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.
Borrowing it
Nothing to install: this file belongs to microsoft/waza. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/waza/main/.github/skills/test-discipline/SKILL.mdgit 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/test-discipline)<a href="https://agentmods.dev/skills/microsoft/waza/test-discipline"><img src="https://agentmods.dev/badge/skills/microsoft/waza/test-discipline/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/test-discipline"><img src="https://agentmods.dev/badge/skills/microsoft/waza/test-discipline.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.00346 |
| Opus 5.5 | $0.00007 | $0.00138 |
| Sonnet 5.5 | $0.00003 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
test-discipline 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 5d 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.
This is a copy
100% identical to test-discipline — 48 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Context
Use this skill whenever a change affects an API, public interface, workflow contract, generated artifact, or user-observable behavior. A passing status-only test is not evidence that the intended artifact or contract is correct.
Patterns
- Update tests in the same change as an API, signature, export, or public-interface change.
- Make assertions name and inspect the offending artifact, output, or configuration field—not just an exit code or broad success status.
- Mutation-test critical gates by changing the real source or emitted artifact and proving the assertion turns red.
- Exercise every caller path for a changed parser, normalizer, or helper; isolated unit coverage can miss the integration path that invokes it differently.
- Reproduce working-tree-only failures locally when the contract depends on index, filesystem, line-ending, or generated-output state.
- Keep expected inventory arrays synchronized with the files they enumerate.
Examples
A workflow-compilation test mutates the source workflow, compiles it, and inspects the emitted safe-output contract. A repair-script test constructs the actual index/blob/worktree state that the repair routine must handle instead of a simplified fixture.
Anti-Patterns
- Calling a test sufficient because it observes only a successful process exit
- Mutating a hand-built fixture instead of the source or artifact protected by the gate
- Testing a helper while omitting production callers
- Treating a local checkout defect as something CI alone can validate
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.
- 5d ago Changed · +2 lines · +5 tokens per session d84983f8e881
- 1mo ago First seen · 38 lines · 12 tokens per session scan A 6efe81cabcd2
test-discipline is a skill published in the GitHub repository microsoft/waza (1,424 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 346 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to test-discipline, differing in 48 lines, and is treated as a copy.
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.
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.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.