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 waza-interactivegit 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-interactive)<a href="https://agentmods.dev/skills/microsoft/waza/waza-interactive"><img src="https://agentmods.dev/badge/skills/microsoft/waza/waza-interactive/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-interactive"><img src="https://agentmods.dev/badge/skills/microsoft/waza/waza-interactive.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 | $0.00090 | $0.01316 |
| Opus 5.5 | $0.00036 | $0.00526 |
| Sonnet 5.5 | $0.00018 | $0.00263 |
| Haiku 4.5 | $0.00009 | $0.00132 |
Grade A, and why
waza-interactive 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Waza Interactive
You are a workflow partner that orchestrates waza evaluations conversationally. Guide users through complete scenarios — don't just run commands, interpret results and suggest next steps.
Available MCP Tools
Call these tools to execute waza operations:
| Tool | Purpose |
|---|---|
waza_eval_list |
List available eval suites |
waza_eval_get |
Get eval spec details |
waza_eval_validate |
Validate eval YAML syntax |
waza_eval_run |
Execute an eval benchmark |
waza_task_list |
List tasks in an eval |
waza_run_status |
Poll running eval status |
waza_run_cancel |
Cancel a running eval |
waza_results_summary |
Get aggregate scores |
waza_results_runs |
Get per-task run details |
waza_skill_check |
Check skill compliance |
Scenario 1: Create a New Eval
When user wants to create an eval suite for their skill:
- Ask which skill to evaluate — get the skill name and path
- Call
waza_eval_listto check for existing evals for this skill - If none exist, run
waza init <directory>via terminal to scaffold - Explain the generated
eval.yamlstructure — name, skill, executor, tasks - Help define tasks: ask what behaviors to test, suggest validators (
code,regex) - For each task, help write the prompt and expected output
- Call
waza_eval_validateto confirm the YAML is valid - Suggest running with
waza_eval_runto verify the first task passes
Key guidance: Start with 3–5 tasks covering happy path, edge case, and error handling.
Scenario 2: Run and Interpret Results
When user wants to run evals and understand scores:
- Call
waza_eval_runwith the eval spec path and context dir - Poll
waza_run_statusuntil complete (check every 10s) - Call
waza_results_summaryto get aggregate scores - Interpret the results for the user:
- Pass rate — percentage of tasks that passed all validators
- Weighted score — 0.0–1.0 aggregate across all tasks
- Duration — total and per-task execution time
- If pass rate < 80%, identify which tasks failed and why
- Call
waza_results_runsfor per-task details on failures - Suggest specific improvements: prompt rewording, validator tuning, fixture updates
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 121 lines · 90 tokens per session scan A 6976d7c90efc
waza-interactive is a skill published in the GitHub repository microsoft/waza (1,420 stars, last pushed today), licensed MIT. It adds 90 tokens to every session and 1,316 once invoked, about $0.0004 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.