What is trader CLAUDE.md?

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.

Use them to develop, run, configure, test, or deploy the repository’s prediction-market agents.

They help an agent understand which settings and deployment paths apply to each trading service, avoiding incorrect local or production configuration.

How valory-xyz/trader configures Claude Code

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/valory-xyz/trader/claude-md/github.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/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" 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. 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.

Model	Per session	Once invoked
Fable 5.1	$0.03071	$0.03071
Opus 5.5	$0.01228	$0.01228
Sonnet 5.5	$0.00614	$0.00614
Haiku 4.5	$0.00307	$0.00307

Measured 2mo ago against content hash aa0399c10178, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

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.

2mo 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 (86 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,071 tokens to every session, about $0.0123 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.

Finance and fintech Web3 and blockchain olas prediction-market trading-agent valory

trader CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
trader CLAUDE.mdvalory-xyz/trader	Instructions file	86	yesterday	Apache-2.0	A	3,071	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	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	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

trader: Instructions file for Claude Code