Borrowing it
Nothing to install: this file belongs to mfmezger/ai_agent_dotfiles. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mfmezger/ai_agent_dotfiles/main/AGENTS.mdgit clone --depth 1 https://github.com/mfmezger/ai_agent_dotfilesWrote 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/mfmezger/ai_agent_dotfiles/agents-md)<a href="https://agentmods.dev/instructions/mfmezger/ai_agent_dotfiles/agents-md"><img src="https://agentmods.dev/badge/instructions/mfmezger/ai_agent_dotfiles/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.
<a href="https://agentmods.dev/instructions/mfmezger/ai_agent_dotfiles/agents-md"><img src="https://agentmods.dev/badge/instructions/mfmezger/ai_agent_dotfiles/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01579 | $0.01579 |
| Opus 5.5 | $0.00632 | $0.00632 |
| Sonnet 5.5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade C, and why
ai_agent_dotfiles AGENTS.md scanned grade C with 2 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- GNU Stow (macOS: `brew install stow`, Linux: `sudo apt install stow`) Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/settings.json | python -m json.tool How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Dotfiles - Agent Guidelines
This is a dotfiles repository for AI coding tools (Claude Code, OpenCode, Codex CLI, Gemini CLI), not a software project with build/test artifacts.
Installation & Setup
Installation Commands
# Full installation (runs install.sh)
./install.sh
# Manual installation using stow
stow claude # Install Claude Code configs to ~/.claude/
stow opencode # Install OpenCode configs to ~/.config/opencode/
stow codex # Install Codex CLI configs to ~/.codex/
stow gemini # Install Gemini CLI configs to ~/.gemini/
# Update symlinks after adding new files
stow -R claude opencode codex gemini
# Unlink configs
stow -D claude opencode codex gemini
Prerequisites
- GNU Stow (macOS:
brew install stow, Linux:sudo apt install stow) - Bash for install.sh script
Code Style Guidelines
Shell Scripts (install.sh)
- Shebang:
#!/usr/bin/env bash - Use
set -efor error handling - Color output using ANSI codes (RED, GREEN, YELLOW, BLUE, NC)
- Function naming:
lowercase_with_underscores - Indentation: 2 spaces
- Quotes around all variable expansions:
"$variable" - Use
[[for tests instead of[ - Exit on errors: functions return non-zero to indicate failure
Configuration Files (JSON, Markdown)
- JSON: 2-space indentation, no trailing commas
- Markdown: Use GitHub Flavored Markdown, line length ~80-100 chars
- Paths in comments use absolute paths starting with
~for user home - Code blocks specify language for syntax highlighting
Project-Specific Conventions
Directory Structure
claude/.claude/
├── settings.json # User preferences
├── CLAUDE.md # User-level context
├── agents/ # Custom agents (.md files)
├── skills/ # Skills (directories with SKILL.md)
└── rules/ # User-level rules (.md files)
opencode/.config/opencode/
├── AGENTS.md # User-level context
├── opencode.json # Main config with permissions
├── agents/ # Custom agents (.md files)
├── skills/ # Skills (directories with SKILL.md)
├── rules/ # Custom rules (.md files)
└── README.md # Config documentation
codex/.codex/
├── AGENTS.md # User-level context
├── rules/ # Codex rules / permissions
└── skills/ # Skills (directories with SKILL.md)
gemini/.gemini/
├── GEMINI.md # User-level context
├── skills/ # Symlinks to shared skills
└── commands/ # Custom command files (.md)
pi/.pi/agent/
├── AGENTS.md # User-level context
├── settings.json # pi settings
└── themes/ # Custom pi themes
shared/
├── context/
│ └── default-coding-guidelines.md # Canonical shared context source
└── skills/
└── <skill>/... # Canonical skill source for all tools
scripts/
├── sync-contexts.sh # Syncs generated global context files across tools
└── sync-skills.sh # Syncs per-tool skill symlinks and Gemini commands
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.
- 1mo ago First seen · 193 lines · 1,579 tokens per session scan C 321e37556ff5
ai_agent_dotfiles AGENTS.md is an instructions file published in the GitHub repository mfmezger/ai_agent_dotfiles (7 stars, last pushed 3mo ago), licensed MIT. It adds 1,579 tokens to every session, about $0.0063 per session on Opus 5.5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.