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/nweii/agent-stuff/software-test-qualitynpx skills add nweii/agent-stuff --skill software-test-qualitygit clone --depth 1 https://github.com/nweii/agent-stuffWhat 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 | $0.00054 | $0.00674 |
| Opus 5 | $0.00027 | $0.00337 |
| Sonnet 5 | $0.00011 | $0.00135 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
software-test-quality 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 yesterday.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software test quality
Choose the branch that matches the task:
- Existing tests or suite → Review test quality
- Proposed behavior or risk → Choose the test level
Use the tdd skill instead when building a feature or fixing a bug test-first.
Review test quality
Review tests through their public seam: the interface where callers observe behavior. A test should fail when that behavior breaks and survive internal refactors that preserve it.
Apply the Desiderata as design lenses, not a checklist:
- Isolated: results do not depend on execution order or shared mutable state.
- Composable: tests combine without hidden coupling or cascading setup.
- Deterministic: unchanged code and inputs produce the same result.
- Fast: tests are quick enough to run while working.
- Writable: creation cost is proportionate to the behavior protected.
- Readable: motivation and expected behavior are clear.
- Behavioral: the result changes when the behavior changes.
- Structure-insensitive: internal refactors do not change the result.
- Automated: tests run without manual intervention.
- Specific: failures make the likely cause clear.
- Predictive: passing gives justified confidence in production behavior.
- Inspiring: the suite increases confidence instead of creating noise, flakes, or avoidance.
Then inspect the failure modes that a structural review can miss:
- Weak assertions that prove existence instead of behavior.
- Fixtures that do not represent production inputs.
- Risky paths that the suite never exercises.
- Names that disagree with the behavior asserted.
- Mocks that encode assumptions the real collaborator does not satisfy.
- Tautological expectations derived through the same logic as the implementation.
When a test's sensitivity is uncertain and a controlled check is cheap, break the protected behavior minimally and confirm that the test fails for the expected reason. Restore the behavior before continuing.
Report every material weakness, the behavior or risk it affects, and any intentional Desiderata tradeoff. The review is complete when every in-scope test has been assessed and each finding identifies concrete evidence.
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.
- yesterday First seen · 61 lines · 54 tokens per session scan A 9422a37b11a0
software-test-quality is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 13d ago), licensed MIT. It adds 54 tokens to every session and 674 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.