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.
npx agentmods add instructions/djizus/agent-gmx/claude-mdgit clone --depth 1 https://github.com/djizus/agent-gmxWrote 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/djizus/agent-gmx/claude-md)<a href="https://agentmods.dev/instructions/djizus/agent-gmx/claude-md"><img src="https://agentmods.dev/badge/instructions/djizus/agent-gmx/claude-md.svg" alt="Measured on agentmods" 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 | $0.03055 | $0.03055 |
| Opus 5 | $0.01528 | $0.01528 |
| Sonnet 5 | $0.00611 | $0.00611 |
| Haiku 4.5 | $0.00305 | $0.00305 |
Grade A, and why
agent-gmx 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 327 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
Vega - An autonomous AI-powered trading agent for GMX perpetual futures on Arbitrum/Avalanche networks. Built with the Daydreams AI framework to implement aggressive, high-frequency scalping strategies with advanced risk management.
Key Commands
# Install dependencies
bun install
# Run the trading agent
bun run start
# or
bun run dev
# or directly
bun run agent-gmx.ts
# No build step needed - Bun handles TypeScript compilation
# No test framework implemented - TypeScript strict mode enforces code quality
# No lint commands defined
Architecture Overview
Core Components
-
agent-gmx.ts - Main entry point defining the "Vega" personality and agent configuration
- Implements aggressive scalping strategy
- Integrates with Daydreams AI framework
- Handles memory persistence and action orchestration
-
gmx-actions.ts - All trading actions and GMX SDK integration
- Each action follows consistent pattern: name, description, handler
- Actions include: portfolio queries, position management, order placement
- All outputs formatted as strings for AI comprehension
-
gmx-queries.ts - Market data abstraction layer
- Formats complex GMX data into AI-readable strings
- Provides: market info, positions, orders, trades, price feeds
- Cache-first approach with fallback to SDK
- Contains advanced Synth AI analysis with intelligent trading signals
-
gmx-utils.ts - Financial calculations and utilities
- BigInt-based precision for blockchain compatibility
- Position sizing, PnL calculations, liquidation prices
- Risk management calculations
-
gmx-cache.ts - High-performance caching system with promise deduplication
- Handles multi-level caching with 5-minute TTL for all GMX data types
- Prevents concurrent duplicate API calls
- Used by all query functions for optimal data access
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.
- 5d ago First seen · 327 lines · 3,055 tokens per session scan A 7f131b74d0d4
agent-gmx CLAUDE.md is an instructions file published in the GitHub repository djizus/agent-gmx (2 stars, last pushed 1y ago), licensed MIT. It adds 3,055 tokens to every session, about $0.0153 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 2026-08-31.
Other instructions, from other repositories
gmgn-skills CLAUDE.md
Claude Code instructions for GMGNAI/gmgn-skills, covering claude.md, critical rule — read this first, project overview, available skills and quick decision guide.
mercato-dapp AGENTS.md
Instructions for mercato-supply-chain/mercato-dapp, covering mercato — agent guide, quick facts, documentation map, domain glossary and user roles.
coingecko-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/coingecko-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
gensyn-delphi-skills CLAUDE.md
Instructions for gensyn-ai/gensyn-delphi-skills, a project described as: Skills for agents to view markets and place trades on Gensyn's Delphi prediction markets.
x402-stellar-kit CLAUDE.md
Claude Code instructions for CodeStrux/x402-stellar-kit, a project described as: x402 payment primitives for Stellar: intent binding, a deterministic policy engine, a pluggable approver, and an agent surface. Apache-2.0.
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).