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 skills add uptimerobot/ai --skill create-keyword-monitorgit clone --depth 1 https://github.com/uptimerobot/aiWrote 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/skills/uptimerobot/ai/create-keyword-monitor)<a href="https://agentmods.dev/skills/uptimerobot/ai/create-keyword-monitor"><img src="https://agentmods.dev/badge/skills/uptimerobot/ai/create-keyword-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/skills/uptimerobot/ai/create-keyword-monitor"><img src="https://agentmods.dev/badge/skills/uptimerobot/ai/create-keyword-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00733 |
| Opus 5 | $0.00016 | $0.00367 |
| Sonnet 5 | $0.00006 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
create-keyword-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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a KEYWORD monitor
Preflight — read first. If you cannot see any
uptimerobot:*MCP tools in your tool list, invoke theuptimerobot:setupskill before doing anything else. Do not tell the user the MCP is misconfigured —setup's Step 0 detects the common case (server connected, tools loaded after session start) and resolves it without re-keying.
Use when the user cares not just that an endpoint returns a 200, but that a specific string is present (login page has "Sign in") or absent (homepage is not showing "502 Bad Gateway"). For structured JSON assertions, prefer create-api-monitor instead.
Tool: create-monitor
Required params: friendlyName, type: "KEYWORD", url (full URL), keywordValue, keywordType.
Minimal call
{
"friendlyName": "Login page shows Sign in",
"type": "KEYWORD",
"url": "https://app.example.com/login",
"keywordValue": "Sign in",
"keywordType": "ALERT_NOT_EXISTS"
}
keywordType:
ALERT_NOT_EXISTS— alert when the keyword disappears (expected content missing → down).ALERT_EXISTS— alert when the keyword appears (error string present → down).
Common optional params
All HTTP-monitor params are supported: httpMethodType, authType, httpUsername, httpPassword, followRedirections, checkSSLErrors, timeout, interval, sslExpirationReminder, domainExpirationReminder, responseTimeThreshold, assignedAlertContacts, tagNames, maintenanceWindowsIds.
KEYWORD-specific:
keywordCaseType—0for case-sensitive (default),1for case-insensitive.
Example: alert when a 500 message appears
{
"friendlyName": "Homepage not erroring",
"type": "KEYWORD",
"url": "https://www.example.com/",
"keywordValue": "Internal Server Error",
"keywordType": "ALERT_EXISTS",
"keywordCaseType": 1,
"interval": 60,
"assignedAlertContacts": [
{ "alertContactId": "10", "threshold": 0, "recurrence": 0 }
]
}
Common mistakes
- Leaving off
keywordType— it is required. - Using an HTTP monitor when the user said "alert me if the page shows X" — use KEYWORD.
- Case-sensitivity confusion. Default is case-sensitive; pass
keywordCaseType: 1for insensitive. keywordValuelonger than 500 chars is rejected.- HEAD requests cannot match body content. If
httpMethodTypeisHEAD, the keyword check will not work as expected.
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 · 74 lines · 32 tokens per session scan A 8ca516577e82
create-keyword-monitor is a skill published in the GitHub repository uptimerobot/ai (24 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 733 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 skills, from other repositories
monitoring
Use when setting up uptime and health monitoring, alerts, or on-call basics for a service already in production, so you learn it is down before customers do — health and readiness probes, alerting on SLO error-budget burn rather than raw counts, curing alert fatigue, on-call rotation with escalation, and a status…
create-test-run
Create a Kobiton test run from a test case or suite, then offer to monitor it. When the user gives only partial details (or just a test case id), fill the rest with sensible defaults that match the createTestRun schema, show a summary of what will run, and ask to proceed or customize before creating. After the run is…
gatus-health
Automated health monitoring with Gatus.
BytesAgain Monitor — Advanced Uptime & Performance Auditor
A website checker that measures whether sites respond, which HTTP status codes they return, and how long they take to respond. HTTP status codes are server replies such as 200 for success or 404 for a missing page.
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.