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 skills/uptimerobot/ai/bulk-pausenpx skills add uptimerobot/ai --skill bulk-pausegit clone --depth 1 https://github.com/uptimerobot/aiWhat 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 | $0.00033 | $0.01138 |
| Opus 5 | $0.00016 | $0.00569 |
| Sonnet 5 | $0.00007 | $0.00228 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
bulk-pause 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 2d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bulk pause / resume
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.
There is no single "pause all" tool. The workflow is: enumerate the target monitors with list-monitors, then call update-monitor-status for each.
Use this when the user says "pause everything", "silence alerts during deploy", "mute the api monitors", or "bring them all back online".
Prefer
maintenance-windowsfor scheduled downtime. Maintenance windows suppress alerts without changing monitor state and don't count against your plan's active-monitor cap on resume. Only bulk-pause when the user explicitly wants the monitors stopped, or when a maintenance window isn't suitable (ad-hoc, very short, or already in the middle of a deploy).
Step 1 — List the target monitors
Filter as tightly as possible to avoid pausing unrelated monitors.
By tag
{ "search": "", "filter": [], "limit": 50 }
list-monitors doesn't support tag-based server-side filtering. Pull the page, then filter client-side on tagNames before touching anything.
By name or URL
{ "search": "api.example.com", "limit": 50 }
By state (only currently-running monitors)
{ "filter": ["UP", "DOWN", "NOT_STARTED"], "limit": 50 }
Excluding PAUSED avoids re-pausing already-paused monitors.
Follow the instructions field for pagination until hasMore: false. Do not start pausing until the full list is collected — partial pauses mid-paginate are easy to miss on resume.
Step 2 — Confirm with the user
Before any write, echo the list back:
Pausing 14 monitors tagged `deploy-api`:
- Prod API (HTTP, UP)
- Prod API /healthz (KEYWORD, UP)
- ...
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.
- 2d ago First seen · 104 lines · 33 tokens per session scan A a7d6e1906f63
bulk-pause is a skill published in the GitHub repository uptimerobot/ai (24 stars, last pushed 19d ago), licensed MIT. It adds 33 tokens to every session and 1,138 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
fix-datadog-issues
Find, triage, and fix production errors captured by Datadog Error Tracking, then open a PR. Use when asked to look at "Datadog issues/incidents/errors", "find and fix bugs from Datadog", investigate the most-frequent or newest production errors, or work a specific Datadog Error Tracking issue.
database-postgres
Drizzle schema, repositories, RLS, SqlClient wiring, Postgres migrations, psql / reset, or platform mappers (toDomain / toInsertRow).
async-jobs-and-events
Queues and workers, domain event publishers, async notifications or projections, or not doing that work inside HTTP handlers.
effect-and-errors
Composing Effect programs, domain errors, HttpError, repository error types, or error propagation at HTTP boundaries.
better-auth-best-practices
Configure Better Auth server and client, set up database adapters, manage sessions, add plugins, and handle environment variables. Use when users mention Better Auth, betterauth, auth.ts, or need to set up TypeScript authentication with email/password, OAuth, or plugin configuration.
ci-watchdog
Continuously monitor GitHub PR CI checks and automatically fix failures until all checks pass. USE THIS SKILL when: The user wants to "keep an eye on CI" or "wait for checks to pass" The user mentions monitoring PR status, CI status, or GitHub checks The user asks to watch a PR until it's ready or fix failing checks…