runtime

A system that sends specialist sub-agents into stages of an ALIVE data-analysis workflow. Their results are saved in analysis files so the work can be reviewed in Git.

In plain words
What is it for?
Use it to run specialist checks automatically or on request, apply required safeguards, and merge their output into the current analysis stage.
Why use it?
It brings in targeted assistance when a stage needs it and keeps the resulting advice traceable.

Agent

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/with-geun/alive-analysis/runtime
Clone the repo
git clone --depth 1 https://github.com/with-geun/alive-analysis
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 1,014 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 $0.01014
Opus 5 $0.00000 $0.00507
Sonnet 5 $0.00000 $0.00203
Haiku 4.5 $0.00000 $0.00101

Measured 2d ago against content hash f7c42f86468f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runtime 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 2d 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.

core/agents/runtime.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sub-agent Runtime — Invocation, Merge & Logging Policy

alive-analysis v1.2+

Overview

The Sub-agent Dispatch System runs within the ALIVE loop to provide just-in-time specialist assistance. All agent output is written into the analysis markdown files for full Git traceability.


Invocation Flow

1. Trigger point

Sub-agents are invoked at two moments:

  • /analysis-next: after generating the new stage file (Step 4)
  • /analysis-agent: explicit user call, any time

2. Router evaluation (deterministic)

  1. Read .analysis/status.md + current stage file + user message
  2. Evaluate core/agents/router.yml gate conditions → identify gates to auto-run
  3. Evaluate routing rules → score all agents → filter by threshold → take top_k
  4. Check suppression: skip if same agent ran in this stage without content change
  5. Read user config from .analysis/agents.yml (falls back to core/config/agents.yml)

3. Gate execution (no user confirmation)

Required-gate agents run automatically when their signals fire:

[auto] Running scope-guard — Scope section empty detected
[auto] Running ethics-guard — PII keyword "이메일" detected

Output is merged into the current stage file immediately.

4. Recommendation block (optional agents)

After gates complete, show compact recommendation block (≤3 agents):

─────────────────────────────────────────
🤖 Specialist Recommendations — {STAGE}
─────────────────────────────────────────
  1. sql-writer      — 데이터소스 확인됨, 가설별 쿼리 초안 생성 가능
  2. stats-agent     — 가설 검증 중, 통계 검정 방법론 검토
  3. peer-reviewer   — 결과 도출 완료, 시니어 관점 검토
─────────────────────────────────────────
Run? (1 / 2 / 3 / all / n)  →

Ask at most one confirmation question. If ask_confirmation: false in config, run all recommendations automatically.

5. Agent execution

  • Claude Code: invoke agents as parallel sub-tasks using Agent tool when multiple selected
  • Cursor: each agent prompt is applied sequentially (Cursor background agent limitation)
  • Each agent reads its input_contract files, generates output, calls Write/Edit tool

Read the full file on GitHub · 125 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. 2d ago First seen · 125 lines · 0 tokens per session scan A f7c42f86468f

Subscribe to this mod's changes

runtime is an agent 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 1,014 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.

Related

Other agents, from other repositories

discussion-spec

작업일지가 무엇을 했나(회고), 플래너가 무엇을, 어디까지(결정 후 계획)라면, 문제 해결 문서(.oculpm/discussion/ /discussion.md)는 그 앞 단계 — "이게 문제인가? 어떤 안들이 있나?" 를 결정 전에 정리하는 회의록입니다.

bunhine0452/Ocul-PM · 0 tokens

_template

당신은 ocul-pm 추적 프로젝트에서 작업 중입니다. 하나의 논리적 작업 단위(버그 수정 / 기능 / 리팩토링 / 에러 사이클 / 잡일)를 끝낼 때마다 즉시 기록하세요 — 사용자에게 묻지 말 것.

bunhine0452/Ocul-PM · 0 tokens

shopify-app-ux-reviewer

Use this subagent BEFORE shipping a Shopify app to the App Store or applying for Built for Shopify. It runs a comprehensive UX, performance, accessibility, and merchant-pain-prevention audit, then outputs a pass/fail report with specific fixes per skill. Trigger when user says 'ux audit', 'pre-ship review', 'is this…

khadinakbarlabs/shopify-app-builder · 99 tokens

app-listing-copywriter

Use when preparing to submit a Shopify app to the App Store. Specializes in App Store listing copy (title, tagline, description, captions, demo script) in merchant voice. Route here to research competitors and draft submission-ready copy.

khadinakbarlabs/shopify-app-builder · 53 tokens

shopify-debugger

Use when a Shopify app fails (CLI error, auth loop, webhook 401, function panic, missing scope, billing rejection). Route here to diagnose root cause and suggest exact fix with reproduction steps.

khadinakbarlabs/shopify-app-builder · 45 tokens

shopify-app-architect

Use when starting a new Shopify app or designing a major feature. Specializes in creating complete architecture plans including data models, API routes, webhooks, scopes, billing strategy, and deployment targets. Route here for architecture approval workflows.

khadinakbarlabs/shopify-app-builder · 52 tokens