microsoft/waza is a Go command-line tool for building and evaluating AI agent skills through test suites, benchmarks, and model comparisons. It is for developers who need to measure and improve how reliably agent skills work. The catalogue entries are Waza's own skills, instructions, agent, and MCP integration.
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 skills add microsoft/waza --skill wazagit clone --depth 1 https://github.com/microsoft/wazaWrote 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/waza/waza)<a href="https://agentmods.dev/skills/microsoft/waza/waza"><img src="https://agentmods.dev/badge/skills/microsoft/waza/waza/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/microsoft/waza/waza"><img src="https://agentmods.dev/badge/skills/microsoft/waza/waza.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00145 | $0.01804 |
| Opus 5.5 | $0.00058 | $0.00722 |
| Sonnet 5.5 | $0.00029 | $0.00361 |
| Haiku 4.5 | $0.00015 | $0.00180 |
Grade A, and why
waza 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 1mo 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Waza
"The way of technique — measure, refine, master."
A Go CLI tool for evaluating AI agent skills through structured benchmarks. Define test cases in YAML, run them against agent engines, and validate results with pluggable scoring validators.
Help
When user says "waza help" or asks how to use waza:
╔══════════════════════════════════════════════════════════════════╗
║ WAZA - CLI Tool for Evaluating Agent Skills ║
╠══════════════════════════════════════════════════════════════════╣
║ ║
║ COMMANDS: ║
║ waza run <eval.yaml> # Run an evaluation benchmark ║
║ waza init [directory] # Initialize a new eval suite ║
║ waza generate <SKILL.md> # Generate eval from SKILL.md ║
║ waza compare <r1> <r2> ... # Compare result files ║
║ waza dev [skill-path] # Improve SKILL.md compliance ║
║ ║
║ RUN FLAGS: ║
║ --context-dir, -c Fixtures directory (default: ./fixtures) ║
║ --output, -o Save results JSON to file ║
║ --verbose, -v Verbose output ║
║ --task, -t Filter tasks by name (repeatable) ║
║ --parallel, -p Run tasks in parallel ║
║ --workers, -w Number of parallel workers ║
║ --transcript-dir Save per-task transcripts ║
║ ║
║ COMPARE FLAGS: ║
║ --format, -f Output format: table or json ║
║ ║
║ GENERATE FLAGS: ║
║ --output-dir, -d Output directory for generated files ║
║ ║
║ DEV FLAGS: ║
║ --target Adherence level: low|medium|high ║
║ --max-iterations Max improvement iterations (default: 5) ║
║ --auto Auto-apply without prompting ║
║ ║
║ WORKFLOW: ║
║ 1. waza init my-eval # Scaffold eval suite ║
║ 2. Edit eval.yaml + tasks # Define test cases ║
║ 3. waza run eval.yaml -v # Execute benchmark ║
║ 4. waza compare a.json b.json # Cross-model comparison ║
║ ║
║ FIXTURE ISOLATION: ║
║ Each task gets a fresh temp workspace with fixtures copied ║
║ in. Original fixtures are never modified. ║
║ ║
╚══════════════════════════════════════════════════════════════════╝
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.
- 1mo ago First seen · 215 lines · 145 tokens per session scan A e7ef60562bbf
waza is a skill published in the GitHub repository microsoft/waza (1,420 stars, last pushed today), licensed MIT. It adds 145 tokens to every session and 1,804 once invoked, about $0.0006 per session on Opus 5.5. 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.