dotfiles CLAUDE.md

Instructions for a public dotfiles repository managed with chezmoi, a tool that keeps configuration files synchronized across computers. They cover secret handling, Claude Code directories, and safe configuration updates.

In plain words
What is it for?
Use them when changing the repository’s shell, Claude Code, or other machine-configuration files and when checking changes before applying them.
Why use it?
They help contributors avoid exposing private data or editing generated files in the wrong location.

Instructions file

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/laurigates/dotfiles/claude-md
Clone the repo
git clone --depth 1 https://github.com/laurigates/dotfiles
Per session 1,387 This file is loaded in full into every session.
When invoked 1,387 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 $0.01387 $0.01387
Opus 5 $0.00694 $0.00694
Sonnet 5 $0.00277 $0.00277
Haiku 4.5 $0.00139 $0.00139

Measured 3d ago against content hash 62bb80328852, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dotfiles CLAUDE.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 3d 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.

CLAUDE.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Chezmoi dotfiles repository with cross-platform development environment configuration.

⚠️ Public Repository

This repo is public (github.com/laurigates/dotfiles). Never commit private information: secrets/API tokens (use ~/.api_tokens, sourced by mise), personal hostnames/IPs, internal-only org facts, or machine-specific identifiers. Secret-adjacent files use the chezmoi private_ prefix and stay out of templates that render to tracked output. When in doubt, leave it out — assume anything committed is world-readable and indexed.

Chezmoi Quick Reference

  • Source directory: ~/.local/share/chezmoi/ (always edit here)
  • Target locations: ~/.* (never edit directly)
  • Essential commands: chezmoi diff, chezmoi apply --dry-run, chezmoi apply
  • Cross-platform: Templates handle OS/arch differences; Chezmoi Expert skill provides guidance

Claude Code Directories

Two distinct .claude/-shaped directories exist here:

  • exact_dot_claude/ — chezmoi source for the user-global ~/.claude/ tree (exact-match semantics; orphaned files auto-removed). Edit source here, then run chezmoi apply -v ~/.claude to sync. A PostToolUse hook (exact_dot_claude/hooks/chezmoi-workflow-nudge.sh) reminds you to apply after edits under this path.
  • .claude/ at the repo root — project-scoped Claude Code config for working inside this repo: settings.json (permissions allowlist, pinned plugins, hooks), skills/, commands/, agents/, hooks/. Tracked in git. Only per-machine runtime state (sessions/, projects/, todos/, .credentials*) is gitignored.

Plugins

Managed in laurigates/claude-plugins. Use just plugins-* recipes for bulk management. The provider ↔ consumer symbiosis between the two repos, and the just module/group layout, are diagrammed in docs/justfile-architecture.md.

MCP Servers

Managed per-project in .mcp.json. Registry of available servers in .chezmoidata.toml under [mcp_servers]. Use /configure:mcp for guided setup.

Read the full file on GitHub · 102 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. 3d ago First seen · 102 lines · 1,387 tokens per session scan A 62bb80328852

Subscribe to this mod's changes

dotfiles CLAUDE.md is an instructions file published in the GitHub repository laurigates/dotfiles (10 stars, last pushed 3d ago), licensed MIT. It adds 1,387 tokens to every session, about $0.0069 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 2026-08-31.