trader: Instructions file for Claude Code

CLAUDE.md

trader CLAUDE.md is an instructions file for Claude Code from valory-xyz/trader. It costs 3,071 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Olas prediction-market trading agents that estimate event probabilities and place blockchain trades on Omen or Polymarket. They explain the services, chains, venues, configuration, and local development details.

In plain words
What is it for?
Use them to develop, run, configure, test, or deploy the repository’s prediction-market agents.
Why use it?
They help an agent understand which settings and deployment paths apply to each trading service, avoiding incorrect local or production configuration.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is valory-xyz/trader's own configuration. It tells Claude Code how to work on trader 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 trader configures →

Reuse

Borrowing it

Nothing to install: this file belongs to valory-xyz/trader. 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/valory-xyz/trader/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/valory-xyz/trader

Made for: Claude Code.

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 trader CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/valory-xyz/trader/claude-md.svg)](https://agentmods.dev/instructions/valory-xyz/trader/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/valory-xyz/trader/claude-md"><img src="https://agentmods.dev/badge/instructions/valory-xyz/trader/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,071 This file is loaded in full into every session.
When invoked 3,071 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03071 $0.03071
Opus 5 $0.01536 $0.01536
Sonnet 5 $0.00614 $0.00614
Haiku 4.5 $0.00307 $0.00307

Measured 6d ago against content hash aa0399c10178, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

trader CLAUDE.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 6d 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.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

The Trader repo hosts the Olas prediction-market agents. A single agent package (valory/trader) is shipped as two services:

Service Stack name Chain Venue
valory/trader_pearl Omenstrat Gnosis Omen
valory/polymarket_trader Polystrat Polygon Polymarket (CLOB v2)

Both run as single-agent (sovereign) deployments distributed via Pearl. The agent queries an AI Mech for probability estimates, evaluates profitability, and executes on-chain via a Safe multisig. Built on Open Autonomy (ABCI skills, FSMs, content-addressed packages); Tendermint is framework plumbing, not the deployment shape.

When working locally with make run-agent / aea-helpers run-agent, the agent-level aea-config.yaml defaults are Omen-flavored — service-level polymarket_trader/service.yaml overrides only apply under autonomy deploy. Local Polystrat dev requires explicit overrides (IS_RUNNING_ON_POLYMARKET=true, MECH_CHAIN_ID=polygon, DEFAULT_CHAIN_ID=polygon, pUSD-scaled STRATEGIES_KWARGS, the Polymarket TOOLS_ACCURACY_HASH, and the chain-specific market-filter flags). See README.md for the full set.

Tech Stack

  • Framework: Open Autonomy
  • Package management: uv (versions pinned in pyproject.toml — check there for the current Python range and dependencies; do not duplicate them here)
  • Task running: Makefile + tox
  • Lint / format: tomte (wraps black, isort, flake8, mypy, pylint, darglint, bandit)
  • Tests: pytest + hypothesis

Common Commands

Testing

# Run all skill tests (pick the env that matches your interpreter; 3.10–3.14 supported)
uv run tox -e py3.10-linux     # or py3.11/3.12/3.13/3.14-linux, *-darwin, etc.

# Run a single skill's tests
uv run pytest packages/valory/skills/<skill_name>/tests/ -v

# Run a specific test
uv run pytest packages/valory/skills/<skill_name>/tests/test_behaviours.py::TestClassName::test_method -v

Read the full file on GitHub · 224 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. 6d ago First seen · 224 lines · 3,071 tokens per session scan A aa0399c10178

Subscribe to this mod's changes

trader CLAUDE.md is an instructions file published in the GitHub repository valory-xyz/trader (77 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,071 tokens to every session, about $0.0154 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

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

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 · 5,182 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

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

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

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