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/ulises-jeremias/dotfiles/agents-mdgit clone --depth 1 https://github.com/ulises-jeremias/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/ulises-jeremias/dotfiles/agents-md)<a href="https://agentmods.dev/instructions/ulises-jeremias/dotfiles/agents-md"><img src="https://agentmods.dev/badge/instructions/ulises-jeremias/dotfiles/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 5.1 | $0.00780 | $0.00780 |
| Opus 5 | $0.00390 | $0.00390 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
dotfiles 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 6d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Guidelines for HorneroConfig
For AI coding assistants and automated tools
Last Updated: 2026-02-27
Purpose
This is the authoritative guide for AI agents working on HorneroConfig. Follow the Hornero Bird philosophy: build robust, functional, adaptable, beautiful, and modular environments.
Quick Reference
Core Principles (The Hornero Way)
- Theme-Adaptive - All visuals adapt to any color palette automatically
- Modular - Components work independently yet integrate seamlessly
- Single Source of Truth - Configuration flows from centralized sources
- Graceful Degradation - Function even with missing dependencies
- Security by Default - Never commit secrets, validate all inputs
See Architecture Philosophy for detailed principles.
Essential Standards
Scripts Must:
- Use EasyOptions for CLI parsing
- Include
set -euo pipefail - Follow naming:
dots-*for user scripts,snake_casefor functions/vars - Handle errors gracefully with logging
- Work without optional dependencies (fallbacks required)
See Development Standards for complete requirements.
Key Systems
- Appearance Themes - Apply-once theme packs + live wallpaper/scheme/GTK controls
- Smart Colors - Semantic color adaptation cached in
~/.cache/dots/smart-colors/ - Quickshell - Unified QML desktop shell (bar, launcher, dashboard, notifications, AI chat) with multi-layout bar (
bar.position: left/right/top/bottom,bar.style: attached/floating/dock) and shell presets (~/.local/share/dots/shell-presets/*.json, applied live viadots-quickshell preset apply <name>or the in-shell layout picker) - Hornero C++ Plugin - Performance-critical Quickshell extensions (image analysis, audio, calculator)
- Dots CLI - Unified script interface
- Chaotic-AUR - Precompiled AUR packages for faster installation
See System Architecture for detailed architecture.
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.
- 6d ago First seen · 74 lines · 780 tokens per session scan A 85a19c788810
dotfiles AGENTS.md is an instructions file published in the GitHub repository ulises-jeremias/dotfiles (134 stars, last pushed 2d ago), licensed MIT. It adds 780 tokens to every session, about $0.0039 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.
Other instructions, from other repositories
dotfiles CLAUDE.md
Claude Code instructions for IvanWng97/dotfiles, a project described as: macOS dotfiles managed with GNU stow — ghostty, neovim, zsh, tmux, starship, lazygit, homebrew.
j3w1zsh AGENTS.md
AGENTS.md instructions for j3w1/j3w1zsh, covering j3w1zsh agent instructions, purpose and authority, start every run, security and privacy and platform and installer contract.
dotfiles CLAUDE.md
Claude Code instructions for M0rtalPhe0nix/dotfiles, covering coding agent instructions, repository purpose, safety rules, chezmoi conventions and operational invariants.
alunduil-chezmoi CLAUDE.md
Claude Code instructions for alunduil/alunduil-chezmoi, covering alunduil-chezmoi, source vs. apply path, invariants, sensors and two claude.md files.
dotfiles AGENTS.md
AGENTS.md instructions for M0rtalPhe0nix/dotfiles, covering agent instructions, rtk (rust token killer) - token-optimized commands, key commands, git (59-80% savings) and files & search (60-75% savings).
codex-desktop-linux AGENTS.md
AGENTS.md instructions for ilysenko/codex-desktop-linux, covering agents.md, purpose, non-negotiable rules, source routing and editing guidance.