) files into React + Node.js applications. The compiler is written in Haskell.
Repository Structure
waspc/— Haskell compiler, CLI, and LSP server (the core of Wasp)src/— Main compiler library (Analyzer, Generator, AppSpec, Psl)cli/src/— CLI commands (start, build, new, deploy, etc.)data/packages/— TypeScript packages called by the CLI when compiling projects as FFIdata/Generator/libs/— TypeScript libraries embedded into generated project codedata/Generator/templates/— Mustache templates for code generatione2e-tests/— Golden file snapshot testsrun— Main development script (run./runwith no args to see all commands)
wasp-app-runner/— Node.js CLI for running Wasp apps in e2e testsweb/— Documentation website (Docusaurus), deployed to wasp.shexamples/— Tutorial and example apps (kitchen-sink, waspello, etc.)scripts/— Monorepo-level build/packaging scripts
Build & Development
All waspc development commands run from the waspc/ directory via the ./run script. Run ./run with no arguments to see the full list of available commands (build, test, format, lint, etc.).
Key things to know:
- Two-phase build: TS packages in
data/packages/and libs indata/Generator/libs/compile first, then Haskell (which embeds them). Use./run buildfor the full build. - Run the dev CLI with
./run wasp-cli <args>. - Toolchain versions are specified in
mise.toml.
Code Conventions
- When renaming a type or function, cascade the rename to parameters, local variables, and other names derived from it.
Haskell
- Simple, readable Haskell — no complicated features. See
CONTRIBUTING.md. - Default extensions are listed in
waspc/waspc.cabal. - CamelCase for types/modules, camelCase for functions/values.
- Qualified imports preferred.
- Formatting: Ormolu (
./run check:ormolu/./run format:ormolu). Linting: HLint (./run hlint, config inwaspc/.hlint.yaml). - Tests use
tasty+hspec+QuickCheck, mirroring source module paths with aTestsuffix.
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.
- 4d ago First seen · 59 lines · 929 tokens per session scan A c9afdb387ab1
wasp AGENTS.md is an instructions file published in the GitHub repository wasp-lang/wasp (18,714 stars, last pushed 5d ago), licensed MIT. It adds 929 tokens to every session, about $0.0046 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
dom-docx AGENTS.md
Instructions for floodtide/dom-docx, covering agent guide: html → docx (dom-docx), design goal for agents, what converts best, tier 1 — excellent (90–96% visual fidelity) and tier 2 — good (80–92%).
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.
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
qiankun AGENTS.md
Instructions for umijs/qiankun, covering qiankun project knowledge base, structure, architecture (big picture), commands and build (vite 8 → package javascript; tsc → declarations).
qiankun CLAUDE.md
Instructions for umijs/qiankun: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
core CLAUDE.md
Claude Code instructions for module-federation/core, covering claude task parallelization & development guidelines, core principles, maximum parallelization strategy, universal parallel task patterns and for any codebase task.