pixel-capi

pixel-capi is a skill for Claude Code, Codex from TheMattBerman/meta-ads-kit. It costs 53 tokens per session (2,681 once invoked), scanned A, original, MIT.

A setup and checking guide for Meta Pixel, a browser tracking code, and Conversions API, which sends advertising events from your server. It covers matching browser and server events and improving event-quality scores.

In plain words
What is it for?
Use it to install or audit browser and server tracking, test events, configure duplicate-event handling, and improve data sent to Meta advertising platforms.
Why use it?
It helps find gaps in ad conversion tracking when browsers, ad blockers, or privacy settings hide some events. It also helps prevent the same purchase or lead from being counted twice.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/themattberman/meta-ads-kit/pixel-capi
Any agent
npx skills add TheMattBerman/meta-ads-kit --skill pixel-capi
Clone the repo
git clone --depth 1 https://github.com/TheMattBerman/meta-ads-kit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for pixel-capi

README.md
[![agentmods](https://agentmods.dev/badge/skills/themattberman/meta-ads-kit/pixel-capi.svg)](https://agentmods.dev/skills/themattberman/meta-ads-kit/pixel-capi)
Your own site
<a href="https://agentmods.dev/skills/themattberman/meta-ads-kit/pixel-capi"><img src="https://agentmods.dev/badge/skills/themattberman/meta-ads-kit/pixel-capi.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,681 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.02681
Opus 5 $0.00026 $0.01340
Sonnet 5 $0.00011 $0.00536
Haiku 4.5 $0.00005 $0.00268

Measured 4d ago against content hash b45acd067033, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pixel-capi scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/capi-send.sh, scripts/capi-test.sh, scripts/emq-check.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "https://graph.facebook.com/v19.0/act_ACCOUNT_ID/adspixels?fields=name,id,last_fired_time&access_token=$META_TOKEN" | jq '.data'
skills/pixel-capi/SKILL.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pixel + CAPI -- Your Server-Side Signal Stack

The browser pixel alone is broken. iOS 14.5 killed 30-50% of signal. Ad blockers take another 20-30%. Cookie deprecation is finishing the job.

The fix is Conversions API (CAPI) -- server-side event sending that runs parallel to the browser pixel, shares event IDs for deduplication, and passes hashed user data that browsers can't block.

This skill audits, sets up, tests, and optimizes your Meta Pixel + CAPI stack. Target: 9.3+ EMQ on Purchase, 8.0+ on Lead.

Always read references/pixel-capi-reference.md first. That doc is the full knowledge base. Scripts automate the work; the reference doc explains the why.


Brand Memory Integration

Reads: workspace/brand/stack.md for stored pixel IDs and account IDs

File What it provides
workspace/brand/stack.md Stored pixel ID, ad account ID, platform type

Writes:

File What it contains
workspace/brand/stack.md Appends pixel ID, EMQ scores, platform config
workspace/brand/learnings.md Appends EMQ findings, platform gotchas, fixes applied

Core Concepts (Read Before Acting)

Before running any script, load references/pixel-capi-reference.md for:

  • Why pixel + CAPI together is non-negotiable in 2026
  • How deduplication works (shared event_id between browser and server)
  • EMQ scoring weights (em > ph > fn+ln > fbp/fbc > ip+ua)
  • Platform-specific gotchas (Next.js hydration, Shopify checkout limits, etc.)

Key principle: Never send PII unhashed. Scripts handle SHA-256 hashing automatically. If implementing manually, hash everything: lowercase, trim whitespace, then sha256sum.


Workflow

1. Audit an Existing Pixel

Check what's configured, what's missing, infer EMQ.

Run: scripts/pixel-audit.sh <account_id_or_pixel_id>

If given an ad account ID (e.g., act_123456): lists all pixels, audits each. If given a pixel ID directly: audits that pixel only.

Read the full file on GitHub · 287 lines

Files

What ships with it

6 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.

Changes

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.

  1. 4d ago First seen · 287 lines · 53 tokens per session scan A b45acd067033

Subscribe to this mod's changes

pixel-capi is a skill published in the GitHub repository TheMattBerman/meta-ads-kit (311 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 2,681 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens