andy-universal-agent-rules AGENTS.md

andy-universal-agent-rules AGENTS.md is an instructions file for Codex, OpenCode from andiupn/andy-universal-agent-rules. It costs 1,414 tokens per session, scanned A, original, MIT.

Repository instructions for a reusable set of rules and scripts for coding agents. They describe the project setup, automatically detected technology stack, quick commands, and a small knowledge-base system.

In plain words
What is it for?
Use them when working on this repository, detecting its environment, managing stored knowledge, running the interactive agent command line, or following its documented workflows.
Why use it?
They give an agent consistent guidance for understanding the project and running its maintenance tools. They also document where to save, search, validate, and back up project knowledge.

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/andiupn/andy-universal-agent-rules/agents-md
Clone the repo
git clone --depth 1 https://github.com/andiupn/andy-universal-agent-rules

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 andy-universal-agent-rules AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/andiupn/andy-universal-agent-rules/agents-md.svg)](https://agentmods.dev/instructions/andiupn/andy-universal-agent-rules/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/andiupn/andy-universal-agent-rules/agents-md"><img src="https://agentmods.dev/badge/instructions/andiupn/andy-universal-agent-rules/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,414 This file is loaded in full into every session.
When invoked 1,414 The same file โ€” 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 $0.01414 $0.01414
Opus 5 $0.00707 $0.00707
Sonnet 5 $0.00283 $0.00283
Haiku 4.5 $0.00141 $0.00141

Measured 3d ago against content hash 1566bc552cc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

andy-universal-agent-rules AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured 3d 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 ยท 250 lines

How it starts

The opening of the file, as written. The whole thing โ€” 250 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

AI Agent Instructions for this project. Supported by GitHub Copilot, Cursor, Kiro, Windsurf, Antigravity.

Stats: 0 entries (start building your knowledge base!)


๐Ÿ“‹ Project Overview

Project: [Your Project Name]
Purpose: [What this project does]
Stack: Auto-detected in .agent/context/environment.json


๐Ÿ› ๏ธ Tech Stack & Environment

NOTE: Actual versions are auto-detected. Run python .agent/scripts/detect-environment.py to update.

Check your environment:

python .agent/scripts/detect-environment.py
cat .agent/context/environment.json

โšก Quick Commands

# Knowledge Management (Core Features)
python .agent/scripts/save-knowledge.py --category gotchas "Your gotcha here"
python .agent/scripts/search-knowledge.py "search term"
python .agent/scripts/validate-index.py --fix

# Backup & Environment
python .agent/scripts/backup-memory.py
python .agent/scripts/detect-environment.py

# Interactive CLI (Recommended - No Python needed!)
bash .agent/scripts/agent-cli.sh        # Linux/Mac
powershell .agent/scripts/agent-cli.ps1 # Windows

๐Ÿ”„ Workflows (AI-Powered)

Tell your AI assistant to run these workflows:

Workflow Command What It Does
Maintenance "Run maintenance workflow" Validate, backup, update environment
Save from Chat "Save learnings from this chat" Extract & save knowledge from session
Search "Search for [topic]" Find existing knowledge

๐Ÿ“ Workflow files: .agent/workflows/


๐Ÿ”ง Supported Editors

Editor Status
VSCode + GitHub Copilot โœ…
Cursor AI โœ…
Kiro AI โœ…
Windsurf Editor โœ…
Antigravity (Gemini/Claude) โœ…

โš ๏ธ Critical Gotchas

Your knowledge base starts here! Add gotchas as you discover them.

Example Format:

Read the full file on GitHub ยท 250 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. 3d ago First seen ยท 250 lines ยท 1,414 tokens per session scan A 1566bc552cc6

Subscribe to this mod's changes

andy-universal-agent-rules AGENTS.md is an instructions file published in the GitHub repository andiupn/andy-universal-agent-rules (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,414 tokens to every session, about $0.0071 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.

Related

Other instructions, from other repositories

plinth AGENTS.md

AGENTS.md instructions for jabrena/plinth, covering contributor quickstart guide, your role, tech stack, framework version baseline and internal scripts.

jabrena/plinth ยท 3,046 tokens

plinth CLAUDE.md

Claude Code instructions for jabrena/plinth, a project described as: Plinth is an AI-native engineering toolkit for modern Java enterprise SDLC, built around reusable Commands, Agents, Skills, and MCP Servers.

jabrena/plinth ยท 3 tokens

SoDam-WikiMate AGENTS.md

AGENTS.md instructions for sodam-ai/SoDam-WikiMate, covering wikimate ์ž‘์—… ๊ทœ์น™ (ํฌ๋กœ์Šคํˆด โ€” claude code ยท codex ยท gemini ๊ณต์šฉ), ๋ฌธ์ฒด, ์ž๋™ ๋™์ž‘ (์ž์—ฐ์–ด ํŠธ๋ฆฌ๊ฑฐ โ€” ๊ฐ•์ œ ํ˜ธ์ถœ ๋ถˆํ•„์š”), ์ ‘๊ทผ ๊ทœ์น™ (์ž๋™ ๊ฐ์ง€ โ€” ํŠน์ • ๋„๊ตฌ์— ํ•œ์ •ํ•˜์ง€ ์•Š์Œ) and obsidian ๊ทœ์น™.

sodam-ai/SoDam-WikiMate ยท 2,495 tokens

featherspec memory-bank.instructions.md

FeatherSpec Memory Bank writing rules (thin loader).

GregorBiswanger/featherspec ยท 91 tokens

soia-open-skills AGENTS.md

AGENTS.md instructions for soia-team/soia-open-skills, covering agents.md - soia-open-skills, repository purpose, safety rules, validation and git workflow๏ผˆๆœฌไป“็‰นๆœ‰๏ผš้ป˜่ฎคๅˆ†ๆ”ฏๆ˜ฏ main๏ผ‰.

soia-team/soia-open-skills ยท 1,325 tokens

github-copilot-token-optimization copilot-instructions.md

Copilot instructions for olivomarco/github-copilot-token-optimization: Terse like caveman. Technical substance exact. Only fluff die. Drop: articles, filler (just/really/basically), pleasantries, hedging. Fragments OK. Short synonyms. Code unchanged. Pattern: [thing] [action] [reason]. [next step]. ACTIVE EVERYโ€ฆ

olivomarco/github-copilot-token-optimization ยท 94 tokens