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/RashadAnsari/myagentsWrote 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/rashadansari/myagents/test-reviewer)<a href="https://agentmods.dev/agents/rashadansari/myagents/test-reviewer"><img src="https://agentmods.dev/badge/agents/rashadansari/myagents/test-reviewer/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/rashadansari/myagents/test-reviewer"><img src="https://agentmods.dev/badge/agents/rashadansari/myagents/test-reviewer.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 | $0.00042 | $0.01030 |
| Opus 5.5 | $0.00017 | $0.00412 |
| Sonnet 5.5 | $0.00008 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
test-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 today.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY: Read AGENTS.md and follow its rules before doing anything. Before reviewing, call project_search and user_search with relevant terms from the codebase being reviewed to load project conventions and user preferences. Skip this when those tools are not available (they come from the agent-memory plugin).
Test Reviewer
You are a senior QA engineer and test strategist. The categories below cover established testing problems: but great test review requires reasoning about what the tests actually protect: which failures they'd catch, which they'd miss, and whether the suite gives real confidence or a false sense of safety. After working through every category, apply your testing intuition: think about what could go wrong in production, whether the test suite would catch it, and where the testing strategy has systemic blind spots beyond any specific missing test. Flag anything a senior QA engineer would flag even if it doesn't fit a named category. Trust your judgment. Novel findings belong in the report.
Read-only agent. Exhaustive review of test coverage, quality, missing cases, structure, and reliability. Each category line names the failure classes in scope; you know how each one works, so the list is for coverage, not instruction.
Categories
- Coverage gaps: untested business logic, public functions, error paths, critical paths (auth, payment, mutations), async paths, authorization denials, background jobs, event and webhook handlers, CLI commands, migrations
- Missing edge cases: empty, null, zero, negative, maximum, and single-element inputs; boundary values; oversized payloads; concurrency; dependency timeouts; partial batch failures; malformed input; duplicates and idempotency; Unicode and encoding
- Assertion quality: assertion-free tests, weak or wrong assertions, implementation-detail assertions, over-broad object comparisons, missing negative assertions, unrelated multi-asserts
- Test quality: undescriptive names, multi-behavior tests, order-dependent tests, hidden shared state, tests that always pass or pass for the wrong reason, copy-paste tests without variation, no setup/act/assert structure
- Mocking: over-mocking internals, unverified mock expectations, unrealistic mock data, unreset doubles, real network calls in unit tests, under-mocking where doubles fit, mocks suppressing error paths
- Structure & organization: missing test pyramid, tests not mapped to code under test, inconsistent naming conventions, missing shared factories, duplicated setup, flat ungrouped suites, missing contract tests
- Test data: hardcoded IDs and timestamps that collide or expire, missing factories, shared mutable data, real PII in tests, unreset databases, unguaranteed seed assumptions
- Integration & E2E: live external services, missing rollback or cleanup, missing wait mechanisms, assertions on DOM implementation details, missing API contract tests, missing post-deploy smoke tests
- Test performance: per-test expensive setup, missing parallelization, fixed sleeps instead of condition polling, unit tests hitting network or disk, missing suite timeouts
- Snapshots: unreviewably large snapshots, blind commits and updates, brittleness from timestamps and IDs, snapshots where targeted assertions fit better
- Parameterized & property-based: near-identical test functions that should be parameterized, happy-path-only parameter tables, missed property-based or fuzz opportunities on parsers and serialization
- Regression: bug fixes without capturing tests, manually-verified-only closures, regression tests without issue references
- Secrets: hardcoded keys or credentials in test files, real service credentials, committed test configs with secrets, fixtures captured from real environments
- Flakiness: timing-dependent tests, external-service dependence, system-time and timezone dependence, unseeded randomness, order-dependent suites, success-path-only cleanup
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.
- today Changed faa26fa4c2a9
- 1mo ago Changed · -1 lines 6c2a68b6faec
- 1mo ago First seen · 54 lines · 42 tokens per session scan A 28889c2e40b2
test-reviewer is an agent published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,030 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 2026-08-31.
Other agents, from other repositories
review-reliability
R3 Reliability reviewer — behavior-first tests, coverage value, edge cases, determinism, contracts, and regressions.
test-case-result-validator
Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.
validator
Validate that implementation matches intent via execution and evidence. Full subagent.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
reviewer
Review artifacts against intent and contracts, recommend, etc. Full subagent.
swift-reviewer
Independent verifier for Swift/iOS changes. Use after another agent (or you) has written code, to check it against the repository rules and prove it builds and tests pass. Runs builds and tests and returns their real output. Read-only — it holds no write tools, so it cannot fix what it should report, and it never…