GEPA is a framework that improves text-based system parameters, such as prompts, code, agent designs, and configurations, by using language-model reflection and evolutionary search. Developers and researchers use it to test alternatives against evaluation metrics and refine systems from execution traces. Catalogue add-ons represent workflows for applying GEPA to coding-agent optimization.
Borrowing it
Nothing to install: this file belongs to gepa-ai/gepa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gepa-ai/gepa/main/AGENTS.mdgit clone --depth 1 https://github.com/gepa-ai/gepaWrote 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/instructions/gepa-ai/gepa/agents-md)<a href="https://agentmods.dev/instructions/gepa-ai/gepa/agents-md"><img src="https://agentmods.dev/badge/instructions/gepa-ai/gepa/agents-md/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.
<a href="https://agentmods.dev/instructions/gepa-ai/gepa/agents-md"><img src="https://agentmods.dev/badge/instructions/gepa-ai/gepa/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00447 | $0.00447 |
| Opus 5.5 | $0.00179 | $0.00179 |
| Sonnet 5.5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
gepa AGENTS.md 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.
What it actually says
GEPA
GEPA (Genetic-Pareto) is a Python framework for optimizing text components (AI prompts, code, instructions) using LLM-based reflection and Pareto-efficient evolutionary search.
Agent Skill
This repository ships an Agent Skill at .claude/skills/gepa-optimize-anything/. If you are a coding agent and the user wants to auto-optimize, tune, or search over any scorable text artifact (a prompt, program/code, config, regex/SQL, or agent scaffold) with gepa.optimize_anything, read .claude/skills/gepa-optimize-anything/SKILL.md first and follow it. It is auto-discovered by Claude Code and by other agents that read .claude/skills/ (Cursor, VS Code/Copilot, Codex, Gemini CLI). To install it standalone in another project: /plugin marketplace add gepa-ai/gepa then /plugin install gepa-optimize-anything@gepa.
Setup
We use uv for dependency management. The project uses setuptools as the build backend. All python executions must be done through uv.
uv sync --extra dev
Project Structure
src/gepa/— main package sourcecore/— optimization loop, state, evaluationproposer/— candidate proposal and mutation logicadapters/— integration adapters (DSPy, RAG, MCP, etc.)strategies/— batch sampling and candidate selectionlogging/— experiment tracking and logging
tests/— pytest test suitedocs/— mkdocs documentation site
Build & Test
uv run pytest
uv run ruff check src/
uv run ruff format src/
uv run pyright src/
Code Style
- Linter/formatter: ruff (line length 120, double quotes, space indent)
- Type checking: pyright
- Python target: 3.10+
- No relative imports (enforced by ruff)
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 · 43 lines · 447 tokens per session scan A 84777c6f7920
gepa AGENTS.md is an instructions file published in the GitHub repository gepa-ai/gepa (7,295 stars, last pushed 2d ago), licensed MIT. It adds 447 tokens to every session, about $0.0018 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 2026-08-30.
gepa AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gepa AGENTS.mdgepa-ai/gepa | Instructions file | 7.3k | 2d ago | MIT | A | 447 | Claude Code, Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |