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/ooiyeefei/ccc/meta-pixel-setupnpx skills add ooiyeefei/ccc --skill meta-pixel-setupgit clone --depth 1 https://github.com/ooiyeefei/cccWrote 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/ooiyeefei/ccc/meta-pixel-setup)<a href="https://agentmods.dev/skills/ooiyeefei/ccc/meta-pixel-setup"><img src="https://agentmods.dev/badge/skills/ooiyeefei/ccc/meta-pixel-setup.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 | $0.00176 | $0.02320 |
| Opus 5 | $0.00088 | $0.01160 |
| Sonnet 5 | $0.00035 | $0.00464 |
| Haiku 4.5 | $0.00018 | $0.00232 |
Grade A, and why
meta-pixel-setup 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 4d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Pixel Setup
Get the Meta Pixel tracking a real conversion on a website, verified, so Facebook/Instagram ad optimization has something true to learn from. Two things trip people up and this skill front-loads both: the Pixel-vs-Conversions-API decision (Meta's wizard aggressively pushes the heavier one) and which data category to declare (a wrong choice can throttle your ads).
Naming note: Meta renamed "Pixel" to "Dataset" in the UI. A dataset contains the pixel and its Dataset ID = Pixel ID (a ~15–16 digit number). Treat the two words as the same thing.
Start where the user is
Setup is a chain: Facebook Page → Business portfolio → Events Manager → Pixel/Dataset (get the ID) → base code on site → conversion event → verify. People arrive mid-chain. Ask first, then jump in — don't re-create what exists (a business often already has a pixel; reuse it rather than fragmenting data across two).
Ask (adapt to what they've said):
- Do you have a Facebook Page and Meta Business Suite / Business portfolio set up already?
- Do you already have a Pixel / Dataset (in Events Manager)? If yes, what's the Dataset ID (the ~16-digit number)? Paste it — that may be all that's needed.
- What's the one conversion that matters (a lead/waitlist submit, a signup, a purchase)? This is what ads optimize toward.
- The site's stack + domain (Next.js, plain HTML, WordPress, Shopify) — decides how the code goes in.
If they already have the Dataset ID and a Page, skip straight to install (§3). Do not walk them back through account creation they've done.
Decision 1: Pixel only, or + Conversions API? (start with Pixel only)
Meta's setup wizard shows "Conversions API and Meta Pixel (Recommended)" with a shiny stat. Don't reflexively take it. Here's the honest trade-off:
- Meta Pixel (browser) — a code snippet on the site sends events from the visitor's browser. Simple, no backend, works today. This is all you need to launch.
- Conversions API (CAPI) — your server sends events directly to Meta. It's server-to-server, "developer support required," and to actually help it needs customer PII (email, phone, IP) sent to Meta for matching. That's more build and a bigger privacy/compliance surface (GDPR/PDPA/CCPA).
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.
- 4d ago First seen · 116 lines · 176 tokens per session scan A a50e145143d5
meta-pixel-setup is a skill published in the GitHub repository ooiyeefei/ccc (483 stars, last pushed 1mo ago), licensed MIT. It adds 176 tokens to every session and 2,320 once invoked, about $0.0009 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…