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 swan-gtm/gtm-skills --skill visitor-radargit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/visitor-radar)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/visitor-radar"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/visitor-radar/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/swan-gtm/gtm-skills/visitor-radar"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/visitor-radar.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 | $0.00033 | $0.01383 |
| Opus 5 | $0.00016 | $0.00691 |
| Sonnet 5 | $0.00007 | $0.00277 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade A, and why
visitor-radar 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 9d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
Setup state. Not yet configured for this org. Load the Setup sub-page and walk the user through wiring the visitor-radar trigger (WEBSITE_VISIT, webinar / video WEBHOOK, or the CRM's form-fill workflow) with the right page / form / engagement filters, and wire the follow-up sequence, before running this play. (After setup is performed, rewrite this paragraph via swan-update-skill to describe the current state — trigger type chosen, monitored pages / forms / events with thresholds, exclusion filters, sequence wired, success metric, and last-refreshed date — so future runs see the current configuration without re-checking.)
When this fires
WEBSITE_VISIT (Swan-native website tracking), WEBHOOK (from a webinar / video / analytics platform), or the CRM's workflow trigger (if the CRM is wired to track form fills, list membership, or page visit thresholds — discover via swan-get-available-triggers). Payload includes: engager identity (email, LinkedIn, or anonymous company-level), content engaged with, engagement depth (time on page, completion %, multiple visits).
Step 1 — Filter for signal strength
Not all engagement converts. Tiered priority:
| Engagement | Signal strength |
|---|---|
| Pricing page > 60s, repeat visits | HIGH |
| Demo / sales page > 60s | HIGH |
| Gated asset download with title + company | HIGH |
| Webinar attended live | HIGH |
| Case study or comparison page visit | MEDIUM |
| Webinar registered but no-show | MEDIUM |
| Blog post read, no other activity | LOW |
| Anonymous company visit, no contact | LOW (act at account level) |
Skip LOW unless they're a known target account or multi-visit pattern emerges.
Step 2 — Resolve identity
If the trigger payload has an email, that's enough. If anonymous-company-only (from website tracking), use hubspot-search-objects to check whether any known contact at the company has had recent activity — that's probably who visited.
For form fills with email but no LinkedIn URL, swan-enrich-email to find the LinkedIn, then swan-enrich-contact for the full profile.
What ships with it
1 file 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.
- 9d ago First seen · 108 lines · 33 tokens per session scan A 70bf67c66778
visitor-radar is a skill published in the GitHub repository swan-gtm/gtm-skills (153 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 1,383 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 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.