Claude

Style

• Don't join independent clauses with semicolons or em dashes. End the sentence instead. A colon or other connector in their place is not a fix.
• Wrap filenames and code identifiers with backticks in any markdown context.
• In chat replies, write PR, issue, MR, and tracker-key (ABC-123) references as links, like [dotfiles#827](https://github.com/bendrucker/dotfiles/pull/827), because the terminal doesn't autolink them. Take the URL that gh, glab, or the tracker tool printed, or build it from the repo's remote. With no known URL, keep the bare ID.
• Don't hard-wrap markdown prose you author. In an existing file, follow its wrapping.
• Include a trailing newline in all new files.
• Put explanation of code you're writing in a message before the edit.
• Load the writing:writing skill before the first long-form prose you write for others (PR comments, reviews, documents, issues, Slack). One load covers the session.

Organization

• Don't create or extend catch-all modules like utils. Name modules for what they hold.
• Split code into files before splitting it across directories.
• Don't number steps or phases in code ("Phase 1:", "Step 2:"). Use descriptive function names called in sequence.

Customizations

Before adding a skill, hook, rule, or CLAUDE.md line, define what evidence shows it works, what shows it doesn't, and where that evidence surfaces. Override a Claude Code default only as an experiment with removal criteria.

Workflow

• A skill that instructs a subagent fan-out or background dispatch carries my authorization for Agent. Run it as written. When Agent is absent, run it inline and say so.
• Prefer analyst over general-purpose for read-only spawns. Pass model: haiku for pure lookup.
• When debugging Claude Code itself (harness, classifier, hooks, plugins, startup), launch the observed session with DEBUG_SDK=1 claude, which writes ~/.claude/debug/<session-id>.txt. Set it in the launch environment, since Claude Code ignores it in settings.json env.
• Open a PR with pull-request:create, or with an empty body when it's unavailable. Open PRs ready for review. Use draft only for speculative changes.
• Send build output to /dev/null. Store temporary files in tmp/.

Planning

Investigate in auto mode until the approach is settled, then enter plan mode to write it down. When I ask for a plan and something is still open, tell me what you're resolving and resolve it first.

Git

• Never git push to the default branch unless I say so.
• Name topic branches short and hyphenated.
• Write commit messages with one -m per paragraph, or a heredoc for complex ones. Wrap bodies at ~72 columns.
• Update a checkout with git merge --ff-only <ref>. Revert your own edits with git restore <path>. Run a tree-wide reset, checkout, or clean only when I name it.

Worktrees

Inside an isolated worktree, write files with Write or Edit and keep each Bash command a single plain command. The isolation guard refuses heredocs, $(...), loops, and a cd into the main checkout before git.

Claude Configuration

My Claude Code setup lives in bendrucker/claude. The ~/.claude symlinks point into ~/.claude-repo, a deployed clone of main, so an edit through the symlinks lands outside any branch. Settings that apply everywhere live in managed/settings.json, installed as managed settings. user/settings.json is the local machines' user file, and platforms/local/ and platforms/remote/ hold the entries a local machine or a remote session links in place of or beside user/'s. Project-scoped .claude/ directories stay with their repo.

Dotfiles

Machine setup lives in bendrucker/dotfiles. Anything the machine or shell must provide needs a merged dotfiles PR first, because the Claude repo installs nothing. That covers binaries, $PATH entries, aliases and functions, exported env vars, install steps, symlinks, launchd agents, macOS permission grants, and recurring jobs. Claude-only env vars go in settings.json instead.

Personal Details

My username is @bendrucker. Refer to actions by that user as "you."

@~/.claude/platform.md