Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add samuelzxu/claude-evolve/plugin install claude-evolveWrote 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.
[](https://agentmods.dev/skills/samuelzxu/claude-evolve/evolve-install)<a href="https://agentmods.dev/skills/samuelzxu/claude-evolve/evolve-install"><img src="https://agentmods.dev/badge/skills/samuelzxu/claude-evolve/evolve-install.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00026 | $0.02678 |
| Opus 5 | $0.00013 | $0.01339 |
| Sonnet 5 | $0.00005 | $0.00536 |
| Haiku 4.5 | $0.00003 | $0.00268 |
Grade B, and why
evolve-install scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. Read the current `statusLine.command` from `~/.claude/settings.json` (or `$CLAUDE_CONFIG_DIR/settings.json`). Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Run the probe by inlining a short Python script that drives the MCP handshake. Use `Popen` + a deadline reader — do **not** use `subprocess.run(input=...)`, because closing stdin triggers FastMCP shutdown before the `too How it starts
The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-evolve Install
This is the setup command for claude-evolve. Run it once after installing the plugin to verify Python dependencies, create a virtual environment if needed, and confirm the MCP server is registered.
When this skill is invoked, immediately execute the workflow below. Do not only restate or summarize these instructions back to the user.
Flag Parsing
Check for flags in the user's invocation:
--help→ Show Help Text (below) and stop--force→ Skip Pre-Setup Check, run full setup from scratch--verify→ Only run the verification phase (Phase 4), skip install/env setup--local→ Install into a project-local.venv--global→ Use the system Python (no venv)- No flags → Auto-detect and run full setup if needed
Help Text
When user runs with --help, display this and stop:
claude-evolve Install - Set up evolutionary code discovery plugin
USAGE:
/evolve-install Install or verify (auto-detect)
/evolve-install --local Install into a project-local .venv
/evolve-install --global Use system Python (no venv)
/evolve-install --verify Only verify existing install
/evolve-install --force Force full reinstall
/evolve-install --help Show this help
PHASES:
1. Python check Verify Python >= 3.10 is available
2. Environment setup Create venv (if --local or auto) and install claude-evolve
3. Claude CLI check Verify `claude` is on PATH and authenticated
4. MCP verification Confirm claude-evolve MCP server registers and exposes tools
5. Smoke test Run a trivial claude call to confirm the bridge works
NEXT STEPS:
After install completes, run `/evolve-interview` to define your first
evolution task, or `/evolve` if you already have initial.py + evaluate.py.
Pre-Setup Check: Already Installed?
Before doing anything else, check if the plugin is already installed and working. Read the state file:
CLAUDE_EVOLVE_STATE="${CLAUDE_PLUGIN_ROOT:-.}/state/install-state.json"
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.
- 4d ago First seen · 299 lines · 26 tokens per session scan B 06c7ee544190
evolve-install is a skill published in the GitHub repository samuelzxu/claude-evolve (16 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 2,678 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…