dotfiles copilot-instructions.md

Repository-specific instructions for a chezmoi-managed dotfiles project. Chezmoi is a tool that stores configuration files in a repository and applies them to a computer’s home directory.

In plain words
What is it for?
Use them when working on this dotfiles repository, especially when changing files under home/, preparing commits or reviewing project changes.
Why use it?
They give coding agents the project context and rules needed to suggest safe changes. They also define expectations for commits, tests, pull requests and handling secrets.

Instructions file for GitHub Copilot

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

Made for: GitHub Copilot.

Per session 177 This file is loaded in full into every session.
When invoked 177 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.00177 $0.00177
Opus 5 $0.00088 $0.00088
Sonnet 5 $0.00035 $0.00035
Haiku 4.5 $0.00018 $0.00018

Measured 2d ago against content hash 2c699073a0bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotfiles copilot-instructions.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 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.

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.

.github/copilot-instructions.md · 7 lines

What it actually says

GitHub Copilot Instructions

  • Primary instructions: Read AGENTS.md at the repository root and follow it. It is the source of truth for repository context, comment policy, Git / PR workflow, and test policy.
  • Repository context: This is a chezmoi-managed dotfiles repository. Files under home/ are the public source state applied into the user's $HOME; see the Repository Context section of AGENTS.md before proposing changes.
  • Commit messages: Follow the Commit messages rule in AGENTS.md (Conventional Commits, <type>(<scope>): <summary>, lowercase imperative summary).
  • Security: Never suggest or commit secrets, API keys, or other personal data. Private dotfiles are managed outside this repository.
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 · 7 lines · 177 tokens per session scan A 2c699073a0bd

Subscribe to this mod's changes

dotfiles copilot-instructions.md is an instructions file published in the GitHub repository shunk031/dotfiles (148 stars, last pushed 3d ago), licensed MIT. It adds 177 tokens to every session, about $0.0009 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.