dotclaude

dotclaude

My working ~/.claude/ configuration for Claude Code. Published for reference — not designed as a drop-in clone.

What I'm Exploring

Sessions are ephemeral but work is not. Most of this config is dedicated to an ongoing experiment: what happens when you treat each session as worth remembering?

Chronicle a persistent journalist. A hook extracts a memory block at session end (what was accomplished, what's pending, key decisions). At session start, another hook injects relevant context: recent work in this project, pending items, stale threads. Over time: /chronicle curate to organize, /chronicle insights for cross-session patterns, /chronicle publish for digests.

Supporting pieces: session-title generation (a stop hook names each session from its content), analyze-usage (DuckDB analytics across Claude Code and Cursor logs), recall/remember agents (persistent memory across sessions), /fork (carry context into a new worktree or session).

Much of this config observes work rather than does it. The memory system is where the config is still evolving.

Directory Structure

~/.claude/
├── CLAUDE.md          # Personal context (name, preferences, tool choices)
├── settings.json      # Permissions, hooks, model selection
├── .mcp.json          # MCP server configs
├── commands/          # Slash commands (/bootstrap, /status_line)
├── skills/            # Extended capabilities with references
├── agents/            # Specialized autonomous agents
├── hooks/             # Session lifecycle scripts
├── scripts/           # Helper utilities
├── references/        # Reference documentation
├── chronicle/         # Chronicle session memory
├── webui/             # Config Visualizer dashboard
├── docs/              # Architecture documentation
└── [session data]     # Gitignored: history, todos, plans, etc. (see docs/session-data.md)

Quick Reference

Commands (/command)

Command	Purpose
/bootstrap	Scaffold new projects with structure
/claude-webui	Launch the web dashboard for this dotclaude repo
/opensource-precheck	Audit repo before making public
/plan_retro	Append retrospective to current plan
/pr-review	Address PR feedback toward merge
/project-health	Review ~/code projects health
/reflect	Pause to review work with fresh eyes
/reflection-log	Log feedback to improve reflection prompt
/retro	Review session trajectory and update todos
/session-wrapup	Final step before merge, captures learnings
/status_line	Explain current session metrics
/update-dependencies	Intelligent dependency updates with batching
/code-review	Review recent work against plan and standards
/codex-review	Code review via non-Claude models

Skills (auto-invoked)

Skill	When it activates
analyze-usage	Analyzing AI coding patterns and statistics
brainstorm-to-brief	Visual design exploration and design briefs
image-gen	Generating images with AI (OpenAI, Imagen, fal.ai)
backlog	Capturing explored work for later
chronicle	Capturing and curating session memory
frontend-design	Building web UIs, components, pages
webapp-testing	Playwright testing (Python and TypeScript)
skill-creator	Building new skills
release	Semantic versioned releases from any branch (worktree-aware)
cloudflare-workers-deploy	Workers deployment setup
git-worktree	Parallel branch development
web-artifacts-builder	Complex claude.ai artifacts
verify	Deployment verification and health checks
excalidraw-diagrams	Creating diagrams via Excalidraw
fork	Fork session to new worktree or local session
dotclaude-config	Editing Claude Code configuration
status-line-live	Customizing or troubleshooting the live status line
update-dependencies	Dependency analysis and updates
youtube-content	Extracting/analyzing YouTube video content

Skills (Experimental)

Experimental skills have status: experimental in frontmatter. Usable but incomplete.

Skill	Purpose
rate-title	AI-assisted session title rating with human calibration
session-title-eval	Batch evaluation of session title generation quality

Agents (background tasks)