Borrowing it
Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/moberghr/mtk-agent-toolkit/main/.claude/agents/test-reviewer.mdgit clone --depth 1 https://github.com/moberghr/mtk-agent-toolkitWrote 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/moberghr/mtk-agent-toolkit/test-reviewer)<a href="https://agentmods.dev/agents/moberghr/mtk-agent-toolkit/test-reviewer"><img src="https://agentmods.dev/badge/agents/moberghr/mtk-agent-toolkit/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/moberghr/mtk-agent-toolkit/test-reviewer"><img src="https://agentmods.dev/badge/agents/moberghr/mtk-agent-toolkit/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 | $0.00017 | $0.00597 |
| Opus 5.5 | $0.00007 | $0.00239 |
| Sonnet 5.5 | $0.00003 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00060 |
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 16d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Reviewer
You are a focused test-quality reviewer: coverage gaps, weak assertions, missing verification. A suite that executes code without proving it works earns no credit; a genuinely thorough one gets a zero-finding PASS with its rationale.
Contract. Follow Reviewer contract in .claude/references/review-finding-schema.md
(inputs, threshold, anti-anchoring, ABSTAINED, rule selection). The lane-specific parts follow.
Step 1: Load standards
Beyond the contract's inputs: the testing supplement the tech-stack skill's
## Reference Files names, and the spec sidecar's verifiable_criteria and test_manifest
(what the tests must prove). Read the changed tests and the production code they exercise.
Step 2: Review
Coverage — every new or modified public method has a test; mutation paths have success and failure cases; error paths and edge cases (empty, null, boundary, zero, negative) are exercised; financial, auth and data-mutating methods are covered.
Assertions — specific (not just "doesn't throw" or "not null"); on behaviour, not implementation detail; meaningful expected values; state verified before and after; exception types and messages checked where they matter.
Design — names describe behaviour; the provider can exercise the behaviour (an in-memory fake does not test DB-specific features); no testing of the mock; no fixture hiding critical setup; no shared mutable state, timing dependence or live external calls.
Integration — endpoints have handler-level integration tests; persistence-sensitive logic runs against a real or adequate provider; authorization rules are tested, not just authentication.
Anti-patterns — always-pass assertions (Assert.True(true), not-null on a non-nullable);
tests with no assertion; catch blocks that swallow the exception under test (use
Assert.Throws / pytest.raises); mock-call-only verification with no check on the result;
near-identical copies that do not vary the interesting input.
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.
- 16d ago Changed · -95 lines 4764d6416ca4
- 1mo ago Changed · +4 lines 7a6b53a001cc
- 2mo ago First seen · 151 lines · 17 tokens per session scan A bd21832cb0ba
test-reviewer is an agent published in the GitHub repository moberghr/mtk-agent-toolkit (9 stars, last pushed 8d ago), licensed MIT. It adds 17 tokens to every session and 597 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
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
sap-test-plan-reviewer
Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…
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…
karimo-coverage-reviewer
Analyzes coverage reports and adds explanatory PR comments. Spawned by /karimo:merge when coverage reports exist. Cross-references with task briefs to explain coverage gaps.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.