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/andiupn/andy-universal-agent-rules/agents-mdgit clone --depth 1 https://github.com/andiupn/andy-universal-agent-rulesWrote 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/andiupn/andy-universal-agent-rules/agents-md)<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>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 | $0.01414 | $0.01414 |
| Opus 5 | $0.00707 | $0.00707 |
| Sonnet 5 | $0.00283 | $0.00283 |
| Haiku 4.5 | $0.00141 | $0.00141 |
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.
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!)
๐ Project Overview
Project: [Your Project Name]
Purpose: [What this project does]
Stack: Auto-detected in .agent/context/environment.json
๐ ๏ธ Tech Stack & Environment
NOTE: Actual versions are auto-detected. Run
python .agent/scripts/detect-environment.pyto update.
Check your environment:
python .agent/scripts/detect-environment.py
cat .agent/context/environment.json
โก 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
๐ 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 |
๐ Workflow files:
.agent/workflows/
๐ง Supported Editors
| Editor | Status |
|---|---|
| VSCode + GitHub Copilot | โ |
| Cursor AI | โ |
| Kiro AI | โ |
| Windsurf Editor | โ |
| Antigravity (Gemini/Claude) | โ |
โ ๏ธ Critical Gotchas
Your knowledge base starts here! Add gotchas as you discover them.
Example Format:
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.
- 3d ago First seen ยท 250 lines ยท 1,414 tokens per session scan A 1566bc552cc6
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.
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.
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.
SoDam-WikiMate AGENTS.md
AGENTS.md instructions for sodam-ai/SoDam-WikiMate, covering wikimate ์์ ๊ท์น (ํฌ๋ก์คํด โ claude code ยท codex ยท gemini ๊ณต์ฉ), ๋ฌธ์ฒด, ์๋ ๋์ (์์ฐ์ด ํธ๋ฆฌ๊ฑฐ โ ๊ฐ์ ํธ์ถ ๋ถํ์), ์ ๊ทผ ๊ท์น (์๋ ๊ฐ์ง โ ํน์ ๋๊ตฌ์ ํ์ ํ์ง ์์) and obsidian ๊ท์น.
featherspec memory-bank.instructions.md
FeatherSpec Memory Bank writing rules (thin loader).
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๏ผๆฌไป็นๆ๏ผ้ป่ฎคๅๆฏๆฏ main๏ผ.
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 EVERYโฆ