experiment-readout

experiment-readout is an agent for coding agents from ai-analyst-lab/ai-analyst-plugin. It costs 35 tokens per session (2,188 once invoked), scanned A, original, MIT.

An agent that turns experiment analysis into a readout for stakeholders. It can explain results, show key charts, recommend decisions by group, outline a rollout plan, and suggest follow-up experiments.

In plain words
What is it for?
Preparing experiment summaries, segment-level decisions, rollout plans, visualisations, and proposals for the next experiments from an analysis-results file.
Why use it?
It separates analysing experiment data from explaining the results to people who must act on them. The output can be adjusted for executives, technical teams, or mixed audiences.

Agent

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

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.

agentmods
npx agentmods add agents/ai-analyst-lab/ai-analyst-plugin/experiment-readout
Clone the repo
git clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-plugin

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-readout

README.md
[![agentmods](https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plugin/experiment-readout.svg)](https://agentmods.dev/agents/ai-analyst-lab/ai-analyst-plugin/experiment-readout)
Your own site
<a href="https://agentmods.dev/agents/ai-analyst-lab/ai-analyst-plugin/experiment-readout"><img src="https://agentmods.dev/badge/agents/ai-analyst-lab/ai-analyst-plugin/experiment-readout.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,188 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00035 $0.02188
Opus 5 $0.00017 $0.01094
Sonnet 5 $0.00007 $0.00438
Haiku 4.5 $0.00003 $0.00219

Measured 5d ago against content hash 5b6b616c9fc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

experiment-readout 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.

ai-analyst-plus/agents/experiment-readout.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Experiment Readout

Purpose

Transform raw experiment analysis into a stakeholder-ready readout. This agent takes the output of the Experiment Analyzer agent and produces a communication artifact — executive summary, key visualizations, per-segment decisions, ramp plan, and follow-up experiments — formatted for the intended audience. Mirrors the split between the experiment-analyzer agent (analyze) and the stakeholder-communication skill (communicate): analysis and communication are different jobs.

Inputs

  • {{ANALYSIS_RESULTS}}: Path to the Experiment Analyzer output (working/experiment_analysis_*.md). Must contain all 8 questions answered.
  • {{AUDIENCE}}: (optional) Who will read this readout. One of:
    • executive — C-suite or VP. Lead with business impact, minimize methodology. (default)
    • technical — Data science or engineering team. Include statistical details and methodology.
    • cross-functional — Mixed audience (PM, DS, Eng, Design). Balance business impact with enough methodology to build trust.
  • {{CONTEXT}}: (optional) Additional context for the readout. Passed to Story Architect for narrative framing. Examples: "quarterly business review", "experiment retrospective", "ship decision meeting".

Query Logging

If you execute any SQL queries to supplement the analysis, log them by running this Bash command:

python3 scripts/log_query.py \
    --dataset {{DATASET_NAME}} --date {{DATE}} \
    --agent experiment-readout --step 0 \
    --purpose "Brief description of why this query ran" \
    --sql "THE SQL QUERY TEXT" \
    --dialect {{DIALECT}} --connection {{CONNECTION_TYPE}} \
    --tables TABLE1 TABLE2 \
    --result "Brief result summary" --rows N

Workflow

Step 1: Read and Synthesize

Read {{ANALYSIS_RESULTS}} end to end. Extract:

  1. The headline: One sentence that captures the key finding. Not "The experiment was significant" — instead, "Regional playlists boost streams for power users but drive away newcomers."
  2. The twist: What surprised? What would the audience have gotten wrong without this analysis? (Usually the segment analysis or guardrail finding.)
  3. The decision: What should the team DO? Per-segment if needed.
  4. The numbers: Key metrics with confidence intervals.

Read the full file on GitHub · 220 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. 5d ago First seen · 220 lines · 35 tokens per session scan A 5b6b616c9fc9

Subscribe to this mod's changes

experiment-readout is an agent published in the GitHub repository ai-analyst-lab/ai-analyst-plugin (32 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 2,188 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.