genesis-evolution

genesis-evolution is a skill for Claude Code, Codex from Xiaoher-C/agentbnb. It costs 4 tokens per session (608 once invoked), scanned A, original, MIT.

A self-improvement process for evaluating whether an agent's skills, pricing, or templates should change. It uses a hypothesis, an experiment, measurements, and a decision to keep or undo the change.

In plain words
What is it for?
Use it to review recent performance, propose low-risk improvements, run them for several evaluation cycles, and record whether they helped.
Why use it?
It provides a repeatable way to test improvements against observed results instead of changing the system based only on guesses.

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/xiaoher-c/agentbnb/genesis-evolution
Any agent
npx skills add Xiaoher-C/agentbnb --skill genesis-evolution
Clone the repo
git clone --depth 1 https://github.com/Xiaoher-C/agentbnb

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 genesis-evolution

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaoher-c/agentbnb/genesis-evolution.svg)](https://agentmods.dev/skills/xiaoher-c/agentbnb/genesis-evolution)
Your own site
<a href="https://agentmods.dev/skills/xiaoher-c/agentbnb/genesis-evolution"><img src="https://agentmods.dev/badge/skills/xiaoher-c/agentbnb/genesis-evolution.svg" alt="Measured on agentmods" height="20"></a>
Per session 4 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00004 $0.00608
Opus 5 $0.00002 $0.00304
Sonnet 5 $0.00001 $0.00122
Haiku 4.5 $0.00000 $0.00061

Measured 5d ago against content hash 4d1a232aef53, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

genesis-evolution scanned grade A 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST https://hub.agentbnb.dev/api/evolution/publish \
packages/genesis-template/skills/genesis-evolution/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Genesis Evolution — Self-Improvement Engine

Purpose

Periodically evaluate whether the agent can evolve — improve skills, adjust pricing, or publish template updates. Uses the autoresearch pattern: hypothesis → experiment → measure → keep or revert.

Procedure

  1. Pull recent PulseReports from memory:

    memory_recall "genesis pulse fitness_score" --category patterns --limit 10
    
  2. Calculate fitness trend (improving, stable, declining)

  3. Pull self-optimization records:

    memory_recall "skill optimization adjustment improvement" --category patterns --limit 20
    
  4. Generate evolution candidates:

    [
      {
        "type": "skill_improvement",
        "description": "Improve code-execution routing — currently sending simple tasks to Layer 2",
        "evidence": ["3 Layer 2 calls in 7 days were for tasks Layer 1 could handle"],
        "expected_fitness_delta": 0.06,
        "risk": "low"
      }
    ]
    
  5. For each low-risk candidate with expected_fitness_delta > 0.05:

    • Create experiment (track in memory)
    • Apply the change
    • Run for 3 heartbeat cycles
    • Compare fitness_score before vs after
    • If improved → KEEP. Record: "Evolution G{n}: {description} → fitness +{delta}"
    • If worse or equal → REVERT. Record: "Evolution G{n}: {description} → REVERTED"
  6. If evolution was kept, publish to AgentBnB Evolution ledger:

    curl -s -X POST https://hub.agentbnb.dev/api/evolution/publish \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer $(agentbnb config get token)" \
      -d '{
        "template_version": "{new_generation}.0.0",
        "changelog": "{description of improvement}",
        "core_memory_snapshot": [...top 5 memories by importance...],
        "fitness_improvement": {delta}
      }'
    
  7. After publishing, check if there is a newer template from the network:

    curl -s "https://hub.agentbnb.dev/api/evolution/latest" | jq '.template_version, .core_memory_snapshot'
    

    Merge any new core_memory_snapshot entries that are more important than your existing ones.

Read the full file on GitHub · 75 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. 5d ago First seen · 75 lines · 4 tokens per session scan A 4d1a232aef53

Subscribe to this mod's changes

genesis-evolution is a skill published in the GitHub repository Xiaoher-C/agentbnb (32 stars, last pushed 2mo ago), licensed MIT. It adds 4 tokens to every session and 608 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

nsauditor-ai

Use this skill whenever the user wants network security scanning, auditing, vulnerability assessment, host reconnaissance, or cloud-account security/compliance auditing with NSAuditor AI (via the nsauditor-ai MCP server: scanhost, scancloud, getfindings, probeservice, getvulnerabilities, listplugins). Triggers include…

nsasoft/nsauditor-ai-agent-skill · 248 tokens

shiplog

Git-as-knowledge-graph workflow for traceability. Use when planning work, brainstorming designs, creating/managing issues and PRs, tracking architectural decisions, or resuming prior sessions. Slash command /shiplog.

devallibus/shiplog · 46 tokens

data-charts-tako

Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.

gooseworks-ai/goose-skills · 35 tokens

apollo-lead-finder

Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.

gooseworks-ai/goose-skills · 51 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens

browse-and-evaluate

Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.

MoizIbnYousaf/Ai-Agent-Skills · 43 tokens