analysis-new

analysis-new is a command for Claude Code from with-geun/alive-analysis. It costs 0 tokens per session (6,506 once invoked), scanned A, original, MIT.

A command for starting a new data analysis. It can begin an investigation, modeling, or simulation, or continue from an earlier analysis or monitoring alert.

In plain words
What is it for?
Starting root-cause investigations, predictive or classification modeling, what-if simulations, and analysis escalated from alerts.
Why use it?
It guides the setup of an analysis and loads the project's configuration, reducing missed context and setup steps.

Command for Claude Code

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 commands/with-geun/alive-analysis/analysis-new
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 analysis-new

README.md
[![agentmods](https://agentmods.dev/badge/commands/with-geun/alive-analysis/analysis-new.svg)](https://agentmods.dev/commands/with-geun/alive-analysis/analysis-new)
Your own site
<a href="https://agentmods.dev/commands/with-geun/alive-analysis/analysis-new"><img src="https://agentmods.dev/badge/commands/with-geun/alive-analysis/analysis-new.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 6,506 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 $0.00000 $0.06506
Opus 5 $0.00000 $0.03253
Sonnet 5 $0.00000 $0.01301
Haiku 4.5 $0.00000 $0.00651

Measured 4d ago against content hash fc748836d22f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analysis-new 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 4d 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/analysis-new.md · 848 lines

How it starts

The opening of the file, as written. The whole thing — 848 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/analysis new

Start a new analysis. Supports --from {Quick ID} for Quick-to-Full succession and --from-alert {Alert ID} for monitor alert escalation.

Instructions

Step 1: Check initialization

Verify .analysis/config.md exists. If not, tell the user to run /analysis init first. Read config.md to load team context (metrics, stakeholders, data stack).

Step 2: Parse arguments

  • If --from-alert {Alert ID} is provided, this is a monitor alert escalation (skip to Step 2d)
  • If --from {ID} is provided, this is a Quick→Full succession (skip to Step 2c)
  • Otherwise, proceed to Step 2a

Step 2a: Ask analysis type

Use AskUserQuestion:

Q1. What type of analysis?

  • 🔍 Investigation — "Why did this happen?" Root cause analysis, anomaly detection, ad-hoc deep dives.
  • 📈 Modeling — "Can we predict/classify/segment?" Statistical modeling, ML, forecasting.
  • 🔮 Simulation — "What would happen if we do X?" Policy evaluation, pricing strategy, resource allocation.

(These are available as separate commands:)

  • 📊 Monitoring → /monitor setup
  • 🧪 Experiment → /experiment new

Step 2b: Ask mode and details

Q2. Analysis mode?

  • Full — 5 ALIVE files + full checklists.
  • Quick — Single file with abbreviated ALIVE flow.

Q3. Analysis title?

  • Free text input

Q4. (Full only) Brief description

  • Investigation: "What do you want to find out?"
  • Modeling: "What do you want to predict or classify?"
  • Simulation: "What policy or strategy are you evaluating?"
  • This seeds the ASK phase.

Q5. Tags (optional)

  • Suggest tags from config.md's Tags list if available
  • Also suggest based on title/description: "Based on your title, relevant tags might be: retention, mobile"
  • User can accept suggestions, add custom tags, or skip
  • Format: comma-separated, lowercase, no spaces (use hyphens for multi-word: user-onboarding)

Step 2c: Quick→Full succession

  • Read the Quick file referenced by --from {ID}
  • Extract content from each ALIVE section
  • Use as seed content for Full analysis files using the mapping below
  • Add a reference link in the Quick file: > ⬆️ Promoted to Full: {new Full ID}

Read the full file on GitHub · 848 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. 4d ago First seen · 848 lines · 0 tokens per session scan A fc748836d22f

Subscribe to this mod's changes

analysis-new 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 6,506 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.