greedy: Instructions file for Codex

AGENTS.md

greedy AGENTS.md is an instructions file for Codex, OpenCode from antonygiomarxdev/greedy. It costs 1,066 tokens per session, scanned A, original, MIT.

A set of instructions for Greedy, a local trading engine that runs trading bots and exposes their state and controls to AI agents through MCP, a standard tool-connection protocol.

In plain words
What is it for?
Use it when developing, operating, or connecting AI agents to Greedy's exchange-trading bots and MCP tools.
Why use it?
It documents how prices, orders, rate limits, duplicate-order protection, and saved bot state work, making the system's operating rules easier to follow.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is antonygiomarxdev/greedy's own configuration. It tells Codex and OpenCode how to work on greedy 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 greedy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to antonygiomarxdev/greedy. 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/antonygiomarxdev/greedy/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/antonygiomarxdev/greedy

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 greedy AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/antonygiomarxdev/greedy/agents-md/github.svg)](https://agentmods.dev/instructions/antonygiomarxdev/greedy/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/antonygiomarxdev/greedy/agents-md"><img src="https://agentmods.dev/badge/instructions/antonygiomarxdev/greedy/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.

agentmods 80×15 button for greedy AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/antonygiomarxdev/greedy/agents-md"><img src="https://agentmods.dev/badge/instructions/antonygiomarxdev/greedy/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,066 This file is loaded in full into every session.
When invoked 1,066 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 $0.01066 $0.01066
Opus 5.5 $0.00426 $0.00426
Sonnet 5.5 $0.00213 $0.00213
Haiku 4.5 $0.00107 $0.00107

Measured 2mo ago against content hash 0cd68637b41b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

greedy 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.

AGENTS.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Context for Greedy

Sovereign, local-first algorithmic trading engine. Single static binary. AI-native via MCP.

Architecture

CLI (greedy serve) → daemon with exchange registry + supervisor + MCP server
MCP Server (stdio)  → AI agents control bots via 14 tools, 4 resources, 3 prompts
  • One process: greedy serve. Daemon + MCP share registry and supervisor.
  • Bots run autonomously in goroutines. AI controls them via MCP tools.
  • All state persists to SQLite (~/.greedy/greedy.db).

Stream Layer

When greedy serve runs:

  • PriceStreamer: One fetch goroutine per symbol, shared across all bots. Lock-free atomic cache. 100ms interval.
  • MarketTracker: Ring buffer per symbol with Δ% tracking. Circuit breaker activates if price moves >5% in 30s (cooldown 60s).
  • Debouncer: Per-bot rate limiting. Default 5s cooldown, max 10 orders/30s. Configurable per strategy.
  • Idempotency: ClientOrderID write-ahead reservation prevents duplicate orders on retry. Format: {botID}-{unixMilli}-{seq}.

MCP Tools (14 total)

Tool Exchange param Description
get_ticker ✅ Current price
get_order_book ✅ Order book depth
get_candles ✅ OHLCV history
place_order ✅ Market/limit orders
cancel_order ✅ Cancel by order ID
get_positions ✅ Positions + P&L
get_balances ✅ Account balances
get_order_history ❌ Query filled orders
start_bot ❌ Launch bot (YAML or inline)
stop_bot ❌ Stop running bot
list_bots ❌ Active bots + P&L
set_credential ❌ Store API keys
list_credentials ❌ List stored keys
delete_credential ❌ Remove stored keys

Default exchange is paper when exchange is omitted.

MCP Resources

URI Description
portfolio://summary Full portfolio snapshot: balances, positions, total P&L
bot://{id}/status Bot status, strategy config, P&L, open orders
bot://{id}/history Complete order history for a bot
market://prices/{symbol} Real-time price for any symbol

Read the full file on GitHub · 116 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. 2mo ago First seen · 116 lines · 1,066 tokens per session scan A 0cd68637b41b

Subscribe to this mod's changes

greedy AGENTS.md is an instructions file published in the GitHub repository antonygiomarxdev/greedy (3 stars, last pushed 2mo ago), licensed MIT. It adds 1,066 tokens to every session, about $0.0043 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 2026-08-31.

Related

greedy AGENTS.md compared with instructions from other repositories

greedy AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
greedy AGENTS.mdantonygiomarxdev/greedyInstructions file32mo agoMITA1,066Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot