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/manage-experimentnpx skills add mixpanel/ai-plugins --skill manage-experimentgit 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/manage-experiment)<a href="https://agentmods.dev/skills/mixpanel/ai-plugins/manage-experiment"><img src="https://agentmods.dev/badge/skills/mixpanel/ai-plugins/manage-experiment.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 | $0.00209 | $0.03621 |
| Opus 5 | $0.00105 | $0.01810 |
| Sonnet 5 | $0.00042 | $0.00724 |
| Haiku 4.5 | $0.00021 | $0.00362 |
Grade A, and why
manage-experiment 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 5d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage Experiment
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 manages a Mixpanel experiment across its full lifecycle — design, launch, monitor, interpret. Four commands sit under the umbrella, picked by experiment phase (the state→command mapping lives in the Canonical commands section below).
The skill runs as a single interactive session per experiment. Commands compose naturally across phases — designing produces a configuration that launching commits, monitoring watches for safety issues mid-flight, interpreting consumes the matured result — but they're rarely invoked in the same session (the lifecycle spans days to weeks).
Components
The pieces the skill is built from. The Steps section below tells you how to use them.
Canonical commands
Each command lives in its own file under commands/ and is loaded on demand. Match commands explicitly (user names them) or implicitly (message matches a trigger phrase below).
| Command | File | Match if message contains any of |
|---|---|---|
design |
commands/design.md |
design, set up, configure, plan, sanity-check, hypothesis, MDE, sizing, sequential vs frequentist, CUPED, Winsorization |
launch |
commands/launch.md |
launch, go live, start the experiment, ready to ship the experiment, pre-launch check, launch readiness |
monitor |
commands/monitor.md |
monitor, mid-flight, is it safe, should I peek, SRM mid-flight, sample pace, guardrail wobble, terminate early |
interpret |
commands/interpret.md |
read results, ship, iterate, kill, wait, statsig, SRM, sample ratio mismatch, retro A/A, lift, polarity, segment breakdown, session replays |
If a message could route to more than one, use the phase-derived rule based on experiment state:
What ships with it
19 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.
- commands/design.md 13 KB
- commands/interpret.md 8.9 KB
- commands/launch.md 7.0 KB
- commands/monitor.md 6.2 KB
- references/advanced-features.md 7.6 KB
- references/health-check-interpretation.md 13 KB
- references/hypothesis-framing.md 7.4 KB
- references/lifecycle-handoff.md 2.9 KB
- references/metric-selection.md 6.5 KB
- references/per-metric-interpretation.md 11 KB
- references/pitfalls.md 8.4 KB
- references/prior-experiments.md 6.0 KB
- references/routing-xp-vs-ff.md 5.9 KB
- references/segment-breakdown-interpretation.md 6.4 KB
- references/segment-of-interest-selection.md 6.6 KB
- references/session-replay-analysis.md 7.1 KB
- references/sizing.md 9.0 KB
- references/statistical-model.md 7.7 KB
- references/why-no-statsig.md 13 KB
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.
- 5d ago First seen · 199 lines · 209 tokens per session scan A dc030125452d
manage-experiment is a skill published in the GitHub repository mixpanel/ai-plugins (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 209 tokens to every session and 3,621 once invoked, about $0.0010 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…