Borrowing it
Nothing to install: this file belongs to brujack/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/brujack/dotfiles/master/CLAUDE.mdgit clone --depth 1 https://github.com/brujack/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/brujack/dotfiles/claude-md)<a href="https://agentmods.dev/instructions/brujack/dotfiles/claude-md"><img src="https://agentmods.dev/badge/instructions/brujack/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/brujack/dotfiles/claude-md"><img src="https://agentmods.dev/badge/instructions/brujack/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 | $0.22361 | $0.22361 |
| Opus 5.5 | $0.08944 | $0.08944 |
| Sonnet 5.5 | $0.04472 | $0.04472 |
| Haiku 4.5 | $0.02236 | $0.02236 |
Grade D, and why
dotfiles CLAUDE.md scanned grade D with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- On a provisioned host run `./setup_env.sh -t doctor`, paste each remedy line one at a time (a sudo prompt can swallow the next), then re-run it. → `dotfiles-conventions.md` § `CLAUDE.md relocation: setup_env.sh workflo Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `setup_user` reads the Claude plugin manifest from ai-config `~/.claude/settings.json` (`extraKnownMarketplaces`, `enabledPlugins`), never a hardcoded list. → `dotfiles-conventions.md` § `CLAUDE.md relocation: setup_en Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- In `_install_ubuntu_tfenv` the `[[ ! -x "${_root}/bin/tfenv" ]]` guard must return before the symlink loop; the `rm -rf ${_root}` remedy belongs in the WARN, not doctor. → `dotfiles-conventions.md` § `CLAUDE.md relocat Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Never mock `sha256sum`; supply the real digest in `_RUSTUP_INIT_SHA256`, computed over `MOCK_CURL_STDOUT`'s exact bytes (`tests/mocks/curl` never fetches). → `dotfiles-test-seams.md` § `CLAUDE.md relocation: rustup ins How it starts
The opening of the file, as written. The whole thing — 615 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — dotfiles
A trailing → `file` § `heading` on a rule means: before acting on that rule's subject, read ai-config/docs/knowledge/<file> at that heading for the incident history and measurements.
Repository Overview
Personal development environment bootstrapping system for macOS and Linux (Ubuntu). Manages shell configs, tool installation, and symlink setup across multiple machine types.
Layout
Tracked top-level dirs: lib/ (shell libraries), config/ (profiles.sh, git-ignored local.sh, hook_repos.sh), scripts/, tests/, docs/, .config/ (.zshrc.d/), .github/ (workflows), .claude/, powershell/, LaunchAgents/, keys/, manifests/, pyenv.d/, .ssh/, .vscode/, .warp/; pyenv.d/rehash/*.bash is installed as a copy into ${PYENV_ROOT}/pyenv.d/rehash/, never symlinked, so edits need a reinstall; regenerate with git ls-files | awk -F/ 'NF>1{print $1}' | sort -u, never from memory. → dotfiles-conventions.md § CLAUDE.md budget: Layout directory tree
10-80-10 Execution Cycle
Sessions in this repo follow the 10-80-10 execution cycle defined in ai-config ADR-0009 (with the ADR-0010 wave-dispatch extension):
- Phase 1 (10%, Opus):
brainstorming→writing-plans, emitting per-taskyaml-taskblocks. - Phase 2 (80%, Sonnet/Haiku per plan):
subagent-driven-developmentiterate-until-green; never cheat a gate (FORBIDDEN list); wave-dispatch whenparallel_groupis declared. - Phase 3 (10%, Opus):
finishing-a-development-branchruns its gate chain; read the order in its Phase 3 table, not here. →dotfiles-conventions.md§CLAUDE.md budget: 10-80-10 phase list
Validate a plan before dispatch:
make validate-plan PLAN=docs/superpowers/plans/<file>.md
The validator (~/.claude/scripts/validate-plan.py, shared from ai-config) enforces required fields, valid role/model/tdd values, haiku scope guard, and disjoint files_touched within each parallel_group.
Knowledge Directory
Reference material for this repo lives in ai-config/docs/knowledge/ under dotfiles-<topic>.md naming (per ADR-0020). The local docs/knowledge/README.md is a pointer stub.
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.
- today Changed · +6 lines · +453 tokens per session 57929f0e5d29
- yesterday Changed · +1 lines · +154 tokens per session 4b129931477b
- 4d ago Changed · +5 lines · +302 tokens per session b4d5fa83d65f
- 7d ago Changed · +1 lines · +81 tokens per session 4fee3dadff4c
- 8d ago Changed · +6 lines · +923 tokens per session aa0cd1a21a37
- 9d ago Changed · +55 tokens per session eff62c1155ad
- 11d ago Changed · +21 tokens per session dffd0e489cbc
- 12d ago Changed · +2 lines · +67 tokens per session 0e41f2d65575
- 14d ago Changed · +6 lines · +360 tokens per session e8c515c590e0
- 15d ago First seen · 588 lines · 19,945 tokens per session scan D 27d499033f1f
dotfiles CLAUDE.md is an instructions file published in the GitHub repository brujack/dotfiles (5 stars, last pushed today), licensed Apache-2.0. It adds 22,361 tokens to every session, about $0.0894 per session on Opus 5.5. A static security scan graded it D with 4 findings (asks for root, reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
dotfiles CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dotfiles CLAUDE.mdbrujack/dotfiles | Instructions file | 5 | today | Apache-2.0 | D | 22,361 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |