dotfiles: Instructions file for Claude Code

AGENTS.md

dotfiles AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from magic3007/dotfiles. It costs 5,122 tokens per session, scanned D, original, MIT.

Repository instructions for managing personal configuration files, such as shell and editor settings. The project uses Dotbot to install those files by linking them from the repository to their usual locations.

In plain words
What is it for?
Running the installer, previewing changes, updating submodules, and adding new configuration files and their links.
Why use it?
They explain how to install or preview configuration changes safely and how local setup differs from network-dependent setup.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: ${CLAUDE_SKILL_DIR} variable, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; reads ~/.codex paths.

This is magic3007/dotfiles's own configuration. It tells Claude Code, Codex and OpenCode how to work on dotfiles itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dotfiles configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/magic/....

Reuse

Borrowing it

Nothing to install: this file belongs to magic3007/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.

Copy the file
curl -O https://raw.githubusercontent.com/magic3007/dotfiles/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/magic3007/dotfiles

Made for: Claude Code, 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 dotfiles AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/magic3007/dotfiles/agents-md/github.svg)](https://agentmods.dev/instructions/magic3007/dotfiles/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/magic3007/dotfiles/agents-md"><img src="https://agentmods.dev/badge/instructions/magic3007/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.

agentmods 80×15 button for dotfiles AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/magic3007/dotfiles/agents-md"><img src="https://agentmods.dev/badge/instructions/magic3007/dotfiles/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,122 This file is loaded in full into every session.
When invoked 5,122 The same file — it is already loaded in full.
Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.05122 $0.05122
Opus 5.5 $0.02049 $0.02049
Sonnet 5.5 $0.01024 $0.01024
Haiku 4.5 $0.00512 $0.00512

Measured today against content hash a11884c706c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

dotfiles AGENTS.md scanned grade D with 3 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 today.

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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

**omp** (`omp/`, https://omp.sh, Stencil/oh-my-pi): a coding agent harness. Six static configs are symlinked into `~/.omp/agent/`: `config.yml`, `models.yml`, `gateways-login.json` (the `omp-model-gateway` plugin's gatew

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

directive, and it edits `~/.codex/config.toml` in place at runtime, writing

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**omp** (`omp/`, https://omp.sh, Stencil/oh-my-pi): a coding agent harness. Six static configs are symlinked into `~/.omp/agent/`: `config.yml`, `models.yml`, `gateways-login.json` (the `omp-model-gateway` plugin's gatew
AGENTS.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.

Overview

Dotfiles repository using Dotbot for installation. Stores configuration files and symlinks them to their standard locations (~/.zshrc, ~/.gitconfig, ~/.config/nvim, etc.).

Commands

./install                                # Full installation (idempotent, safe to re-run)
./install --only link                   # Phase 1 only: create/relink symlinks (no network)
./install --only clean                  # Remove broken symlinks under ~
./install --only create                 # Create missing directories
git submodule update --init --recursive  # Update Vim plugins

No dry-run flag. This pinned Dotbot submodule has no -n / --dry-run; both fail with unrecognized arguments. Preview by running the single Phase 1 directive you care about (--only link is the one you want after editing the link section — it is idempotent, and it refuses to overwrite an existing regular file, so a stray ~/.foo/config must be moved aside first).

Architecture

Two-Phase Installation (install.conf.yaml)

  • Phase 1 — Local: Defaults, directory creation, submodules, backup existing configs, symlinks. No network required, always succeeds.
  • Phase 2 — Network: Homebrew, platform packages, oh-my-zsh + plugins, fzf, Node.js/nvm, GitHub CLI, AI coding tools. All commands use --connect-timeout / || true to avoid blocking without network.

Symlink Model

All configs live in this repo and are symlinked to ~ via Dotbot. The link section in install.conf.yaml is the single source of truth for what gets symlinked where. When adding new configs: add files to the repo, then add symlink entries to install.conf.yaml.

Local Customization Pattern

Machine-specific overrides go in *_local files (not tracked by git):

  • ~/.gitconfig_local — local git user/config (included via [include] in gitconfig)
  • ~/.zsh_local — local zsh config
  • ~/.common_shell_setup_local.sh — local shell setup (bash/zsh)
  • ~/.codex/config_local.toml — per-machine Codex config, merged over codex/config.toml (example: Linux hosts disable the macOS-only [mcp_servers.node_repl])
  • ~/.config/fish/conf.d/local.fish — local fish config (fish is archived; see below)

Read the full file on GitHub · 225 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. today Changed · +75 tokens per session a11884c706c2
  2. 3d ago Changed · +2 tokens per session 2465e050e0c1
  3. 9d ago Changed · +3 tokens per session 22e27f4a34a8
  4. 14d ago Changed · +2 lines · +177 tokens per session bb7870ced681
  5. 16d ago Changed · +61 tokens per session 27d46d87f04d
  6. 21d ago Changed · +125 tokens per session 4662bd9c1662
  7. 23d ago Changed · +33 lines · +643 tokens per session b9b72dee5041
  8. 24d ago Changed · +18 lines · +321 tokens per session 7565ae6e9284
  9. 25d ago Changed · +9 lines · +265 tokens per session e5f402ea41f0
  10. 1mo ago First seen · 163 lines · 3,450 tokens per session scan D eb75589aced5

Subscribe to this mod's changes

dotfiles AGENTS.md is an instructions file published in the GitHub repository magic3007/dotfiles (11 stars, last pushed yesterday), licensed MIT. It adds 5,122 tokens to every session, about $0.0205 per session on Opus 5.5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). 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

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 · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,750 tokens

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.

deepseek-ai/deepseek-harness · 4,261 tokens