agentmods.dev

aktools-pro AGENTS.md

A set of AGENTS.md instructions for developing the aktools-pro repository, a Python server that provides financial data tools to agents. It defines project structure, development procedures, and how different coding agents should work together.

In plain words
What is it for?
Use it when working on aktools-pro with Codex, Copilot, Claude Code, or OpenCode, especially for changes to its Python server, financial-data tools, caching, and documentation.
Why use it?
It gives coding agents repository-specific rules so they can make changes consistently with the project’s architecture and coding standards.

Instructions file for CodexOpenCode

5 7mo ago A scan 1,619 tokens fork MIT
View the source file tchivs/aktools-pro
Install

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.

agentmods
npx agentmods add instructions/tchivs/aktools-pro/agents-md
Clone the repo
git clone --depth 1 https://github.com/tchivs/aktools-pro

Made for: Codex, OpenCode.

Per session 1,619 This file is loaded in full into every session.
When invoked 1,619 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin fork From a forked repository.
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 $0.01619 $0.01619
Opus 5 $0.00809 $0.00809
Sonnet 5 $0.00324 $0.00324
Haiku 4.5 $0.00162 $0.00162

Measured 2d ago against content hash a7fc904e9a49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aktools-pro 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 2d 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 · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Cross-Agent Development Guide

This document defines the Standard Operating Procedures (SOPs) for Agentic assistants (OpenCode Sisyphus, Claude Code, and Codex/Copilot) operating in the aktools-pro repository.

🤖 Multi-Agent Compatibility Protocol

Agent Source of Truth Primary Behavior
OpenCode (Sisyphus) AGENTS.md Follow Phase-based SOPs
Claude Code MCP Tool Metadata Update @mcp.tool descriptions
Codex / Copilot .cursorrules & Types Strict adherence to PEP 8 and Type Hints

🎯 Role & Mission

You are Sisyphus, a senior engineer orchestrating financial data tools. Your mission is to maintain a high-quality MCP server that bridges the gap between raw financial data and AI reasoning.

🏗 Project Architecture

  • Framework: FastMCP (Python-based).
  • Structure:
    • mcp_aktools/server.py: MCP server instance
    • mcp_aktools/__init__.py: Main entry point with CLI
    • mcp_aktools/cache.py: Dual-layer caching (Memory + Disk)
    • mcp_aktools/shared/: Shared utilities, constants, fields
    • mcp_aktools/tools/: Tool implementations
      • stocks.py: Stock-related tools
      • crypto.py: Cryptocurrency tools
      • market.py: Market data tools
      • portfolio.py: Portfolio management
      • analysis.py: Analysis & visualization tools
    • mcp_aktools/resources.py: MCP resources
    • mcp_aktools/prompts.py: MCP prompts
    • tests/: Test suite

🛠 Standard Operating Procedures (SOPs)

Phase 1: Intent Gate & Assessment

Before any implementation, classify the task to select the right approach:

  • Quick: Typo fixes, simple field additions to existing tools.
  • Ultrabrain: Complex strategy implementation, backtesting logic, or multi-step financial reasoning.
  • Visual Engineering: Improving draw_ascii_chart or Markdown output formatting.

Phase 2: Exploration & Research

  • Internal: Use file search and code reading to find existing @mcp.tool patterns.
  • External: Check akshare documentation if a specific financial indicator is missing.
  • Pattern: Proactively check skill://trading/logic/technical-analysis resource for existing SOPs before calculating new indicators.

Read the full file on GitHub · 144 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. 2d ago First seen · 144 lines · 1,619 tokens per session scan A a7fc904e9a49

Subscribe to this mod's changes

aktools-pro AGENTS.md is an instructions file published in the GitHub repository tchivs/aktools-pro (5 stars, last pushed 7mo ago), licensed MIT. It adds 1,619 tokens to every session, about $0.0081 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.

LanguagesPlanningWriting and docsai-agentaksharebacktestingclaude-codecryptocurrencyfinancial-data
Related

Other instructions, from other repositories

backtrader AGENTS.md

AGENTS.md instructions for cloudQuant/backtrader, covering agents.md, project overview, branch context, implementation status / reality checks and development commands.

cloudQuant/backtrader · 3,824 tokens

backtrader CLAUDE.md

Claude Code instructions for cloudQuant/backtrader, covering claude.md, project overview, branch context, implementation status / reality checks and development commands.

cloudQuant/backtrader · 3,448 tokens

ashare-ai-analyst CLAUDE.md

Instructions for Jcstack/ashare-ai-analyst, covering claude.md, project, stack, architecture and setup.

Jcstack/ashare-ai-analyst · 966 tokens

jesse AGENTS.md

Instructions for jesse-ai/jesse, covering jesse repository guide for ai agents, skills, key characteristics, central framework and technology stack.

jesse-ai/jesse · 2,749 tokens

Get-Started-with-Web3 AGENTS.md

Instructions for beihaili/Get-Started-with-Web3, covering get started with web3 agent notes, 项目定位, ceo 运营目标, 常用命令 and ai-native 内容层.

beihaili/Get-Started-with-Web3 · 4,297 tokens

awesome-quant AGENTS.md

AGENTS.md instructions for wilsonfreitas/awesome-quant, covering agents.md, project overview, architecture, commands and install deps (requires python 3.11+).

wilsonfreitas/awesome-quant · 1,367 tokens