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/shunk031/dotfiles/copilot-instructionsgit clone --depth 1 https://github.com/shunk031/dotfilesWhat 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 | $0.00177 | $0.00177 |
| Opus 5 | $0.00088 | $0.00088 |
| Sonnet 5 | $0.00035 | $0.00035 |
| Haiku 4.5 | $0.00018 | $0.00018 |
Grade A, and why
dotfiles copilot-instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
GitHub Copilot Instructions
- Primary instructions: Read
AGENTS.mdat the repository root and follow it. It is the source of truth for repository context, comment policy, Git / PR workflow, and test policy. - Repository context: This is a
chezmoi-managed dotfiles repository. Files underhome/are the public source state applied into the user's$HOME; see theRepository Contextsection ofAGENTS.mdbefore proposing changes. - Commit messages: Follow the
Commit messagesrule inAGENTS.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.
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.
- 2d ago First seen · 7 lines · 177 tokens per session scan A 2c699073a0bd
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.
Other instructions, from other repositories
dotfiles AGENTS.md
Cross-platform dotfiles managed by Chezmoi with Homebrew/apt and per-language version managers. One-command bootstrap for macOS and Linux with Neovim, Tmux, Zsh, and AI agent skills.
dotfiles CLAUDE.md
Instructions for magic3007/dotfiles, covering claude.md, commands, ⚠️ 重要约束, architecture and two-phase installation (install.conf.yaml).
dotfiles CLAUDE.md
Instructions for laurigates/dotfiles, covering claude.md, ⚠️ public repository, chezmoi quick reference, claude code directories and plugins.
dotfiles AGENTS.md
Instructions for sfc-gh-eraigosa/dotfiles, covering dotfiles repository, repository structure, usage guidelines, asking the user (blocking questions must be colorized) and portability & best practices.
dotfiles AGENTS.md
Instructions for fmind/dotfiles, covering agents.md (project), house rules, conventions, workflows and agents.
dotfiles CLAUDE.md
Claude Code instructions for M0rtalPhe0nix/dotfiles, covering coding agent instructions, repository purpose, safety rules, chezmoi conventions and operational invariants.