microsoft/wassette is a runtime that loads WebAssembly Components as tools exposed through the Model Context Protocol (MCP), an interface that lets AI agents use external capabilities. It is for extending coding agents with reusable tools while isolating those tools in a Wasmtime security sandbox. The catalogue skills, instructions, and agent help configure and operate Wassette with supported MCP clients.
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 skills/microsoft/wassette/build-and-testnpx skills add microsoft/wassette --skill build-and-testgit clone --depth 1 https://github.com/microsoft/wassetteWrote 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/skills/microsoft/wassette/build-and-test)<a href="https://agentmods.dev/skills/microsoft/wassette/build-and-test"><img src="https://agentmods.dev/badge/skills/microsoft/wassette/build-and-test.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 | $0.00053 | $0.00428 |
| Opus 5 | $0.00026 | $0.00214 |
| Sonnet 5 | $0.00011 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
build-and-test 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.
What it actually says
build-and-test skill
Build Wassette and run its tests through the just recipes defined in the
repository Justfile. Prefer these recipes over raw cargo invocations so the
WebAssembly component prerequisites are built automatically.
Prerequisites
- Rust: the version pinned in
rust-toolchain.toml(nightly is required only for formatting). - Cargo: Rust's package manager.
- Just: the command runner used for every development task.
- Node.js: only needed for the MCP Inspector when debugging.
- mdBook: only needed to build documentation.
Building
just build # Debug build (default)
just build release # Release build
just build-examples # Build the example components under examples/
just clean # Remove build artifacts
Testing
just test # Build test components, then run all tests
just build-test-components # Pre-build only the test components
just clean-test-components # Remove test-component artifacts
just test runs both unit tests and documentation tests, and automatically
builds the WebAssembly components the tests depend on. When a test fails because
a component is stale, run just clean-test-components and retry.
Notes
- Run the smallest recipe that covers your change; escalate to a full
just testonly when targeted checks pass but you need broader coverage. - After changing dependencies in a
Cargo.toml, rebuild before testing. - Follow the
rust-code-styleskill for formatting and linting, and validate server behavior with themcp-inspector-testingskill before committing.
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 · 50 lines · 53 tokens per session scan A 29db8b94ca7d
build-and-test is a skill published in the GitHub repository microsoft/wassette (941 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 428 once invoked, about $0.0003 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 skills, from other repositories
tests-run
Execute Unity tests (EditMode or PlayMode) and return per-test results. Supports filtering by test assembly, namespace, class, and method. Refreshes the AssetDatabase first; defers execution across domain reloads if scripts changed. Precondition: every open scene must be saved — dirty scenes abort the run.
xcodebuildmcp-test-boundary-review
Use when reviewing XcodeBuildMCP tests for correct unit, snapshot, schema, smoke, and external process boundaries.
myco:runtime-bootstrap-and-test-isolation
Activate this skill when adding a new manager, adding a new tool category, writing or debugging tool unit tests, diagnosing tool-visibility failures, investigating startup performance, or extending/maintaining/debugging the two-tier tool discovery system (toolindex) — even if the user doesn't explicitly ask about the…
frontmcp-authorities
Use when implementing authorization and access control for FrontMCP tools, resources, prompts, or skills, deciding who may invoke what. Covers the RBAC, ABAC, and ReBAC models and when to choose each; JWT claims mapping per identity provider (Auth0, Keycloak, Okta, Cognito, Frontegg); reusable named authority…
eclipse-test
Run JUnit tests in Eclipse projects — all tests, by package, by class, or individual test methods. Also build Maven projects.
testing
To write thorough, isolated, idempotent tests — 80%+ coverage, external-only mocking, scenario-driven.