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/mixpanel/ai-plugins/tracking-implementationnpx skills add mixpanel/ai-plugins --skill tracking-implementationgit clone --depth 1 https://github.com/mixpanel/ai-pluginsWhat 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 | $0.00087 | $0.04042 |
| Opus 5 | $0.00044 | $0.02021 |
| Sonnet 5 | $0.00017 | $0.00808 |
| Haiku 4.5 | $0.00009 | $0.00404 |
Grade A, and why
tracking-implementation 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 2d 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 — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
For any reference to agents.md.template, use this resource: agents.md.template.
For any reference to reference.md, use this resource: reference.md.
For any reference to sdk-snippets.md, use this resource: sdk-snippets.md.
Mixpanel Implementation
Engine optional — the core flow (SDK code generation, Live View verification) needs no engine. When schema lookups or post-deploy query checks come up, use an available engine per
ENGINE.md; otherwise use the documented fallbacks (direct the customer to Mixpanel Reports and Lexicon). Never stop for a missing engine.
CRITICAL -- DO NOT WRITE ANY CODE YET
This skill is a guided conversation, not a build template. You MUST collect answers from the user before generating any implementation code. Writing Mixpanel code without the inputs below will produce a broken implementation -- wrong SDK, wrong events, missing consent gates, or duplicate data pipelines.
Before writing ANY code, you must know ALL of the following:
- Which mode the user wants (Quick Start / Full Implementation / Add Tracking / Audit)
- What platform they're building on (determines which SDK -- wrong SDK = full rewrite)
- Whether they use a CDP like Segment (if yes, direct SDK installation is wrong -- data must route through the CDP)
- Whether they have EU or California users (if yes, events fired before consent = compliance violation requiring data deletion)
- What their Value Moment is -- the most important user action (you can't write tracking code without knowing what to track)
- For web/JavaScript platforms: whether they want Autocapture and/or Session Replay enabled -- if Autocapture is on, do NOT also set
track_pageview: trueor write manual page view events (duplicates)
If you do not have explicit answers to items 2--5, ASK. Do not assume. Do not infer from the project name. Do not start building.
The sections below tell you what to ask, in what order, and what to do with the answers. Follow the conversation flow -- it exists because wrong assumptions here create irreversible rework.
Full guidance, vertical-specific event examples, and governance detail are in reference.md. All per-language SDK code snippets are in sdk-snippets.md. Read specific sections on demand as you work through each mode.
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.
- 2d ago First seen · 328 lines · 87 tokens per session scan A ad079fdde220
tracking-implementation is a skill published in the GitHub repository mixpanel/ai-plugins (15 stars, last pushed 8d ago), licensed Apache-2.0. It adds 87 tokens to every session and 4,042 once invoked, about $0.0004 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…