alive-analysis

alive-analysis is a skill for Claude Code, Codex from with-geun/alive-analysis. It costs 25 tokens per session (3,392 once invoked), scanned A, original, MIT.

A data-analysis workflow based on ALIVE: Ask, Look, Investigate, Voice, and Evolve. It provides a full path for analysts and a shorter guided version for other roles.

In plain words
What is it for?
It helps define the real question, inspect data, test explanations, communicate findings, and update the analysis; it also manages analysis status and configuration between actions.
Why use it?
It helps turn a vague question into a structured investigation while keeping progress and decisions recorded in files for later sessions.

Skill for Claude CodeCodex

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 skills/with-geun/alive-analysis/cursor
Any agent
npx skills add with-geun/alive-analysis --skill cursor
Clone the repo
git clone --depth 1 https://github.com/with-geun/alive-analysis

Made for: Claude Code, Codex.

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 alive-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/with-geun/alive-analysis/cursor.svg)](https://agentmods.dev/skills/with-geun/alive-analysis/cursor)
Your own site
<a href="https://agentmods.dev/skills/with-geun/alive-analysis/cursor"><img src="https://agentmods.dev/badge/skills/with-geun/alive-analysis/cursor.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,392 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 $0.00025 $0.03392
Opus 5 $0.00013 $0.01696
Sonnet 5 $0.00005 $0.00678
Haiku 4.5 $0.00003 $0.00339

Measured 4d ago against content hash 80f46e5c14e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

alive-analysis 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.

The scan reads SKILL.md. This mod also ships 1 executable file (hooks/post-analysis-action.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

platforms/cursor/SKILL.md · 384 lines

How it starts

The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.

alive-analysis Skill (Cursor Edition)

Data analysis workflow kit based on the ALIVE loop. Optimized for Cursor's batch-oriented agent model.


Cursor-Specific Behavior

State management: Read .analysis/status.md and .analysis/config.md at the start of EVERY command. Write updates back to .analysis/status.md after EVERY action.

Question style: Present ALL questions at once in a structured form. Do NOT ask questions one by one — Cursor agents work best with batch input.

File-based context: There is no session memory. Always read state from files before acting.


Overview

alive-analysis structures data analysis using the ALIVE loop: Ask → Look → Investigate → Voice → Evolve

Two personas:

  • Data analysts: Deep, systematic analysis with full ALIVE flow (5 files)
  • Non-analyst roles (PM, engineers, marketers): Quick analysis with guided framework (1 file)

ALIVE Loop Summary

Stage 1: ASK

What do we want to know — and WHY?

  • Define the problem clearly; confirm the requester's REAL goal
  • Frame: causation ("Why did X happen?") vs correlation ("Are X and Y related?")
  • Build a hypothesis tree before touching data
  • Set success criteria and scope boundaries
  • Use the Structured Data Request: [Period] + [Subject] + [Condition] + [Metric] + [Output Format]

Stage 2: LOOK

What does the data ACTUALLY show — and what's missing?

  • Review data quality (missing values, outliers, date ranges)
  • Segment before averaging — never trust aggregates alone
  • Check for confounding variables and external factors
  • Map cross-service dependencies
  • Validate data access methods

Stage 3: INVESTIGATE

Why is it REALLY happening — can we prove it?

  • Eliminate hypotheses systematically (not just confirm the first one)
  • Apply multi-lens analysis: macro → meso → micro
  • Test causation vs correlation rigorously
  • Perform sensitivity analysis for robustness
  • Assign confidence levels to findings

Stage 4: VOICE

So what — and now what?

Read the full file on GitHub · 384 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 · 384 lines · 25 tokens per session scan A 80f46e5c14e1

Subscribe to this mod's changes

alive-analysis is a skill published in the GitHub repository with-geun/alive-analysis (41 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 3,392 once invoked, about $0.0001 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.