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/installnpx skills add mixpanel/ai-plugins --skill installgit 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 | $0.00167 | $0.01360 |
| Opus 5 | $0.00084 | $0.00680 |
| Sonnet 5 | $0.00033 | $0.00272 |
| Haiku 4.5 | $0.00017 | $0.00136 |
Grade A, and why
install 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mixpanel Install
No engine required — this skill is what sets engines up.
Set up how this project talks to Mixpanel. Engines can coexist — a project may have more than one; this skill adds one and can record which to prefer. How the other skills resolve an engine (the precedence ladder, preference locations) lives in ../../ENGINE.md — read it before starting.
This skill is interactive: it asks the user to choose. If the session can't ask questions (non-interactive/CI run), stop and tell the user to run /mixpanel:install in an interactive session instead.
The bundled references defer to the live Mixpanel docs they cite — on any conflict, trust the live page.
Step 0 — Detect existing state
- Mixpanel MCP tools listed in this session → tell the user the MCP engine is already set up (name the region if the server URL is visible) and ask: keep it, switch, or add another engine alongside it. Keep → stop here. Add another → Step 1, skipping the MCP option.
- Otherwise run
mp --version(one command). Success → the headless SDK is installed: ask "MCP is not available — how should we proceed?" with two options: (a) install MCP, (b) use headless. Installing MCP → Step 2a. Using headless → verify auth (Step 2b's verify) and jump to Step 3, including the preference note. - Neither → continue to Step 1.
Step 1 — Pick an engine to set up
Ask with the client's multiple-choice question UI (one question, three options):
- Mixpanel MCP server (recommended for interactive analytics) — a remote server exposing Mixpanel tools; OAuth login; best when a person is in the loop.
- Headless SDK — the
mixpanel-headlessPython package; the full Mixpanel platform as a Python object; best for scripted, CI, or coding-agent workflows. - I have my own integration — the user already has their own way to reach Mixpanel.
Step 2a — MCP path
- Ask the region: US / EU / India (URL map in
references/mcp-setup.md). If the user is unsure, their Mixpanel URL tells them (eu.mixpanel.com→ EU,in.mixpanel.com→ India; otherwise US). - Register the server with the current client following
references/mcp-setup.md— the standard recipe per client, plus the fallback transport. No further questions; just run the standard installation. - Verify: list the server's tools. If authentication is pending, have the user complete the client's OAuth flow (per the reference), then re-check.
What ships with it
2 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 · 69 lines · 167 tokens per session scan A e47e49bad3b6
install is a skill published in the GitHub repository mixpanel/ai-plugins (15 stars, last pushed 8d ago), licensed Apache-2.0. It adds 167 tokens to every session and 1,360 once invoked, about $0.0008 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…