dotfiles AGENTS.md

Repository-specific instructions for managing shunk031/dotfiles, a project that keeps configuration files and applies them to a computer. They describe the repository context, setup, skills, and boundaries between public and private files.

In plain words
What is it for?
Use them when working on this dotfiles repository, its AGENTS.md guidance, shared Codex configuration, skills, or chezmoi-managed public and private files.
Why use it?
They clarify which files belong to which configuration source and how changes should be handled, reducing the risk of editing the wrong area or exposing private settings.

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/shunk031/dotfiles/agents-md
Clone the repo
git clone --depth 1 https://github.com/shunk031/dotfiles

Made for: Codex, OpenCode.

Per session 517 This file is loaded in full into every session.
When invoked 517 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.00517 $0.00517
Opus 5 $0.00259 $0.00259
Sonnet 5 $0.00103 $0.00103
Haiku 4.5 $0.00052 $0.00052

Measured 2d ago against content hash a4e18770dbee, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

dotfiles AGENTS.md scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

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

- Codex boundary: This repo manages the Codex CLI, shared guidance, `~/.codex/AGENTS.md`, and `~/.codex/agents`; `dotfiles-private` manages `~/.codex/config.toml`, private profiles, credentials, and internal launchers.
AGENTS.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

[!NOTE] After reading this AGENTS.md, say: 🤖 I read the project-level AGENTS.md for shunk031/dotfiles.

Repository Context

  • Tooling: This repository is managed with chezmoi (GitHub).
  • Public source: Files under home/ are the public source state and are applied by chezmoi into the user's $HOME directory.
  • Private source: Private dotfiles are managed separately from ~/.local/share/chezmoi-private with config at ~/.config/chezmoi-private/chezmoi.yaml.
  • Management boundary: Treat the public home/ tree and the private chezmoi source/config as separate management domains.
  • Codex boundary: This repo manages the Codex CLI, shared guidance, ~/.codex/AGENTS.md, and ~/.codex/agents; dotfiles-private manages ~/.codex/config.toml, private profiles, credentials, and internal launchers.

Skills

  • Skill content is not in this repository. Public skills live in shunk031/skills and internal ones in shunk031/skills-private; these dotfiles subscribe to both through the allowlist in install/common/skills.sh.
  • When asked to add, change, or remove a skill, use the shunk031-manage-public-private-skills skill to decide which repository owns it before editing anything.
  • Changing which skills this machine installs is an allowlist edit here; changing what a skill does is an edit in the repository that owns it.

Comment Policy

  • When adding or updating comments for shell scripts or shell-based executables, write them in English using shdoc-compatible format; use the shunk031-shellscript-shdoc-docs skill for detailed conventions.

Development Setup

  • In every new clone or worktree, run make setup before editing or committing.
  • mise compatibility changes: When a tool or configuration change requires newer mise behavior, determine the minimum mise release that supports the change, raise min_version in the same pull request, and record the requirement in the pull request description.

Read the full file on GitHub · 32 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. 2d ago First seen · 32 lines · 517 tokens per session scan B a4e18770dbee

Subscribe to this mod's changes

dotfiles AGENTS.md is an instructions file published in the GitHub repository shunk031/dotfiles (148 stars, last pushed 3d ago), licensed MIT. It adds 517 tokens to every session, about $0.0026 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.