experiment-archive

experiment-archive is a command for Claude Code from with-geun/alive-analysis. It costs 0 tokens per session (704 once invoked), scanned A, original, MIT.

A command that archives a completed alive-analysis experiment by creating a summary from its recorded stages. An experiment tests a hypothesis and uses the result to guide a decision.

In plain words
What is it for?
Use `/experiment archive` after an experiment reaches the decision stage, or when a cancelled or abandoned experiment should be documented and stored.
Why use it?
It turns scattered experiment notes into a durable record of the hypothesis, results, decision, important numbers, and lessons learned.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use /experiment archive after an experiment reaches the decision stage, or when…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/with-geun/alive-analysis/experiment-archive
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/with-geun/alive-analysis

Made for: Claude Code.

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-archive

README.md
[![agentmods](https://agentmods.dev/badge/commands/with-geun/alive-analysis/experiment-archive.svg)](https://agentmods.dev/commands/with-geun/alive-analysis/experiment-archive)
Your own site
<a href="https://agentmods.dev/commands/with-geun/alive-analysis/experiment-archive"><img src="https://agentmods.dev/badge/commands/with-geun/alive-analysis/experiment-archive.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 704 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 $0.00000 $0.00704
Opus 5 $0.00000 $0.00352
Sonnet 5 $0.00000 $0.00141
Haiku 4.5 $0.00000 $0.00070

Measured 7d ago against content hash 474a3db274cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

experiment-archive 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 7d 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.

.claude/commands/experiment-archive.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/experiment archive

Archive a completed experiment.

Instructions

Step 1: Identify experiment to archive

Read .analysis/status.md for active experiments (Type: 🧪 Experiment).

  • If argument provided (ID), use that
  • If only 1 active experiment in LEARN stage → select automatically
  • Otherwise, show list and ask user which to archive
  • Warn if the experiment hasn't reached DECIDE stage yet: "This experiment is still in {stage}. Archive anyway? (Archiving early is OK for cancelled/abandoned experiments)"

Step 2: Generate summary.md

For Full Experiment:

Read all stage files (01_design.md through 05_learn.md) and generate:

# Summary: {title}
> ID: {ID}
> Period: {start_date} ~ {end_date}
> Type: 🧪 Experiment | Owner: {owner}

## Outcome
- **Hypothesis**: {from 01_design.md}
- **Result**: Confirmed / Rejected / Inconclusive
- **Decision**: 🚀 Launched / 🔴 Killed / ⏳ Extended / 🔄 Iterated

## Key Numbers
| Metric | Control | Treatment | Δ | Significant? |
|--------|---------|-----------|---|-------------|
| {primary} | | | | |

## Key Takeaway
- (Extract from 05_learn.md "One-Sentence Takeaway", or ask user)

## Impact
- (Extract from 04_decide.md impact estimate)

## Follow-Up
- Experiments: (from 05_learn.md)
- Analyses: (from 05_learn.md)
- Monitoring: (post-launch checkpoints status)

## Reproduction
- Key assets: `assets/`
- Design doc: `01_design.md`

For Quick Experiment:

Generate a compact summary appended to the Quick file header:

> ✅ Archived: {today} | Result: {decision} | Takeaway: {one-line summary}

Step 3: Move to archive

Determine archive folder: ab-tests/archive/{YYYY-MM}/

  • Create the year-month folder if it doesn't exist
  • Move the full experiment folder (or quick file) from active/ to archive/{YYYY-MM}/
  • For Full: place summary.md inside the experiment folder

Step 4: Update status.md

  • Remove the experiment from the "Active" table
  • Add to "Recently Archived" table (keep max 5 entries, remove oldest)
  • Update counts and "Last updated" timestamp

Read the full file on GitHub · 94 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. 7d ago First seen · 94 lines · 0 tokens per session scan A 474a3db274cf

Subscribe to this mod's changes

experiment-archive is a command published in the GitHub repository with-geun/alive-analysis (41 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 704 tokens. 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.