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-runnergit 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-runner)<a href="https://agentmods.dev/skills/microsoft/waza/waza-runner"><img src="https://agentmods.dev/badge/skills/microsoft/waza/waza-runner/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-runner"><img src="https://agentmods.dev/badge/skills/microsoft/waza/waza-runner.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 | $0.00093 | $0.00626 |
| Opus 5.5 | $0.00037 | $0.00250 |
| Sonnet 5.5 | $0.00019 | $0.00125 |
| Haiku 4.5 | $0.00009 | $0.00063 |
Grade A, and why
waza-runner 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 2mo 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
Skill Eval Runner
Evaluate Agent Skills like you evaluate AI Agents
This skill runs evaluations on other skills to measure their effectiveness using the same patterns that power AI agent evaluations.
When to Use
- Running quality evaluations on a skill
- Testing if a skill triggers on correct prompts
- Measuring skill behavior quality
- Generating eval reports for CI/CD
Commands
Run Evals
Run evals on <skill-name>
Initialize Eval Suite
Create evals for <skill-name>
Generate Report
Generate eval report for <skill-name>
Workflow
- Check for Eval Suite: Look for
eval.yamlin the skill directory - Load Tasks: Parse task definitions from
tasks/*.yaml - Execute: Run each task through the configured graders
- Report: Output results in JSON or Markdown format
Metrics Measured
| Metric | Description | Default Threshold |
|---|---|---|
| Task Completion | Did the skill accomplish the goal? | 80% |
| Trigger Accuracy | Was skill invoked on correct prompts? | 90% |
| Behavior Quality | Tool calls, efficiency, reasoning | 70% |
Grader Types
- Code Graders: Deterministic assertions, regex matching
- LLM Graders: Model-as-judge with configurable rubrics
- Human Graders: Manual review workflow
Example Usage
Running Evals
# From CLI
waza run ./my-skill/eval.yaml
# Output to file
waza run ./my-skill/eval.yaml -o results.json
Interpreting Results
{
"summary": {
"pass_rate": 0.85,
"composite_score": 0.82
},
"metrics": {
"task_completion": { "score": 0.9, "passed": true },
"trigger_accuracy": { "score": 0.95, "passed": true }
}
}
References
- Eval Specification - Full eval.yaml schema
- Writing Tasks - Task definition guide
- Grader Reference - Available graders
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.
- 2mo ago First seen · 96 lines · 93 tokens per session scan A c05f979bbedf
waza-runner is a skill published in the GitHub repository microsoft/waza (1,505 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 626 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.
waza-runner compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| waza-runnermicrosoft/waza | Skill | 1.5k | today | MIT | A | 93 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |