darwinia: Instructions file for Codex

AGENTS.md

darwinia AGENTS.md is an instructions file for Codex, OpenCode from 0xSanei/darwinia. It costs 1,018 tokens per session, scanned A, original, MIT.

A set of instructions for AI agents working with Darwinia, an evolutionary trading system where computer-generated strategies compete on market data and change over generations.

In plain words
What is it for?
Use it to install Darwinia, run strategy evolution, test a selected champion against attacks, open its dashboard, and run the test suite.
Why use it?
It explains the project’s structure, commands, and tests so an agent can work with the codebase without guessing how its trading experiments are organized.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; built for openclaw.

This is 0xSanei/darwinia's own configuration. It tells Codex and OpenCode how to work on darwinia itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything darwinia configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 0xSanei/darwinia. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/0xSanei/darwinia/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/0xSanei/darwinia

Made for: Codex, OpenCode.

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 darwinia AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/0xsanei/darwinia/agents-md.svg)](https://agentmods.dev/instructions/0xsanei/darwinia/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/0xsanei/darwinia/agents-md"><img src="https://agentmods.dev/badge/instructions/0xsanei/darwinia/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,018 This file is loaded in full into every session.
When invoked 1,018 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01018 $0.01018
Opus 5 $0.00509 $0.00509
Sonnet 5 $0.00204 $0.00204
Haiku 4.5 $0.00102 $0.00102

Measured 8d ago against content hash 2705b884a973, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

darwinia 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 8d 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.

AGENTS.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Darwinia — Instructions for AI Agents

This file tells AI agents (Claude Code, Cursor, OpenClaw, etc.) how to use Darwinia.

What Is Darwinia?

An evolutionary trading agent ecosystem. You don't write strategies — you evolve them. Agents with 17-gene DNA compete on real market data, face adversarial attacks, and only the fittest survive to breed.

Quick Commands

# Install
pip install -e ".[dev]"

# Run evolution (default: 50 gens, 50 agents, BTC 1h data)
python -m darwinia evolve

# Custom evolution
python -m darwinia evolve -g 100 -p 80 --arena-start 10

# Test a specific champion against attacks
python -m darwinia arena -c output/champions/champion_gen_0049.json -r 10

# Launch visualization dashboard
python -m darwinia dashboard

# Run tests
pytest tests/ -v

Key Files

Path Purpose
darwinia/core/dna.py 17-gene DNA definition + crossover/mutation
darwinia/core/agent.py Trading agent that interprets DNA into decisions
darwinia/core/market.py Market data loader (CSV)
darwinia/evolution/engine.py Main evolution loop orchestrator
darwinia/evolution/fitness.py Composite fitness scoring (Sharpe, drawdown, win rate)
darwinia/evolution/population.py Selection + breeding
darwinia/arena/adversary.py 6 attack types targeting agent weaknesses
darwinia/arena/arena.py Arena runner, survival scoring
darwinia/discovery/analyzer.py Gene convergence + correlation analysis
darwinia/chronicle/recorder.py JSON snapshot recorder
darwinia/chronicle/speciation.py K-means species clustering
darwinia/__main__.py CLI entry point
data/btc_1h.csv 10,946 BTC/USDT 1h candles (2024-01 to 2025-04)

Common Tasks

"Evolve a trading strategy for BTC"

python -m darwinia evolve -g 50
# Results in output/champions/ and output/evolution_summary.json

"What patterns did the agents discover?"

# After evolution, check:
cat output/final_report.json | python -m json.tool | grep -A5 "patterns_discovered"

Read the full file on GitHub · 112 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. 8d ago First seen · 112 lines · 1,018 tokens per session scan A 2705b884a973

Subscribe to this mod's changes

darwinia AGENTS.md is an instructions file published in the GitHub repository 0xSanei/darwinia (87 stars, last pushed 4mo ago), licensed MIT. It adds 1,018 tokens to every session, about $0.0051 per session on Opus 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens