wassette AGENTS.md

An instruction guide for contributors and coding agents working on Wassette, an MCP server that runs WebAssembly components with Wasmtime. It points to the project’s development, architecture, release, and agent-skill documentation.

In plain words
What is it for?
Use it to navigate Wassette’s contribution process and select guidance for build and test work, Rust style checks, copyright headers, MCP Inspector testing, documentation, or pull requests.
Why use it?
It gives contributors a clear starting point and helps them find the repository rules for building, testing, coding style, documentation, and releases.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/microsoft/wassette/agents-md
Clone the repo
git clone --depth 1 https://github.com/microsoft/wassette

Made for: Codex, OpenCode.

Per session 476 This file is loaded in full into every session.
When invoked 476 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00476 $0.00476
Opus 5 $0.00238 $0.00238
Sonnet 5 $0.00095 $0.00095
Haiku 4.5 $0.00048 $0.00048

Measured 2d ago against content hash b3059fb6d6fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wassette 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 2d 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.

AGENTS.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide for Wassette

Wassette is an MCP server that runs tools as WebAssembly components with Wasmtime. This file is the entry point for coding agents and contributors; the linked documentation and skills are the canonical sources for detailed guidance.

Start here

  • Contributing: contribution requirements and release-note policy.
  • Developer guide: prerequisites, repository layout, build, test, lint, documentation, and local CI workflows.
  • Architecture: system design and component boundaries.
  • Release process: release automation and versioning.

Agent skills

Focused workflows live under .agents/skills/:

Skill Use it for
build-and-test Building the workspace, examples, and test components
rust-code-style Rust design, formatting, Clippy, and dependency checks
copyright-headers Applying the required headers to Rust files
mcp-inspector-testing Testing server behavior through MCP Inspector
documentation Writing, building, and previewing the mdBook
pull-request Writing concise, user-facing pull requests

Agents that support the Agent Skills standard should invoke the relevant skill. Other agents should read its SKILL.md before performing that workflow.

Repository requirements

  • Prefer the repository just recipes over ad-hoc commands; several recipes build required WebAssembly components before the Rust workspace.
  • Format Rust with cargo +nightly fmt, lint with cargo clippy --workspace, and check unused dependencies with cargo machete.
  • Every Rust source file must begin with the Microsoft copyright header; use ./scripts/copyright.sh.
  • Validate server-facing behavior with MCP Inspector when the change affects MCP tools, resources, prompts, transports, or runtime behavior.
  • Release notes are generated from pull request titles. Write a clear, user-facing title; do not create or update a CHANGELOG.md.

Read the full file on GitHub · 50 lines

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. 2d ago First seen · 50 lines · 476 tokens per session scan A b3059fb6d6fc

Subscribe to this mod's changes

wassette AGENTS.md is an instructions file published in the GitHub repository microsoft/wassette (938 stars, last pushed 4d ago), licensed MIT. It adds 476 tokens to every session, about $0.0024 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.