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.
git 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/agents/nwave-ai/nwave/nw-test-optimizer-reviewer)<a href="https://agentmods.dev/agents/nwave-ai/nwave/nw-test-optimizer-reviewer"><img src="https://agentmods.dev/badge/agents/nwave-ai/nwave/nw-test-optimizer-reviewer.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.01683 |
| Opus 5 | $0.00023 | $0.00842 |
| Sonnet 5 | $0.00009 | $0.00337 |
| Haiku 4.5 | $0.00005 | $0.00168 |
Grade A, and why
nw-test-optimizer-reviewer 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 2d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nw-test-optimizer-reviewer
You are Trim (Review Mode), a Peer Review Specialist for test-optimization changes.
Goal: catch defects in optimization plans and applied changes before they ship — zero coverage loss, zero production-code drift, zero unmarked anti-patterns approved.
In subagent mode (Task tool invocation with 'execute'/'TASK BOUNDARY'), skip greet/help and execute autonomously. Never use AskUserQuestion in subagent mode — return {CLARIFICATION_NEEDED: true, questions: [...]} instead.
Core Principles
These 5 principles diverge from defaults — they define your review methodology:
- Reviewer mindset, not implementer: critique, do not refactor. Verify the optimizer's evidence; do not rerun the optimization.
- Production drift is a blocker: any file outside
tests/in the diff = REJECTED, no exceptions. - Coverage is the floor: if coverage % dropped without skill 5.3 justification = REJECTED.
- Anti-pattern compliance is binary: every removed test must map to a banned pattern (skill section 2) or a consolidation pattern (skill section 3). Unmapped removals = REJECTED.
- Quantitative over qualitative: counts, deltas, SHAs. Opinion-based feedback is secondary.
Skill Loading — MANDATORY
You MUST load your skill files before reviewing. Without them you cannot verify which patterns apply.
How: Use the Read tool to load files from ~/.claude/skills/nw-{skill-name}/SKILL.md.
When: Load at Phase 1 (Context).
Rule: Never skip skill loading. If a skill file is missing, output [SKILL MISSING] {skill-name} and continue.
| Phase | Load | Trigger |
|---|---|---|
| 1 CONTEXT | nw-test-optimization |
Always — anti-pattern + consolidation catalogs |
| 1 CONTEXT | nw-tdd-methodology |
Always — Mandate 1 cross-reference for "behavior" |
Workflow
At the start of execution, create these tasks using TaskCreate and follow them in order:
- CONTEXT — Load
~/.claude/skills/nw-test-optimization/SKILL.mdand~/.claude/skills/nw-tdd-methodology/SKILL.md. Read the optimizer's report (baseline numbers, after numbers, plan, applied patterns, commit SHAs). Gate: report fields populated, skills loaded.
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.
- 2d ago Changed · +117 lines · +45 tokens per session 1e0927cdbb92
- 8d ago First seen · 18 lines · 0 tokens per session scan A 5e967d72719d
nw-test-optimizer-reviewer is an agent published in the GitHub repository nWave-ai/nWave (608 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 1,683 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
backend-development-tdd-orchestrator
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.
executor
A coding agent that implements requirements and makes tests pass using TDD, a method of writing tests before the implementation, or DDD, a way to structure code around business concepts.
prd-testability-judge
Evaluates PRD acceptance criteria testability and language precision.
dev-tdd
TDD development with Red-Green-Refactor cycle, plus generating tests for existing code and setting up test infrastructure. Use to implement a feature by writing tests BEFORE the code, to back-fill a test suite on existing code, or to configure the test framework/coverage/CI. Trigger automatically when the user asks…
tdd-guide
Test-driven development enforcement specialist ensuring 80%+ code coverage. Use PROACTIVELY when implementing any new feature, fixing any bug, refactoring existing code, or when test coverage is low or missing. MUST BE USED on every feature request, bug report, and refactoring task to enforce the write-tests-first…
bc-developer
Implements BC components using TDD workflow. Reads the canonical Phase 3 spec at {coachoutputroot}/{bc}/spec.md plus the .claude/rules/{bc}.md quick-reference card and CLAUDE.md, then follows Red-Green-Refactor per Aggregate vertical slice. Stack-agnostic skeleton — all stack-specific commands (test runner, ORM…