prompt-evolver

prompt-evolver is an agent for coding agents from frankxai/claude-codex-gemini-opencode-settings. It costs 0 tokens per session (2,687 once invoked), scanned A, original, no licence file.

An agent for improving prompts through ongoing research and performance feedback. Prompts are the instructions given to AI systems.

In plain words
What is it for?
Use it to evolve AI prompts based on new research, measured performance, and emerging methods.
Why use it?
It helps address prompts that need refinement as research, results, or prompting techniques change.

Agent

Part of the prompt-library plugin — 1 skill, 10 commands, 4 agents shipped together

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/frankxai/claude-codex-gemini-opencode-settings/prompt-evolver
Clone the repo
git clone --depth 1 https://github.com/frankxai/claude-codex-gemini-opencode-settings

Or install prompt-library, the plugin that ships this one along with the rest of its 1 skill, 10 commands, 4 agents.

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 prompt-evolver

README.md
[![agentmods](https://agentmods.dev/badge/agents/frankxai/claude-codex-gemini-opencode-settings/prompt-evolver.svg)](https://agentmods.dev/agents/frankxai/claude-codex-gemini-opencode-settings/prompt-evolver)
Your own site
<a href="https://agentmods.dev/agents/frankxai/claude-codex-gemini-opencode-settings/prompt-evolver"><img src="https://agentmods.dev/badge/agents/frankxai/claude-codex-gemini-opencode-settings/prompt-evolver.svg" alt="Measured on agentmods" height="20"></a>
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 2,687 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.02687
Opus 5 $0.00000 $0.01344
Sonnet 5 $0.00000 $0.00537
Haiku 4.5 $0.00000 $0.00269

Measured 4d ago against content hash cef5326845cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prompt-evolver 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 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.

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.

claude/plugins/prompt-library/agents/prompt-evolver.md · 481 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 4d ago First seen · 481 lines · 0 tokens per session scan A cef5326845cb

Subscribe to this mod's changes

prompt-evolver is an agent published in the GitHub repository frankxai/claude-codex-gemini-opencode-settings (2 stars, last pushed 4mo ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 2,687 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 2026-08-31.

Related

Other agents, from other repositories

prompting.ru

← AI-агенты · Память · Безопасность → · 🇬🇧 English.

bestdeejay-design/awesome-ai-handbook · 0 tokens

prompting

Agent "prompting" from bestdeejay-design/awesome-ai-handbook, covering prompting for ai agents, 1. how agent prompting differs, 2. system prompt structure, role and tools.

bestdeejay-design/awesome-ai-handbook · 0 tokens

prompt-debugger

Evaluates why a prompt produced bad, unexpected, or suboptimal output and suggests targeted fixes. Use when a user says "my prompt isn't working", "this prompt gives bad results", "why is my prompt failing", "debug this prompt", "the AI keeps getting this wrong", "fix my prompt", "prompt not producing expected…

RadOrigin-LLC/RAD-Claude-Skills · 456 tokens

prompt-engineering-patterns

Design complex, production Optimize existing prompts for performance, consistency, and token efficiency.

bl1nk-bot/bl1nk-agents-manager · 22 tokens

prompts-guide

Interactive guide for using prompt-factory skill to generate mega-prompts. Helps choose from 69 presets or create custom prompts, select formats (XML/Claude/ChatGPT/Gemini), and explains usage. Use when user wants to generate production-ready prompts for any LLM.

alirezarezvani/claude-code-skill-factory · 60 tokens

marketing

You create assets that look like they were made by a designer who codes. One job: make ystack look real, credible, and worth starring. No AI slop. No stock photo energy. No generic gradients. No corporate speak.

Yasuui/ystack · 0 tokens