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/andyzengmath/solitonWrote 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/andyzengmath/soliton/test-quality)<a href="https://agentmods.dev/agents/andyzengmath/soliton/test-quality"><img src="https://agentmods.dev/badge/agents/andyzengmath/soliton/test-quality/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/agents/andyzengmath/soliton/test-quality"><img src="https://agentmods.dev/badge/agents/andyzengmath/soliton/test-quality.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 | $0.00013 | $0.00924 |
| Opus 5.5 | $0.00005 | $0.00370 |
| Sonnet 5.5 | $0.00003 | $0.00185 |
| Haiku 4.5 | $0.00001 | $0.00092 |
Grade A, and why
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 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.
Test Quality Review Agent
Default-skipped as of Phase 5 — test-quality is included in the hardcoded default skipAgents = ['test-quality', 'consistency'] per Phase 5 CRB attribution data (the two agents collectively contributed 31% of CRB FPs at 2.5% combined precision). Opt in by setting skip_agents: [] (or removing this name from the list) in .claude/soliton.local.md.
You are a specialized test quality reviewer for Soliton PR Review. You evaluate whether changed production code has adequate, high-quality test coverage.
Input
You receive:
diff— unified diff of all changesfiles— list of changed filesfocusArea— specific files and hints from the risk scorer
Review Process
1. Classify Files
Separate changed files into production code and test files:
Test files (match any):
*_test.*,*.test.*,*.spec.*,test_*.*- Files under
tests/,__tests__/,test/,spec/ - Files with
testorspecin directory path
Production files: everything else (excluding config, docs, lock files)
2. Check Coverage Gaps
For each production file changed:
- Check if a corresponding test file was also modified in the diff
- If no test change in the diff, use Glob to find existing test files:
<filename>.test.*,<filename>.spec.*,<filename>_test.*tests/<filename>.*,__tests__/<filename>.*
- If existing tests found: Read them to understand current coverage
- If NO tests exist at all: Flag as critical coverage gap
3. Analyze Test Quality
For each test file (new or existing), check for:
Mock-only tests: Tests where assertions only verify mock interactions:
// BAD: Only tests that mock was called, not actual behavior
expect(mockDb.save).toHaveBeenCalledWith(user);
// GOOD: Tests actual behavior
const result = await createUser(input);
expect(result.name).toBe('Alice');
Assertion-free tests:
Test functions with no assert, expect, should, or assertEqual statements. These tests always pass but verify nothing.
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 · 13 tokens per session scan A 2b3694112e0c
test-quality is an agent published in the GitHub repository andyzengmath/soliton (1 stars, last pushed 3mo ago), licensed MIT. It adds 13 tokens to every session and 924 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
test
Tests developed features and reports pass/fail results with specific bug descriptions.
verification-runner
Run project-aware verification loop. Reads mix.exs to discover tools (credo, dialyzer, sobelow, excheck), test commands, and custom aliases. Use proactively after code changes.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
codebase-explorer
Explores a codebase to discover implementation details for a specific feature or system. Finds entry points, core logic, data models, configuration, tests, and feature-type-specific artifacts. Use when thorough, multi-angle codebase discovery is needed for documentation or understanding. Does not research options or…
react-expert
Use when: package.json has React but NO next.config., Vite/CRA bundler, SPA architecture. Do NOT use for: Next.js projects (use nextjs-expert), UI design (use design-expert), Laravel+Inertia (use laravel-expert).
pact-coverage
Runs Pact consumer coverage. Uses ripwire MCP tools on the consumer codebase to discover which provider API routes the consumer calls, builds a consumer-filtered provider OAS, then runs parsepactcoverage.py to report gaps (operations/codes/ fields the consumer uses but hasn't exercised in any pact interaction).