alive-agents

alive-agents is a cursor rule for coding agents from with-geun/alive-analysis. It costs 49 tokens per session (2,521 once invoked), scanned A, original, MIT.

A rule that dispatches specialist sub-agents during an alive-analysis workflow. It covers specialists for statistics, data quality, hypotheses, SQL, writing, and ethics, and checks recorded decisions before making suggestions.

In plain words
What is it for?
Use it when moving between analysis stages, requesting a specialist, or asking about statistics, queries, data quality, narrative, hypotheses, or ethics.
Why use it?
It routes analysis tasks to the relevant expertise and prevents new recommendations from contradicting earlier documented decisions.

Cursor rule

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 rules/with-geun/alive-analysis/alive-agents
Clone the repo
git clone --depth 1 https://github.com/with-geun/alive-analysis

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-agents

README.md
[![agentmods](https://agentmods.dev/badge/rules/with-geun/alive-analysis/alive-agents.svg)](https://agentmods.dev/rules/with-geun/alive-analysis/alive-agents)
Your own site
<a href="https://agentmods.dev/rules/with-geun/alive-analysis/alive-agents"><img src="https://agentmods.dev/badge/rules/with-geun/alive-analysis/alive-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,521 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 $0.00049 $0.02521
Opus 5 $0.00024 $0.01260
Sonnet 5 $0.00010 $0.00504
Haiku 4.5 $0.00005 $0.00252

Measured 4d ago against content hash cc5b51d083ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

alive-agents 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.

platforms/cursor/rules/alive-agents.mdc · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

alive-analysis — Sub-agent Dispatch System

This rule activates the Sub-agent Dispatch System on top of the base alive-analysis workflow. It mirrors the Claude Code behavior using the same core/agents/registry.yml and router.yml.


When this rule applies

Activate when:

  • User runs /analysis-next (stage transition)
  • User runs /analysis-agent (explicit specialist call)
  • User message matches agent aliases: "통계", "가설", "리뷰", "데이터품질", "쿼리", "서술", "윤리", "scope", "sql", "stats", "review", "narrative", "ethics"

Decision Records Check (runs before agent dispatch)

Before evaluating gates or recommendations, check for relevant Decision Records:

  1. Read analyses/decisions/INDEX.md (if it exists and has entries)
  2. For each agent about to make a methodology suggestion, check for conflicting DRs:
    • hypothesis-gen: check Metric + Scope + Principle DRs
    • stats-agent: check Methodology DRs
    • metric-definer: check Metric DRs
  3. If a DR conflicts with a planned suggestion: surface the DR first, do not propose the rejected alternative
  4. Acknowledge applied DRs with: > DR-{NNN} 적용: {summary}

Sub-agent Dispatch Protocol

Step 1: Load config

Read .analysis/agents.yml (project-local) or fall back to core/config/agents.yml. If global.enabled: false → skip all agent dispatch logic.

Step 2: Determine context

  • Current stage (from analysis folder: which .md files exist)
  • Current stage file content (all sections)
  • .analysis/agent-state.md suppression history (if exists)

Step 3: Evaluate gates

Check gate conditions from core/agents/router.yml:

Gate Trigger
scope-guard ASK + Scope empty + Problem Definition filled
data-quality-sentinel LOOK→INVESTIGATE transition + quality incomplete
ethics-guard PII keywords in any content
reproducibility-keeper INVESTIGATE→EVOLVE transition + reproducibility section empty

For each matching gate (if enabled: true in config):

  • Print: [auto] Running {gate-id} — {reason}
  • Apply the gate's prompt from core/agents/prompts/{gate-id}.md
  • Write output to current stage file

Read the full file on GitHub · 222 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 · 222 lines · 49 tokens per session scan A cc5b51d083ee

Subscribe to this mod's changes

alive-agents is a cursor rule published in the GitHub repository with-geun/alive-analysis (41 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 2,521 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.