alphaloop AGENTS.md

alphaloop AGENTS.md is an instructions file for Codex, OpenCode from realnaka/alphaloop. It costs 980 tokens per session, scanned A, original, MIT.

Project instructions for AlphaLoop, a suite of agent skills for investment research. It defines a workflow in which the agent gathers and checks evidence while a human keeps the final decision.

In plain words
What is it for?
Setting up AlphaLoop, loading its research skills, and guiding work on stocks, companies, industries, or research notes.
Why use it?
They give agents a consistent way to work on investment research without treating the agent's conclusions as automatic trading decisions.

Instructions file for CodexOpenCode

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/realnaka/alphaloop/agents-md
Clone the repo
git clone --depth 1 https://github.com/realnaka/alphaloop

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 alphaloop AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/realnaka/alphaloop/agents-md.svg)](https://agentmods.dev/instructions/realnaka/alphaloop/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/realnaka/alphaloop/agents-md"><img src="https://agentmods.dev/badge/instructions/realnaka/alphaloop/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 980 This file is loaded in full into every session.
When invoked 980 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 $0.00980 $0.00980
Opus 5 $0.00490 $0.00490
Sonnet 5 $0.00196 $0.00196
Haiku 4.5 $0.00098 $0.00098

Measured 4d ago against content hash 3206cda226bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

alphaloop 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 4d 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AlphaLoop — Agent Instructions

For AI agents reading this repo: this is a skill suite, not an application. It defines a human-agent collaboration operating model for investment research and bundles the six sub-skills it orchestrates.

What you are looking at

AlphaLoop is an operating model: the trader sets direction, the agent gathers and verifies evidence, and the human always keeps the decision. The full specification lives in SKILL.md. Read it before doing anything else.

This AGENTS.md exists so that agents following the AGENTS.md standard (OpenAI Codex, OpenCode, Hermes, OpenClaw, Aider, etc.) can discover and load the suite consistently.

Quick install (any agent)

git clone https://github.com/realnaka/alphaloop.git
cd alphaloop
./install.sh

The installer auto-detects which agents are present and symlinks the orchestrator plus every bundled sub-skill into each agent's skills directory. It also initializes an empty wiki at ${OPENORDER_HOME:-$HOME/openorder} (templates only, no real data).

How to use as an agent

Whenever a conversation enters an investment-research context (a ticker, a company, an industry, a forwarded research note or screenshot, a thesis to verify, a stock to pick, a trade to log):

  1. Treat any logic/claim the human hands you as a hypothesis (C-grade), not a fact. Verify before trusting. → see skills/claim-verification/SKILL.md
  2. First action when a ticker/industry/framework appears: read ${OPENORDER_HOME}/INDEX.md → relevant files. → skills/openorder/SKILL.md
  3. Always pull real-time prices with a timestamp + source; never use stale data. → skills/stock-data-fetch/SKILL.md
  4. For raw materials / chokepoint / export-control topics, run the five-layer funnel. → skills/strategic-materials/SKILL.md
  5. Hand back a verification matrix + stock list + risks; never pull the trigger for the user. The decision is always the human's.
  6. When a trade happens, log it with its source framework to close the feedback loop. → skills/trade-journal/SKILL.md
  7. If any tool fails (403/404/can't fetch), escalate the tool, not the user. → skills/agent-tool-escalation/SKILL.md

Read the full file on GitHub · 59 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. 4d ago First seen · 59 lines · 980 tokens per session scan A 3206cda226bc

Subscribe to this mod's changes

alphaloop AGENTS.md is an instructions file published in the GitHub repository realnaka/alphaloop (19 stars, last pushed 2mo ago), licensed MIT. It adds 980 tokens to every session, about $0.0049 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

apple-dev-skills AGENTS.md

AGENTS.md instructions for markdavidgan/apple-dev-skills, covering apple dev skills — agent guide (codex / kimi / cross-cli), quick reference, repository rules, project-local consumer convention and checkpoint compaction protocol.

markdavidgan/apple-dev-skills · 2,489 tokens

cukaimax-agent GEMINI.md

Gemini CLI instructions for jakzaizzat/cukaimax-agent: Use the cukaimax-tax-authority MCP server when the user asks about Malaysian individual income tax, Form BE, Form B, sole-proprietor records, deductible business expenses, tax reliefs, or HASiL source requirements.

jakzaizzat/cukaimax-agent · 192 tokens

skene-cookbook AGENTS.md

Instructions for SkeneTechnologies/skene-cookbook, covering agents.md, quick context, build & test commands, install dependencies and run tests (full suite).

SkeneTechnologies/skene-cookbook · 1,247 tokens

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

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

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