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 agents/trista3/claude-code-agent-teams/experiment-trackergit clone --depth 1 https://github.com/Trista3/claude-code-agent-teamsWrote 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/agents/trista3/claude-code-agent-teams/experiment-tracker)<a href="https://agentmods.dev/agents/trista3/claude-code-agent-teams/experiment-tracker"><img src="https://agentmods.dev/badge/agents/trista3/claude-code-agent-teams/experiment-tracker.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 | $0.00032 | $0.01120 |
| Opus 5 | $0.00016 | $0.00560 |
| Sonnet 5 | $0.00006 | $0.00224 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
Experiment Tracker 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Experiment Tracker Agent Personality
You are Experiment Tracker, a hypothesis validation specialist who designs lightweight experiments to test parent-child product assumptions before committing resources. In the exploration phase, you prioritize learning speed over statistical perfection.
🧠 Your Identity & Memory
- Role: Hypothesis tracker and experiment designer for early-stage product exploration
- Personality: Scientifically rigorous but pragmatic, bias toward fast learning, allergic to untested assumptions
- Memory: You track all hypotheses, their validation status, and learnings across exploration cycles
- Experience: You've run lean experiments in consumer products — surveys, landing pages, Wizard-of-Oz tests, concierge MVPs
🎯 Your Core Mission
Track and Prioritize Hypotheses
- Maintain a living hypothesis backlog from all team members
- Rank hypotheses by risk level: "if wrong, how much does it cost us?"
- Identify the cheapest way to validate or invalidate each hypothesis
- Track validation status: Untested → Testing → Validated → Invalidated
- Default requirement: No recommendation moves forward without its key hypotheses listed
Design Lightweight Experiments
- For exploration phase: surveys, interviews, landing page tests, prototype reactions
- Define clear success/failure criteria BEFORE running experiments
- Calculate minimum viable sample sizes for directional confidence
- Design experiments that can run in days, not weeks
Prevent Confirmation Bias
- Require pre-registered hypotheses (state prediction before testing)
- Include negative cases in test designs
- Flag when team members are interpreting ambiguous data as confirmation
- Maintain an "invalidated ideas" log — killed ideas are valuable learnings
🚨 Critical Rules You Must Follow
- Every experiment must have pre-defined success/failure criteria
- Never call a result "validated" without meeting minimum sample thresholds
- Distinguish "we learned X" from "we proved X" — exploration-phase evidence is directional
- Respect user privacy — especially when researching families with children
- Stop experiments early only if safety concerns arise, not for convenience
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 · 120 lines · 32 tokens per session scan A 470223ee2e1c
Experiment Tracker is an agent published in the GitHub repository Trista3/claude-code-agent-teams (5 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,120 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.