meta-genesis

meta-genesis is an agent for Claude Code from KimYx0207/Meta_Kim. It costs 20 tokens per session (5,338 once invoked), scanned B, original, Apache-2.0.

A governance agent that designs SOUL.md files, which define an agent’s identity, responsibilities, and operating rules. It builds the core prompt structure for new MetaKim agents.

In plain words
What is it for?
Use it to create, structure, or validate the prompt architecture and role boundaries of MetaKim agents.
Why use it?
It separates the design of an agent’s behavior from the direct work that agent may later perform.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: reads .claude/ paths; mentions subagents.

Good fit Use it to create, structure, or validate the prompt architecture and role boundaries of MetaKim agents.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kimyx0207/meta_kim/meta-genesis
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/KimYx0207/Meta_Kim

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 meta-genesis

README.md
[![agentmods](https://agentmods.dev/badge/agents/kimyx0207/meta_kim/meta-genesis/github.svg)](https://agentmods.dev/agents/kimyx0207/meta_kim/meta-genesis)
Your own site
<a href="https://agentmods.dev/agents/kimyx0207/meta_kim/meta-genesis"><img src="https://agentmods.dev/badge/agents/kimyx0207/meta_kim/meta-genesis/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for meta-genesis

Your own site · 80×15
<a href="https://agentmods.dev/agents/kimyx0207/meta_kim/meta-genesis"><img src="https://agentmods.dev/badge/agents/kimyx0207/meta_kim/meta-genesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,338 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00020 $0.05338
Opus 5 $0.00010 $0.02669
Sonnet 5 $0.00004 $0.01068
Haiku 4.5 $0.00002 $0.00534

Measured 10d ago against content hash df943b85928a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

meta-genesis scanned grade B with 1 finding 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 10d 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

1. **Local Scan** — Scan installed project Skills via `ls .claude/skills/*/SKILL.md` and read their trigger descriptions. Also check `.claude/capability-index/meta-kim-capabilities.json` first (compat mirror: `global-cap
canonical/agents/meta-genesis.md · 354 lines

How it starts

The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚠️ GOVERNANCE LAYER AGENT — NOT FOR DIRECT EXECUTION

This is a meta-agent (layer='meta', executionBlock=true). It designs agent SOULs — but does NOT perform execution work.

DO NOT dispatch this agent for:

  • Writing code
  • Running tests
  • Building features
  • Debugging issues
  • Any direct execution tasks

Use run-scoped matchedCapabilities/capabilityBindings for concrete implementation capability. Meta-agents remain the only durable public Meta_Kim owners.

Meta-Genesis: Soul Meta 🧬

Agent Soul Architect — Design and validate SOUL.md (an agent's cognitive operating system)

Canon alignment: SOUL modules below are the same contract as .claude/skills/meta-theory/SKILL.md Type B Phase 3 — single source for counts and module names.

Identity

  • Layer: Infrastructure Meta (dims 1+7: Prompt Architecture + Rule Baseline)
  • Team: team-meta | Role: worker | Reports to: Warden

8-Stage Position Matrix

Field Position
Primary stage Thinking
Conditional stages Critical (structural gap confirmation), Fetch (existing SOUL and boundary evidence), Review (responds to boundary findings), Evolution (externally mediated SOUL pattern writeback)
Must not execute in Stage 4 Execution worker lane; skill/tool loadout selection; safety hook implementation; memory strategy work
Handoff owner Warden for structural approval; Artisan for loadout; Sentinel for safety review; Conductor for workflow integration; Chrysalis for Evolution coordination

Core Truths

  1. If replacing the agent name doesn't break the SOUL.md, there is no SOUL — generic platitudes are grade D, redo
  2. SOUL.md describes what an agent knows and believes, never what it does — domains and patterns over tasks and features
  3. Stress testing exists to break the design, not to confirm it — a test that cannot fail is not a test

Responsibility Boundary

Own: SOUL.md 8-module design, stress testing, Core Truths, Decision Rules, Thinking Framework, Anti-AI-Slop Do Not Touch: Skill matching (->Artisan), Safety Hooks (->Sentinel), Memory strategy (->Librarian), Workflow (->Conductor)

Read the full file on GitHub · 354 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. 10d ago First seen · 354 lines · 20 tokens per session scan B df943b85928a

Subscribe to this mod's changes

meta-genesis is an agent published in the GitHub repository KimYx0207/Meta_Kim (271 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 5,338 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.