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/deep-researchnpx skills add mixpanel/ai-plugins --skill deep-researchgit clone --depth 1 https://github.com/mixpanel/ai-pluginsWrote 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/mixpanel/ai-plugins/deep-research)<a href="https://agentmods.dev/skills/mixpanel/ai-plugins/deep-research"><img src="https://agentmods.dev/badge/skills/mixpanel/ai-plugins/deep-research.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 | $0.00076 | $0.00926 |
| Opus 5 | $0.00038 | $0.00463 |
| Sonnet 5 | $0.00015 | $0.00185 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
deep-research 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 3d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research / Metric Investigation
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.
This skill is a structured investigation, not a one-shot answer.
Requirements
- Access to Mixpanel (query schemas, run queries, manage dashboards).
When to use this skill
Trigger when the user wants to understand why something happened in their data. Common phrasings:
- "Why did [metric] drop / spike / change?"
- "Can you do a deep dive on [X]?"
- "What's driving [trend]?"
- "Root cause this for me."
- "Help me understand what happened with [feature / cohort / segment]."
Do not trigger for one-off lookups ("what was DAU yesterday?"). Those are direct queries, not investigations.
Workflow
Phase 1 — Scope
Do not run analysis queries until scope is confirmed.
Do your best to find the following information from the user's question and context. If anything is missing or ambiguous, ask clarifying questions before proceeding.
- Project. Which Mixpanel project? If the user has access to several, ask.
- Events. Which events relate to the question?
- Properties. Which properties are relevant to break down by? (e.g. platform, utm_source, plan_tier)
State your assumptions and ask the user to confirm before continuing. The final answer depends on this being right.
Phase 2 — Validate and plan
Run small exploratory queries to confirm data exists in the analysis window. Be resilient — try different approaches if your first attempts don't work. If volume is zero, partial, or anomalously low, surface that to the user before going further.
Then present a compact plan:
*Investigation Plan*
• *Project:* `project name`
• *Events:* `event_a`, `event_b`, `event_c`
• *Properties:* `platform`, `utm_source`, `plan_tier`
*Initial Queries:*
• Trend of event_a over 30 days to establish baseline
• Breakdown by platform to isolate where the change happened
• ...
Say *yes* to continue the analysis.
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.
- 3d ago First seen · 99 lines · 76 tokens per session scan A ce44e9a76cbc
deep-research is a skill published in the GitHub repository mixpanel/ai-plugins (15 stars, last pushed 9d ago), licensed Apache-2.0. It adds 76 tokens to every session and 926 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.
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…