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/converlyio/converly-mcp/setup-conversion-trackingnpx skills add converlyio/converly-mcp --skill setup-conversion-trackinggit clone --depth 1 https://github.com/converlyio/converly-mcpWrote 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/converlyio/converly-mcp/setup-conversion-tracking)<a href="https://agentmods.dev/skills/converlyio/converly-mcp/setup-conversion-tracking"><img src="https://agentmods.dev/badge/skills/converlyio/converly-mcp/setup-conversion-tracking.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00055 | $0.00753 |
| Opus 5 | $0.00028 | $0.00377 |
| Sonnet 5 | $0.00011 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
setup-conversion-tracking 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 5d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up conversion tracking with Converly
Tracking only works when THREE things are all true. A flow is published, the destination platform is connected (for server side platforms), and the Converly snippet is installed on the website. Never end this workflow without all three handled or handed to the user.
Steps
-
Understand the goal. Ask which form tool the site uses (Typeform, Webflow forms, Gravity Forms and so on) and which ad platform conversions should go to, unless the user already said.
-
Check the destination. Call
list_destinations. If the target platform isn't connected and it is a server side platform (its entry inlist_destination_typeshas a non emptyconnection_types), callconnect_destination. Share the link it returns, explain the account owner must open it in their browser and authorize, and ask them to tell you when they've finished. Then confirm withcheck_handoff_status. Browser side pixel platforms (emptyconnection_types) need no connection step. -
Build the flow. Call
list_trigger_typesfor the trigger id andlist_action_typesfor the exact action config the destination needs. Create withcreate_flow, then runvalidate_flowand fix any problems it reports. -
Publish. Call
publish_flow. Read its result carefully. Ifinstall_status.detectionis "never_seen", the loader has never phoned home from the site. That usually means the snippet still needs to be installed, so offer it. The check is quick to settle: the loader phones home when a page loads, so once the snippet is in, ask the user to open any page of their site and checkget_install_statusagain. Detection flips to "confirmed" within moments. If it stays "never_seen" after a page load, the snippet is not live yet (site builders need a republish). Two setups never send the phone-home signal: sites using the Converly Webflow app, and visitors with privacy signals or unconsented cookie banners. For those, a real form submission appearing inlist_eventsis the proof instead.
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.
- 5d ago First seen · 28 lines · 55 tokens per session scan A 9001a8bc2c92
setup-conversion-tracking is a skill published in the GitHub repository converlyio/converly-mcp (0 stars, last pushed 18d ago), licensed MIT. It adds 55 tokens to every session and 753 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
adcp-advertising
Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…
adspirer-ads-agent
Adspirer — AI-powered advertising and performance marketing agent. Manage Google Ads, Meta Ads (Facebook & Instagram), LinkedIn Ads, and TikTok Ads via natural language. 100+ tools for paid media campaign creation, live performance analysis, PPC keyword research with real CPC data, budget optimization, ad creative…
analytics-insights
Drive Google Analytics (GA4), Google Tag Manager, Google Search Console, and BigQuery from chat — tracking plans, GA4 reports, key-event (conversion) setup, custom dimensions and metrics, GTM audits, GSC performance, and GA4 BigQuery export queries. Use when the user wants an analytics audit, a GA4 report, a tracking…
cold-email-outreach
Run end-to-end B2B cold-email outreach through the Hyper MCP — enrich prospects with Apollo, scrape per-prospect signals from company sites and LinkedIn, draft personalized emails using proven hook frameworks, send via Gmail with safe defaults, and route replies into labeled folders. Use when the user wants to write…
competitor-intel
Run end-to-end competitor research and monitoring through the Hyper MCP — pick the set, scrape every public surface (site, blog, pricing, organic social, search rank, mentions, demand) via Firecrawl + HyperSEO + the Apify scrapers, diff against last run, and synthesize a brief. Use when the user wants to research…
Manage Instagram professional accounts via the Hyper MCP — publish photos, Reels, Stories, and carousels; moderate comments and mentions; send Direct Messages; pull account and media insights. Uses the Instagram API with Instagram Login (Business Login). Use when the user mentions Instagram posts, Reels, Stories…