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 nWave-ai/nWave --skill nw-optimize-testsgit clone --depth 1 https://github.com/nWave-ai/nWaveWrote 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/nwave-ai/nwave/nw-optimize-tests)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-optimize-tests"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-optimize-tests/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/nwave-ai/nwave/nw-optimize-tests"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-optimize-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 21 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00048 | $0.00939 |
| Opus 5.5 | $0.00019 | $0.00376 |
| Sonnet 5.5 | $0.00010 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
nw-optimize-tests 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NW-OPTIMIZE-TESTS: Test Suite Optimization
Wave: CROSS_WAVE Agent: Trim (nw-test-optimizer) Reviewer: Trim Review (nw-test-optimizer-reviewer)
Overview
Dispatches Trim to inventory a test scope, detect duplication and anti-patterns, propose a consolidation plan, and apply it after explicit approval. Coverage is preserved; production code is never modified. Use after a feature lands, when a suite feels slow or noisy, on weekly audit, or whenever overtesting is suspected.
Context Files Required
- The scope path (passed as argument or auto-detected)
~/.claude/skills/nw-test-optimization/SKILL.md— methodology (loaded by agent)
Timing Baseline
Trim compares against the wall-clock figures recorded in the execution-log.json.
Agent Invocation
@nw-test-optimizer
Execute test optimization for {scope}.
Configuration:
- scope: <path | feature-id | empty for full unit suite>
- approval_required: true # always; gate is non-negotiable
- mutation_validation: false # set true for critical scopes (financial, safety, infra)
- reviewer_chain: false # set true to dispatch nw-test-optimizer-reviewer after apply
Approval Gate
Trim presents the plan as a markdown table after Phase 3 (PLAN). The orchestrator (or invoking user) responds with one of:
- APPROVE — full plan, all rows
- APPROVE WITH EXCLUSIONS — list row IDs to skip
- REJECT — abort, return findings as deferred report
- REPLAN — provide new scope or constraint
No changes are applied without one of these responses. Trim never assumes approval.
Reviewer Chain (optional)
If reviewer_chain: true:
@nw-test-optimizer-reviewer
Validate the optimization output for {scope}.
Reviewer hard-blocks on: production drift, coverage drop without justification, unmapped removal, missing approval gate evidence.
Success Criteria
- Baseline numbers recorded (passed count, coverage %)
- Plan presented before any change
- Explicit approval received
- Production files in diff: 0
- Coverage % preserved (or drop documented per skill 5.3)
- Atomic commits per consolidation pattern
- Final report with deltas and SHAs
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 · 109 lines · 48 tokens per session scan A 2863cbea25ee
nw-optimize-tests is a skill published in the GitHub repository nWave-ai/nWave (620 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 939 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
java-testing-junit-mockito
Use when writing tests for Java (Quarkus or Spring) code - JUnit Jupiter structure, Mockito for collaborators, test slices, Testcontainers, and framework-native integration tests, test-first.
test-writing
Writes meaningful tests that actually catch bugs.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
temporal-python-testing
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.