AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Anakin Monitoring

skill-anakin-inc-agent-skills-anakin-monitoring · by Anakin-Inc

Use when the user wants to watch a web page, site, or Wire action for changes over time rather than fetch it once — price drops, stock or status changes, competitor page edits, new listings, content diffs, or scheduled checks with webhook/email alerts. Covers monitor_create, monitor_list, monitor_changes, monitor_control.

No reviews yet
0 installs
23 views
0.0% view→install

Install

$ agentstack add skill-anakin-inc-agent-skills-anakin-monitoring

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-anakin-inc-agent-skills-anakin-monitoring)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Anakin Monitoring? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Anakin: website monitoring

Scheduled checks that record a change when watched content differs from the previous run, optionally alerting a webhook or email.

Use this instead of re-scraping on a loop. If the user says "tell me when", "watch for", "alert me if", or "track over time", that is a monitor — not a repeated scrape.

Creating a monitor

monitor_create requires url and intervalMinutes (minimum 15).

Scope — what gets watched

  • "page" (default) — one URL.
  • "site" — crawls the site each run and tracks pages added, removed, changed.

Scope it with maxPages, maxDepth, includePatterns, excludePatterns.

  • "wire" — runs a Wire action each check and diffs its JSON. Pass

wireActionId (or wireCatalogSlug), wireParams, wireCredentialId, and wireWatchPaths to watch specific fields.

Watch mode — this is the cost lever

  • "full_page"2 credits/check, compares the whole page.
  • "specific_data"3 credits/check, extracts only the fields in

outputSchema with AI.

specific_data costs more per check but is usually the right choice for price, stock, or status tracking: full_page fires on any incidental edit, so you pay for checks and wade through noise. Define an outputSchema with just the fields that matter.

aiMode adds +1 credit/check and filters trivial noise, summarizing real changes. Worth it on pages that churn.

Cost arithmetic before you create

Credits/day = (1440 / intervalMinutes) x per-check cost. A 15-minute specific_data monitor with aiMode is 96 x 4 = 384 credits/day. Compute this and tell the user before creating — a short interval on a high-cost mode is an easy way to burn a plan.

Active-monitor caps: Free 5, Pro 20, Scale 100.

Other options

alertWebhookUrl, alertEmails, useBrowser, country, sessionId (for login-protected pages — see anakin-browser), expiresAt, isActive.

Managing monitors

  • monitor_list — all monitors, or pass id for one monitor's full config and

status (next/last check, active state, per-check cost, alerts). Call this first to get an id.

  • monitor_changes — the detected changes for a monitor id, each with a

diff/summary (plus the AI summary when aiMode is on).

  • monitor_control"pause", "resume", "run_now", "delete".
  • resume may hit the plan's active-monitor cap.
  • run_now is billed like a normal check.
  • delete permanently removes the monitor and its entire history. Confirm

with the user first; there is no undo.

Working pattern

  1. scrape the URL once to confirm the data is actually there and stable.
  2. Decide watchMode from what the user cares about — define outputSchema for

specific_data.

  1. Pick the longest intervalMinutes that still meets the need.
  2. State the credits/day, then monitor_create.
  3. Report the monitor id back so the user can manage it later.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.