experiment-monitor

experiment-monitor is an agent for Claude Code from ai-analyst-lab/ai-analyst-plugin. It costs 32 tokens per session (1,232 once invoked), scanned A, original, MIT.

A daily checker for live experiments, such as A/B tests that compare different versions. It checks whether groups are receiving the expected traffic, safety limits are being respected, and enough data is accumulating.

In plain words
What is it for?
It helps monitor traffic balance, safety metrics, sample counts, and projected statistical power, with extra checks by platform, country, or browser when traffic is unbalanced.
Why use it?
It helps find problems early, before unreliable data leads to a bad decision.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-analyst-plus plugin — 44 skills, 1 command, 13 agents shipped together

Good fit It helps monitor traffic balance, safety metrics, sample counts, and projected statistical power, with extra checks by platform, country, or browser when traffic is unbalanced.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ai-analyst-lab/ai-analyst-plugin/experiment-monitor
Install

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.

Clone the repo
git clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-plugin

Made for: Claude Code.

Or install ai-analyst-plus, the plugin that ships this one along with the rest of its 44 skills, 1 command, 13 agents.

Wrote 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.

agentmods badge for experiment-monitor

README.md
[![agentmods](https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plugin/experiment-monitor/github.svg)](https://agentmods.dev/agents/ai-analyst-lab/ai-analyst-plugin/experiment-monitor)
Your own site
<a href="https://agentmods.dev/agents/ai-analyst-lab/ai-analyst-plugin/experiment-monitor"><img src="https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plugin/experiment-monitor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for experiment-monitor

Your own site · 80×15
<a href="https://agentmods.dev/agents/ai-analyst-lab/ai-analyst-plugin/experiment-monitor"><img src="https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plugin/experiment-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,232 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.01232
Opus 5 $0.00016 $0.00616
Sonnet 5 $0.00006 $0.00246
Haiku 4.5 $0.00003 $0.00123

Measured 12d ago against content hash c7aa81df2a00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

experiment-monitor 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 12d 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.

ai-analyst-plus/agents/experiment-monitor.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Experiment Monitor

Purpose

Provide daily health checks for running experiments. Detects problems early (SRM, guardrail violations, sample ratio drift) so the team can act before collecting invalid data. Uses coded statistical helpers instead of improvised Python.

Inputs

  • {{EXPERIMENT_CONFIG}}: Path to experiment.yaml with expected allocation and guardrail thresholds.
  • {{CURRENT_DATA}}: Path to current experiment data (CSV/parquet/table).

Workflow

Step 1: SRM Check (Mandatory First)

from experiment_stats import srm_check

# Use Microsoft's production threshold
observed = [control_n, treatment_n]
expected = [config.variants[0].allocation, config.variants[1].allocation]
srm_result = srm_check(observed, expected, threshold=0.0005)

Verdicts:

  • PASS → Continue to Step 2
  • WARNING → Flag in report, continue with caution
  • BLOCK → RED status. HALT. Alert the team immediately.

If BLOCK, run segmented SRM to find the root cause:

from experiment_stats import srm_diagnose
diagnosis = srm_diagnose(assignments_df, group_col="variant",
                         segments=["platform", "country", "browser"])

Step 2: Sample Accumulation

Compare current sample to required sample from experiment.yaml:

Current: [N_control + N_treatment]
Required: [experiment.yaml → power.total_sample_size]
Progress: [current / required * 100]%
Projected completion: [days remaining at current enrollment rate]

Step 3: Guardrail Monitoring

For each guardrail metric in experiment.yaml:

from experiment_stats import welch_test, proportion_test

# One-sided test for "do_not_increase" guardrails
# Two-sided for general guardrails
for guardrail in config.metrics.guardrail:
    if guardrail.type == "proportion":
        result = proportion_test(c_success, c_n, t_success, t_n)
    else:
        result = welch_test(control_values, treatment_values)

    # Check against threshold from experiment.yaml
    if exceeds_threshold(result, guardrail):
        status = "RED"
    elif approaching_threshold(result, guardrail):
        status = "YELLOW"
    else:
        status = "GREEN"

Read the full file on GitHub · 152 lines

Changes

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.

  1. 12d ago First seen · 152 lines · 32 tokens per session scan A c7aa81df2a00

Subscribe to this mod's changes

experiment-monitor is an agent published in the GitHub repository ai-analyst-lab/ai-analyst-plugin (32 stars, last pushed 16d ago), licensed MIT. It adds 32 tokens to every session and 1,232 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 2026-08-30.

Related

Other agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

Geoprocessing Specialist

ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

research-scout

Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.

equinor/neqsim · 61 tokens

mathodology-problem-analyst

Understand contest questions, requirements, mechanisms and decision needs.

sweetcornna/mathodology · 20 tokens

astronomical-instrumentation-scientist

Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…

K-Dense-AI/scientific-agents · 78 tokens

eic_agent

Journal-Fit Reviewer seat; contributes the journal-fit / originality / overall-quality review card — the final editorial decision is editorialsynthesizeragent's Phase 2 work.

GGbond-bo/MemOmics-Agent · 38 tokens