An autonomous code-optimization workflow that generates and evaluates program variations over multiple generations.

Use it with a seed program and evaluator script to explore mutations, patches, and crossovers and return the best result.

It automates repeated experiments so the best-performing version can be selected according to an evaluator’s metrics and correctness checks.

evolve — Skill for Claude Code by samuelzxu/claude-evolve

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.

Any agent

npx skills add samuelzxu/claude-evolve --skill evolve

Clone the repo

git clone --depth 1 https://github.com/samuelzxu/claude-evolve

Made for: Claude Code.

Or install claude-evolve, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/samuelzxu/claude-evolve/evolve/github.svg)](https://agentmods.dev/skills/samuelzxu/claude-evolve/evolve)

Your own site

<a href="https://agentmods.dev/skills/samuelzxu/claude-evolve/evolve"><img src="https://agentmods.dev/badge/skills/samuelzxu/claude-evolve/evolve/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/samuelzxu/claude-evolve/evolve"><img src="https://agentmods.dev/badge/skills/samuelzxu/claude-evolve/evolve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 208 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00010	$0.00208
Opus 5.5	$0.00004	$0.00083
Sonnet 5.5	$0.00002	$0.00042
Haiku 4.5	$0.00001	$0.00021

Measured 2mo ago against content hash d986fd32a540, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evolve 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 2mo 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.

skills/evolve/SKILL.md · 32 lines

What it actually says

Launch an evolution run that optimizes code using Claude Code models as mutation operators.

Usage

/evolve [config.json]
/evolve --init initial.py --eval evaluate.py --generations 50

Requirements

initial.py: Seed program with # EVOLVE-BLOCK-START / # EVOLVE-BLOCK-END markers
evaluate.py: Evaluator script that returns metrics and correctness

What Happens

Loads the initial program and evaluator
Runs N generations of evolutionary optimization:
- Selects parent programs from island populations
- Queries Claude models (via UCB1 bandit) to generate mutations
- Applies diff/full/crossover patches
- Evaluates fitness via the user's evaluator script
- Updates the archive of best solutions
Returns the best-performing solution

The run is autonomous -- it proceeds without interaction until complete or stopped.

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.

2mo ago First seen · 32 lines · 10 tokens per session scan A d986fd32a540

Subscribe to this mod's changes

evolve is a skill published in the GitHub repository samuelzxu/claude-evolve (17 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 208 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-01.

Analytics and metrics Building agents

evolve next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
evolvesamuelzxu/claude-evolve	Skill	17	4mo ago	MIT	A	10	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code