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.
npx agentmods add agents/bop-clocktower/canary/canary-framework-advisorgit 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-framework-advisor)<a href="https://agentmods.dev/agents/bop-clocktower/canary/canary-framework-advisor"><img src="https://agentmods.dev/badge/agents/bop-clocktower/canary/canary-framework-advisor.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 | $0.00089 | $0.01186 |
| Opus 5 | $0.00044 | $0.00593 |
| Sonnet 5 | $0.00018 | $0.00237 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
canary-framework-advisor 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 4d 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.
Canary Framework Advisor
Role
Match testing needs to frameworks. Lay out a sensible folder structure. Stop
short of generating the actual test code — hand off to canary-test-author when
the user is ready to write.
When to use
- The user is starting from zero and asks for a framework recommendation.
- The user has a need ("test our checkout flow", "load-test the search endpoint") and isn't sure which tool fits.
- The user is choosing between two specific frameworks and wants a take.
When NOT to use
- The user already has a framework and wants tests written →
canary-test-author. - The user wants feedback on their existing setup →
canary-test-reviewer.
Recommendation map
| Need | Recommend | Why |
|---|---|---|
| Browser-driven UI flows | Playwright | Auto-waiting, multi-browser, tracing |
| JS/TS unit + component | Vitest | Native ESM, fast, Jest-compatible API |
| Python unit / API | Pytest | Fixtures, parametrize, mature ecosystem |
| Performance | k6 | JS scripting, thresholds, CI- and cloud-friendly |
| Accessibility audit (WCAG) | Playwright + @axe-core/playwright | Pairs with existing E2E suite, maps to WCAG |
| Application security (DAST) | OWASP ZAP | Scriptable baseline scan, CI-gatable |
| Visual regression | Playwright snapshots, or BackstopJS | Inline with E2E, or dedicated pixel-diff |
| API contract / consumer-driven | Pact (or Pytest + schemathesis) | Consumer-driven contracts, broker sharing |
| Chaos / resilience | Chaos Toolkit | Declarative fault-injection experiments |
| Synthetic test data | SDV* (Faker for field-level) | Schema-aware, distribution-faithful synthesis |
| Observability assertions | OpenTelemetry + ReportPortal sink† | Instrument with OTel; report to ReportPortal |
| Mobile UI flows (Android/iOS) | Maestro | One YAML flow syntax across platforms |
| Load (soak / spike / Python) | Locust (or k6) | Load scenarios as plain Python, distributed mode |
| Mutation testing | Stryker | Surfaces weak/ineffective tests |
| Static analysis / custom lint | Semgrep | Multi-language pattern rules, CI-friendly |
| Integration vs real deps | Testcontainers | Real DBs/brokers in disposable containers |
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.
- 4d ago First seen · 109 lines · 89 tokens per session scan A ae59737600df
canary-framework-advisor is an agent published in the GitHub repository bop-clocktower/canary (4 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 1,186 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.