Borrowing it
Nothing to install: this file belongs to DJRHails/dotfiles. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DJRHails/dotfiles/main/CLAUDE.mdgit clone --depth 1 https://github.com/DJRHails/dotfilesWrote 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.
[](https://agentmods.dev/instructions/djrhails/dotfiles/claude-md)<a href="https://agentmods.dev/instructions/djrhails/dotfiles/claude-md"><img src="https://agentmods.dev/badge/instructions/djrhails/dotfiles/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/djrhails/dotfiles/claude-md"><img src="https://agentmods.dev/badge/instructions/djrhails/dotfiles/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00720 | $0.00720 |
| Opus 5.5 | $0.00288 | $0.00288 |
| Sonnet 5.5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
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 16d 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.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dotfiles
Personal dotfiles, checked out at ~/.files. Modules live under modules/<name>/; agent skills
under modules/agents/skills/ (symlinked into ~/.claude/skills, ~/.agents/skills, …).
This repo is PUBLIC — keep everything plaintext generic
Glassine (filter=glassine in .gitattributes) encrypts sensitive files at rest, but git
metadata is always plaintext: PR titles and descriptions, commit messages, branch names,
review comments, issue text, and .gitattributes paths themselves.
- Before writing any of those, check whether the change touches an encrypted path
(
git check-attr filter -- <path>). If it does, describe it generically — "update an encrypted skill" — and put the real rationale inside the encrypted file. - Never name hostnames (including this machine's), device models or IPs, tailnet names, private repos, internal services, credentials, or what a device/service is used for.
- The attribution footer on PRs/comments stays host-free here:
_[via claude](<link>)_, notclaude @ <host>. - Branch names are kept on the PR forever, even after deletion — pick a generic one
(
skill-update) before the first push; there is no after-the-fact fix. - If something leaky is already pushed: rewrite the PR title/body via
gh api --method PATCH repos/DJRHails/dotfiles/pulls/<n>, and before merging replace the commit message (same tree, force-push) so the squash commit onmainis generic too.
Git mechanics
- Parallel sessions leave unpushed commits on local
main. Checkgit log --oneline origin/main..HEADbefore building a branch; never push commits that aren't yours. To open a PR without dragging them along, build the commit onorigin/mainwith a temporary index (GIT_INDEX_FILE=… git read-tree origin/main,git update-index --cacheinfo,git write-tree,git commit-tree -p origin/main) and push<sha>:refs/heads/<branch>. - Encrypted blobs:
git show/git cat-file -pprint ciphertext. Read plaintext withgit cat-file --filters <rev>:<path>; create an encrypted blob from a working-tree file withgit hash-object -w --path=<path> <file>(the--pathapplies the clean filter). - Glassine reuses ciphertext only against the index: cleaning plaintext identical to the
path's index entry returns that entry's blob, but a path with no (or a differing) index entry
gets fresh, non-deterministic ciphertext — so
git status/git diff --statcan report changes that are ciphertext-only. Compare plaintext (git cat-file --filters) before believing a diff;git restore --stagedclears index-only noise. - In zsh,
"$var:refs/…"applies the:rmodifier to$var— write"${var}:refs/…". - Commit with explicit pathspecs (
git commit -- <paths>): other sessions stage files in the shared index.
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.
- 16d ago First seen · 44 lines · 720 tokens per session scan A 04612db8e97d
dotfiles CLAUDE.md is an instructions file published in the GitHub repository DJRHails/dotfiles (2 stars, last pushed today), licensed MIT. It adds 720 tokens to every session, about $0.0029 per session on Opus 5.5. 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 2026-09-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).