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/create-dashboardnpx skills add mixpanel/ai-plugins --skill create-dashboardgit 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 | $0.00055 | $0.01032 |
| Opus 5 | $0.00028 | $0.00516 |
| Sonnet 5 | $0.00011 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
create-dashboard 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dashboard Creation
Engine required — resolve an engine per
ENGINE.md: one named in the conversation or loaded instructions is mandatory (not set up → offer/mixpanel:installfor it); otherwise use the Mixpanel MCP server, or offer/mixpanel:installif it's unavailable.
Your job is to design a coherent analytical narrative, not just drop reports into rows.
Requirements
- Access to Mixpanel (query schemas, run queries, manage dashboards).
Workflow
Phase 1 — Scope
Infer the theme from the user's request and surrounding context. Pick a sensible structure yourself. Ask clarifying questions if the request is fundamentally ambiguous (e.g. no project context at all).
- Project. Which Mixpanel project? If ambiguous, ask.
- Theme. What is the dashboard about? Derive scope from the request.
Phase 2 — Discover and validate
This is the most important phase. Empty or failing reports are the #1 complaint.
- Resolve event and property names by querying the project schema (always discover available events and properties before building queries).
- Run small probe queries to confirm the data exists and returns meaningful results.
- A query that runs successfully but returns zero rows is still not useful — treat it like a missing event.
Phase 3 — Plan layout
Before building, decide:
- Be space-efficient. Fewer rows with more reports each makes the dashboard faster to scan. Don't spread metrics across many rows when they fit naturally together.
- Row hierarchy. Headline metrics on top, supporting breakdowns below. The dashboard reads top-to-bottom like a narrative.
- Row count. Aim for 4-8 rows. Don't add every available breakdown, be smart.
- Items per row. Use 2–4 reports per row. A single report alone in a row wastes space — pair it with related metrics or a text card. 4 cards per row (text + reports combined) is the practical maximum.
- One conceptual focus per row. Group related reports together; never mix unrelated metrics in the same row just to fill space.
- Time filter. Decide intentionally: Dashboard global time filter overrides all the reports. Don't use it when you want each report to have its own default range.
- Text cards. Identify where they add real value (see rules below).
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 · 89 lines · 55 tokens per session scan A b26de352b1d3
create-dashboard is a skill published in the GitHub repository mixpanel/ai-plugins (15 stars, last pushed 8d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,032 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 2026-08-30.
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…