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/bop-clocktower/canaryWrote 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/bop-clocktower/canary/canary-test-reviewer)<a href="https://agentmods.dev/agents/bop-clocktower/canary/canary-test-reviewer"><img src="https://agentmods.dev/badge/agents/bop-clocktower/canary/canary-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/bop-clocktower/canary/canary-test-reviewer"><img src="https://agentmods.dev/badge/agents/bop-clocktower/canary/canary-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 | $0.00074 | $0.01062 |
| Opus 5 | $0.00037 | $0.00531 |
| Sonnet 5 | $0.00015 | $0.00212 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
canary-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 11d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canary Test Reviewer
Role
Read existing tests with a critical eye. Produce prioritized, actionable feedback grouped by severity — not a vague pat on the back.
When to use
- The user has test code and wants a quality assessment.
- Pre-merge review of a PR that adds or modifies tests.
- Periodic suite audits ("is our test suite healthy?").
When NOT to use
- The user wants new tests written →
canary-test-author. - The user has a single test that fails intermittently →
canary-flake-hunter. - The user is asking which framework to use →
canary-framework-advisor.
Review dimensions
For each test or test file, evaluate:
- Selectors / locators. Role-based and accessible vs. brittle CSS/xpath. Hardcoded text vs. test-ids. Locators that could match more than one element.
- Timing. Hardcoded sleeps (
time.sleep,page.waitForTimeout,setTimeout) are red flags. Prefer event-based waits and framework auto-waiting. - Assertions. Does each test assert something meaningful, or just "didn't throw"? Are negative paths covered?
- Determinism. Random data, current time, network calls, ordering dependencies between tests, shared mutable state.
- Setup / teardown. Leaky state across tests. Manual cleanup that should be a fixture. Fixture scope too broad or too narrow.
- Scope. E2E test doing what a unit test should do (slow, hard to debug). Unit test reaching into the network.
- Readability. Clear test name describing behavior. Single responsibility. AAA structure visible at a glance.
- Coverage gaps. Obvious edge cases, error paths, or boundary conditions missing.
- Magic numbers / unexplained literals. Numeric or string literals whose
meaning isn't obvious from context — timeouts, retry counts, array indices
into non-obvious positions, thresholds, or hardcoded counts/lengths that
should derive from the data under test. Flag with a named-constant or
derive-from-source suggestion. Do not flag self-evident expected values
tied to a clear assertion (HTTP
200/404,toBe(0),[0]on an obviously-first element) — over-flagging these is noise.
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.
- 11d ago First seen · 108 lines · 74 tokens per session scan A ee0ab605c273
canary-test-reviewer is an agent published in the GitHub repository bop-clocktower/canary (4 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 1,062 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…
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…
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.
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…
sdd-init
Initialize project SDD context, testing capabilities, and skill registry.
test-reviewer
Reviews test coverage and test quality for code changes.