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/documentationnpx skills add microsoft/wassette --skill documentationgit clone --depth 1 https://github.com/microsoft/wassetteWhat 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 | $0.00049 | $0.00411 |
| Opus 5 | $0.00024 | $0.00205 |
| Sonnet 5 | $0.00010 | $0.00082 |
| Haiku 4.5 | $0.00005 | $0.00041 |
Grade A, and why
documentation 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.
What it actually says
documentation skill
Wassette documentation lives under docs/ and is built with
mdBook.
Build and serve
just docs-build # Build static HTML to docs/book/
just docs-watch # Serve at http://localhost:3000 with live reload
just docs-serve # Serve and open in the browser
Or directly: cd docs && mdbook serve / mdbook build.
URL structure
Production uses a multi-version layout that mdbook serve does not reproduce
locally:
- Local: open
http://localhost:3000/overview.html(or a specific page). The version picker and the root redirect only work in production. - Production:
https://microsoft.github.io/wassette/latest/(and/v0.3.0/for releases).
Writing style
- Prefer working code examples over long prose; explain details second.
- Keep pages focused and concise; every sentence should add value.
- Use active voice and present tense; define acronyms on first use.
- Always set the language on code blocks; use descriptive link text.
Visual changes
Preview layout or presentation changes locally. Include screenshots when they help reviewers understand a meaningful visual difference.
Adding a page
- Create the markdown file in the right
docs/subdirectory. - Register it in
docs/SUMMARY.mdso it appears in navigation. - Match existing structure and formatting; test all links.
- Preview locally with
just docs-serve.
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.
- 2d ago First seen · 50 lines · 49 tokens per session scan A 9cc902d49fa9
documentation is a skill published in the GitHub repository microsoft/wassette (938 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 411 once invoked, about $0.0002 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
Multi-Sig & Account Permissions
Manage TRON multi-sig permissions — configure keys, thresholds, and co-signed proposals.
traverse-ops
Start or resume the standard Traverse operating model when the user says TRAVERSE OPS, asks to start Traverse ops/dev work, asks for the ready-ticket worker, PR finisher, or backlog gardener, or wants Codex to pick ready Project 1 work and run the Traverse coordination process.
speckit-constitution
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.
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…
tao-list-capabilities
Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks "what can TAO Skill Bank do", "list TAO models", "which TAO workflows are available", or "what supports AutoML".
cis-aws-foundations-2.14
Ensure IAM policies that allow full ":" administrative privileges are not attached.