dotfiles AGENTS.md

dotfiles AGENTS.md is an instructions file for Codex, OpenCode from ithinkihaveacat/dotfiles. It costs 1,993 tokens per session, scanned C, original, Apache-2.0.

Development instructions for a public dotfiles repository, a collection of personal configuration files and scripts.

In plain words
What is it for?
Maintaining public configuration files safely and separating them from private and company-specific settings.
Why use it?
They help keep private or employer-specific information out of public code while preserving required script and documentation standards.

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

Made for: 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/ithinkihaveacat/dotfiles/agents-md.svg)](https://agentmods.dev/instructions/ithinkihaveacat/dotfiles/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ithinkihaveacat/dotfiles/agents-md"><img src="https://agentmods.dev/badge/instructions/ithinkihaveacat/dotfiles/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,993 This file is loaded in full into every session.
When invoked 1,993 The same file — it is already loaded in full.
Security scan C 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 $0.01993 $0.01993
Opus 5 $0.00996 $0.00996
Sonnet 5 $0.00399 $0.00399
Haiku 4.5 $0.00199 $0.00199

Measured 4d ago against content hash c0278c8e0635, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

dotfiles AGENTS.md scanned grade C 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 4d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

trap 'rm -rf -- "$TMPDIR"' EXIT
AGENTS.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Guidelines

This document provides development guidelines for this repository, covering privacy, information control, and script quality. These rules apply to all commits, including code, configurations, and documentation.

Privacy and Information Control

This repository is strictly public. You must enforce rigid data segregation across all code, documentation, commit messages, and metadata to protect personal privacy and proprietary information.

Companion Repositories

This public repository works in tandem with two private companion repositories:

  1. private (at ~/.private): For personal secrets and private configurations.
  2. corp (at ~/.corp): For employer-specific work and internal tools.

When operating in either of these companion workspaces, you MUST locate and adhere to their respective AGENTS.md files. The companion AGENTS.md files provide domain-specific privacy constraints that supersede the rules here, while all general coding standards and script requirements from this document still apply.

  • Public Safety: All commits must be strictly safe for public consumption. Never include unreleased features, internal API endpoints, private credentials, or proprietary algorithms.
  • Employer Anonymity: Never leak internal, proprietary, or employer-specific information. It must remain impossible to identify the user's current or past employers from any data, context, or code structure in this repository.
    • Action: Route all employer-specific work, architecture, configurations, and documentation exclusively to the corp repository.
  • Biographical & Location Security: Never leak granular, real-time, or sensitive personal telemetry. While broad, static associations (such as general relevance to London or Melbourne) are acceptable, you must never expose exact locations, specific addresses, real-time travel plans, or holiday schedules.
    • Action: Route all sensitive, personal, or autobiographical data exclusively to the private repository.
  • Pre-Commit Sanitization: Before finalizing any commit, verify that no protected data (corporate or personal) has been inadvertently included in code comments, test fixtures, or documentation.

Read the full file on GitHub · 221 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. 4d ago First seen · 221 lines · 1,993 tokens per session scan C c0278c8e0635

Subscribe to this mod's changes

dotfiles AGENTS.md is an instructions file published in the GitHub repository ithinkihaveacat/dotfiles (48 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,993 tokens to every session, about $0.0100 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.