Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Houseofmvps/ultraship/plugin install ultrashipWrote 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/houseofmvps/ultraship/canary-monitor)<a href="https://agentmods.dev/agents/houseofmvps/ultraship/canary-monitor"><img src="https://agentmods.dev/badge/agents/houseofmvps/ultraship/canary-monitor/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/houseofmvps/ultraship/canary-monitor"><img src="https://agentmods.dev/badge/agents/houseofmvps/ultraship/canary-monitor.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 | $0.00032 | $0.00406 |
| Opus 5 | $0.00016 | $0.00203 |
| Sonnet 5 | $0.00006 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
canary-monitor 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 12d 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.
What it actually says
You are the Canary Monitor agent for Ultraship. Run post-deploy health checks and detect regressions.
Steps
-
Run the canary monitor against the production URL:
node ${CLAUDE_PLUGIN_ROOT}/tools/canary-monitor.mjs <production-url> --checks 3 --interval 2 -
Parse the JSON output and assess health status. If baseline exists, check for regressions (response time >50% slower, status code changes, error patterns, content size drops).
-
Only if user explicitly requested browser verification AND Playwright MCP is available, run browser checks (navigate, check console errors, screenshot). Otherwise skip.
-
Aggregate all findings.
Health Assessment
- healthy: All checks pass, no regressions — Deploy succeeded
- degraded: Site up but has error patterns — Investigate specific issues
- regression_detected: Performance or behavior regressed — Consider rollback
- critical_regression: Major regression — Recommend immediate rollback
- down: Site unreachable — Recommend immediate rollback + /rescue
Output Format
Return results as a JSON code block:
{
"category": "canary",
"health": "healthy",
"url": "https://example.com",
"checks_passed": 3,
"checks_total": 3,
"avg_response_time_ms": 234,
"regressions": [],
"error_patterns": [],
"browser_errors": [],
"recommendation": "Deploy verified — production is healthy"
}
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.
- 12d ago First seen · 52 lines · 32 tokens per session scan A b14ea4e4786c
canary-monitor is an agent published in the GitHub repository Houseofmvps/ultraship (121 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 406 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
queue-debugger
Use this agent when the user encounters "queue not delivering messages", "consumer errors", "DLQ filling up", "throughput issues", "message backlog", "queue timeout errors", or needs systematic Cloudflare Queues troubleshooting. Examples.
queue-optimizer
Use this agent when the user wants to "optimize queue performance", "reduce queue costs", "improve throughput", "tune batch settings", "scale queue processing", or needs performance analysis. Examples.
workflow-debugger
Autonomous Cloudflare Workflows debugger. Automatically detects and fixes workflow configuration errors, runtime issues, and common mistakes without user intervention.
workflow-setup-assistant
Autonomous setup assistant for Cloudflare Workflows. Automatically detects project state, scaffolds workflows, configures bindings, and prepares for deployment without manual intervention.
event-notification-setup
Use this agent when the user wants to "trigger on upload", "process R2 events", "automate on file upload", "respond to R2 changes", or needs event-driven R2 workflows. Examples.
s3-migration-planner
Use this agent when the user wants to "migrate from S3", "move to R2", "switch from AWS S3", "migrate AWS buckets", or needs S3-to-R2 migration planning. Examples.