Skip to main content
plugin

experiment-tracker · ccplugins — Claude Code plugin for experiment tracking

experiment-tracker is a Claude Code plugin for tracking A/B tests and feature experiments, documenting changes, and reviewing results before a launch decision.

Apache-2.0 ★ 1,013 updated 2026-08-12

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add ccplugins/awesome-claude-code-plugins
/plugin install experiment-tracker@awesome-claude-code-plugins
Open on GitHub

What experiment-tracker does

The plugin includes a subagent for feature experiments, A/B tests, and iterative improvements. It can help document a test, set up tracking, and analyze results. Call on it when adding a feature flag, changing an experiment, or reviewing its outcomes.

It can also compile results after launch and at experiment milestones, helping inform a decision about whether to expand a test. Its workflow is framed around a six-day development cycle. The subagent needs experiment results and metrics to analyze; it does not replace the data collected by a test.

What it helps with

  • document an A/B test and record changes to it
  • track results after launching an experimental feature
  • review test outcomes before expanding an experiment
  • weigh metrics and user feedback before deciding what to do with a feature

Example prompts for the agent

  • Document an A/B test for the new onboarding flow and help set up tracking.
  • Review the results of the launched feature experiment and advise whether to expand the test.
  • Compare the metrics and user feedback for this experimental feature before we decide whether to keep it.

How to install experiment-tracker

Plugin marketplace

/plugin marketplace add ccplugins/awesome-claude-code-plugins
/plugin install experiment-tracker@awesome-claude-code-plugins

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about experiment-tracker

How do I install experiment-tracker in Claude Code?

Run these commands in order: /plugin marketplace add ccplugins/awesome-claude-code-plugins, then /plugin install experiment-tracker@awesome-claude-code-plugins.

What does experiment-tracker do?

It adds a subagent that helps document feature experiments and A/B tests, track their results, and analyze experiment data.

When should I use experiment-tracker?

Use it when starting or changing an experiment, adding a feature flag, or reviewing results before deciding whether to expand a test.

Source text

experiment-tracker · Apache-2.0
PROACTIVELY use this agent when experiments are started, modified, or when results need analysis. This agent specializes in tracking A/B tests, feature experiments, and iterative improvements within the 6-day development cycle. Should be triggered automatically when experimental code paths or feature flags are introduced. Examples:\n\n<example>\nContext: When implementing feature flags or A/B test variants\nuser: "Add a feature flag to test the new onboarding flow"\nassistant: "I've implemented the feature flag for the onboarding flow A/B test. Let me use the experiment-tracker agent to properly document this experiment and set up tracking."\n<commentary>\nEvery feature flag represents an experiment that needs proper tracking and success metrics.\n</commentary>\n</example>\n\n<example>\nContext: After deploying experimental features\nuser: "The new viral sharing feature is now live for 10% of users"\nassistant: "Great! The viral sharing feature is deployed. I'll use the experiment-tracker agent to monitor its performance and document initial results."\n<commentary>\nLive experiments need immediate tracking setup to capture valuable data from the start.\n</commentary>\n</example>\n\n<example>\nContext: When reaching experiment milestones\nuser: "It's been a week since we launched the TikTok integration test"\nassistant: "Perfect timing for analysis. Let me use the experiment-tracker agent to compile the week-one results and determine if we should expand the test."\n<commentary>\nRegular experiment checkpoints ensure data-driven decisions about feature rollouts.\n</commentary>\n</example>\n\n<example>\nContext: Before making product decisions\nuser: "Should we keep the AI avatar feature or remove it?"\nassistant: "Let me analyze the experiment data to inform this decision. I'll use the experiment-tracker agent to review all metrics and user feedback for the AI avatar feature test."\n<commentary>\nProduct decisions should be backed by experiment data, not gut feelings.\n</commentary>\n</example>

© Michael Galpert · Apache-2.0 · ccplugins/awesome-claude-code-plugins

Similar plugins

All plugins for Testing and QA →

experiment-tracker by other authors comes first.

experiment-tracker rohitg00 experiment-tracker logs metrics for ML training runs and compares runs side by side inside Claude Code. Useful once you have more than one run to judge. ★ 2,858repo stars managing-experiment-lifecycle PostHog The managing-experiment-lifecycle skill guides experiment state changes, from launch and pausing to exposure freezes, archiving, resets, and migration to the newer engine. CX Codex +1 408installs launchdarkly-experiment-setup launchdarkly launchdarkly-experiment-setup — a skill for Claude Code that sets up LaunchDarkly experiments. It defines metrics, treatments, and flag settings, then runs iterations and records a winner. CX Codex +1 2,800installs configuring-experiment-rollout PostHog configuring-experiment-rollout — a skill that helps the agent set variant splits and rollout percentages for PostHog experiments, and disambiguate vague requests like "roll out to 25%". CX Codex +1 418installs measure-experiment-results product-on-purpose measure-experiment-results turns a finished experiment or A/B test into a readout with statistics, segment analysis and a ship, iterate or kill recommendation. CX Codex +1 830installs measure-experiment-design product-on-purpose measure-experiment-design produces an experiment design doc with variants, metrics, sample size and duration. Useful once the hypothesis is written and the test has not started yet. CX Codex +1 846installs Amplitude Experiment Implementation official github Amplitude Experiment Implementation — a GitHub Copilot subagent that takes a feature from issue requirements to an Amplitude experiment and wraps the code in its variants. CX Codex +1 ★ 41,430repo stars

From the same set184

The whole set →
growth-hacker Ships one subagent, Growth Hacker, into Claude Code for marketing growth work. It sits in the Marketing Growth category of the marketplace. ★ 1,013repo stars flutter-mobile-app-dev The flutter-mobile-app-dev plugin adds an agent for Flutter mobile app work. Ask it to inspect code, build a widget, or investigate a bug. ★ 1,013repo stars finance-tracker The finance-tracker plugin for Claude Code analyzes financial data to manage budgets, optimize costs and forecast revenue. ★ 1,013repo stars feedback-synthesizer feedback-synthesizer analyzes user feedback across multiple channels, detects patterns in complaints, and turns comments into clear backlog priorities. ★ 1,013repo stars enterprise-security-reviewer enterprise-security-reviewer — a Claude subagent that reviews B2B SaaS projects against SOC 2, GDPR and ISO 27001, checks tenant isolation, and preps the codebase for an audit. ★ 1,013repo stars enterprise-onboarding-specialist enterprise-onboarding-specialist adds a specialized agent for planning enterprise client onboarding, organizational adoption, and change management on B2B platforms. ★ 1,013repo stars enterprise-integrator-architect enterprise-integrator-architect is a Claude Code plugin for designing and building integrations between B2B apps and external enterprise systems. Call it for API orchestration, data sync, or third-party webhooks. ★ 1,013repo stars devops-automator The devops-automator subagent builds CI/CD pipelines, cloud infrastructure and monitoring for teams that want deployment handled automatically. ★ 1,013repo stars

Project sponsors

Companies that keep this analytics open