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 anysiteio/agent-skills --skill anysite-monitorgit clone --depth 1 https://github.com/anysiteio/agent-skillsWrote 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/anysiteio/agent-skills/anysite-monitor)<a href="https://agentmods.dev/skills/anysiteio/agent-skills/anysite-monitor"><img src="https://agentmods.dev/badge/skills/anysiteio/agent-skills/anysite-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/anysiteio/agent-skills/anysite-monitor"><img src="https://agentmods.dev/badge/skills/anysiteio/agent-skills/anysite-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 | $0.00260 | $0.03033 |
| Opus 5 | $0.00130 | $0.01517 |
| Sonnet 5 | $0.00052 | $0.00607 |
| Haiku 4.5 | $0.00026 | $0.00303 |
Grade A, and why
anysite-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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anysite Monitor
A one-shot Anysite call answers "what is the state right now?". This skill answers the harder question — "what changed since I last looked?" — by keeping a seen ledger of fingerprints in durable storage, subtracting it from each fresh fetch, and reporting only what's new or edited.
Two things make a monitor good, and both are decided at setup, not at runtime:
- The right sources. This skill ships no catalog. Anysite has 566
sources and they change; a baked-in list rots and quietly points monitors at
endpoints that no longer do what their name suggests. Instead, onboarding
searches the live catalog for the user's actual goal, verifies each candidate
with
discover+ one probe call, and compiles verified specs into the config. - State that survives. Each scheduled run is a fresh session with no memory.
Anysite's request cache does persist for 7 days across sessions (find old
cache_keys with the free
search_requests), but it is a cache of fetches, not a report state — 7-day retention is shorter than the ledger's rolling window, and it can't record what was already reported. So the ledger must sit in external storage a headless run can reach by token — OR, for daily-or-faster monitors with stable-id sources, run ledgerless (ledger_mode: "cache_diff"): diff each fetch against the prior runs' fetches still in that 7-day cache. Zero storage and no persist step, at the price of no long memory and silent loss after a failed delivery — mode selection rules inreferences/storage-backends.md.
Two modes
- Setup mode — the user wants to create or change a monitor. Interview, discover sources, compile the config, register the schedule, seed the baseline.
- Run mode — a scheduled task fired with a config in its prompt. Load ledger, execute the config's sources, diff, deliver, persist. If the incoming prompt already contains a monitor config, you are in Run mode — skip the interview.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 218 lines · 260 tokens per session scan A 6b4a9db10361
anysite-monitor is a skill published in the GitHub repository anysiteio/agent-skills (19 stars, last pushed 28d ago), licensed MIT. It adds 260 tokens to every session and 3,033 once invoked, about $0.0013 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…