ocrosby/claude-config
Claude Code configuration
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
Copy this rig
# review before running: this installs third-party code $ npx degit ocrosby/claude-config/agents ./rig-claude-config/agents $ npx degit ocrosby/claude-config/commands ./rig-claude-config/commands $ npx degit ocrosby/claude-config/skills ./rig-claude-config/skills $ npx degit ocrosby/claude-config/hooks ./rig-claude-config/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit ocrosby/claude-config/skills/architect .claude/skills/architect $ npx degit ocrosby/claude-config/skills/audit .claude/skills/audit $ npx degit ocrosby/claude-config/skills/bench .claude/skills/bench $ npx degit ocrosby/claude-config/skills/code .claude/skills/code $ npx degit ocrosby/claude-config/skills/debug .claude/skills/debug $ npx degit ocrosby/claude-config/skills/docs .claude/skills/docs $ npx degit ocrosby/claude-config/skills/electron .claude/skills/electron $ npx degit ocrosby/claude-config/skills/feature .claude/skills/feature $ npx degit ocrosby/claude-config/skills/git .claude/skills/git $ npx degit ocrosby/claude-config/skills/knowledge-base .claude/skills/knowledge-base $ npx degit ocrosby/claude-config/skills/nvim .claude/skills/nvim $ npx degit ocrosby/claude-config/skills/obsidian .claude/skills/obsidian $ npx degit ocrosby/claude-config/skills/proof .claude/skills/proof $ npx degit ocrosby/claude-config/skills/skill .claude/skills/skill $ npx degit ocrosby/claude-config/skills/study .claude/skills/study $ npx degit ocrosby/claude-config/skills/tauri .claude/skills/tauri $ npx degit ocrosby/claude-config/skills/work .claude/skills/work
$ curl -fsSL --create-dirs -o .claude/agents/electron-architect.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/electron-architect.md $ curl -fsSL --create-dirs -o .claude/agents/electron-debugger.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/electron-debugger.md $ curl -fsSL --create-dirs -o .claude/agents/electron-reviewer.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/electron-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/gherkin-architect.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/gherkin-architect.md $ curl -fsSL --create-dirs -o .claude/agents/gherkin-debugger.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/gherkin-debugger.md $ curl -fsSL --create-dirs -o .claude/agents/gherkin-reviewer.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/gherkin-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/go-architect.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/go-architect.md $ curl -fsSL --create-dirs -o .claude/agents/go-debugger.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/go-debugger.md $ curl -fsSL --create-dirs -o .claude/agents/go-reviewer.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/go-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/nvim-architect.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/nvim-architect.md $ curl -fsSL --create-dirs -o .claude/agents/nvim-debugger.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/nvim-debugger.md $ curl -fsSL --create-dirs -o .claude/agents/nvim-reviewer.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/nvim-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/py-architect.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/py-architect.md $ curl -fsSL --create-dirs -o .claude/agents/py-debugger.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/py-debugger.md $ curl -fsSL --create-dirs -o .claude/agents/py-reviewer.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/py-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/rest-reviewer.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/rest-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/skill-reviewer.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/skill-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/tauri-architect.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/tauri-architect.md $ curl -fsSL --create-dirs -o .claude/agents/tauri-debugger.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/tauri-debugger.md $ curl -fsSL --create-dirs -o .claude/agents/tauri-reviewer.md https://raw.githubusercontent.com/ocrosby/claude-config/main/agents/tauri-reviewer.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash(git commit:*)",
"hooks": [
{
"type": "command",
"command": "~/.claude/hooks/protect-main.sh"
},
{
"type": "command",
"command": "~/.claude/hooks/ruff-format-gate.sh"
}
]
},
{
"matcher": "Bash(git push:*)",
"hooks": [
{
"type": "command",
"command": "~/.claude/hooks/protect-main.sh"
},
{
"type": "command",
"command": "~/.claude/hooks/conflict-check.sh"
}
]
},
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "~/.claude/hooks/tdd-remind.sh"
},
{
"type": "command",
"command": "~/.claude/hooks/electron-browserwindow-check.sh"
}
]
},
{
"matcher": "Read",
"hooks": [
{
"type": "command",
"command": "~/.claude/hooks/sensitive-file-warn.sh"
}
]
}
]
}
} Skills (17)
architectauditbenchcodedebugdocselectronfeaturegitknowledge-basenvimobsidianproofskillstudytauriwork
Subagents (20)
| electron-architect model: claude-opus-4-7 | Designs Electron application architecture — process boundaries, IPC surface, preload API shape, packaging & auto-update strategy. Use when planning a new Electron app, restructuring an existing one, o |
| electron-debugger model: claude-sonnet-4-6 | Diagnoses bugs in Electron apps and proposes targeted fixes. Use when encountering renderer/main-process errors, IPC failures, native-module load failures, packaging or auto-update failures, or `conte |
| electron-reviewer model: claude-sonnet-4-6 | Reviews Electron code for security, IPC hygiene, process-boundary correctness, and packaging/signing. Use proactively after writing or modifying main-process, preload, `BrowserWindow` configuration, ` |
| gherkin-architect model: claude-opus-4-7 | Designs BDD test architecture — feature file organization, step definition structure, and support layer. Use when planning a new BDD suite or restructuring an existing one. |
| gherkin-debugger model: claude-sonnet-4-6 | Diagnoses bugs in Gherkin BDD test suites and proposes targeted fixes. Use when encountering test failures in feature files or step definitions. |
| gherkin-reviewer model: claude-sonnet-4-6 | Reviews Gherkin feature files and step definitions for BDD best practices, clarity, and maintainability. Use proactively after writing or modifying feature files. |
| go-architect model: claude-opus-4-7 | Designs Go application architecture following clean architecture and idiomatic Go patterns. Use when planning a new project, restructuring an existing one, or evaluating design trade-offs. |
| go-debugger model: claude-sonnet-4-6 | Diagnoses bugs in Go applications and proposes targeted fixes. Use when encountering errors, panics, race conditions, or test failures. |
| go-reviewer model: claude-sonnet-4-6 | Reviews Go code for correctness, idiomatic patterns, error handling, and concurrency safety. Use proactively after writing or modifying Go code. |
| nvim-architect model: claude-opus-4-7 | Designs Neovim plugin architecture and module structure. Use when planning a new plugin, restructuring an existing one, or evaluating design trade-offs. |
| nvim-debugger model: claude-sonnet-4-6 | Diagnoses bugs in Neovim plugins and proposes targeted fixes. Use when encountering errors, unexpected behavior, or test failures in Lua plugin code. |
| nvim-reviewer model: claude-sonnet-4-6 | Reviews Neovim plugin code for correctness, API usage, performance, and idiomatic Lua patterns. Use proactively after writing or modifying Lua plugin code. |
| py-architect model: claude-opus-4-7 | Designs Python application architecture following hexagonal architecture principles. Use when planning a new project, restructuring an existing one, or evaluating design trade-offs. |
| py-debugger model: claude-sonnet-4-6 | Diagnoses bugs in Python applications and proposes targeted fixes. Use when encountering errors, unexpected behavior, or test failures. |
| py-reviewer model: claude-sonnet-4-6 | Reviews Python code for correctness, architecture, type safety, and idiomatic patterns. Use proactively after writing or modifying Python code. |
| rest-reviewer model: claude-sonnet-4-6 | Reviews HTTP handler and route code for REST API convention compliance. Use when reviewing code that defines HTTP endpoints. |
| skill-reviewer model: claude-sonnet-4-6 | Reviews Claude skill files (SKILL.md) for structural quality, language durability, and consistency with existing rules and agents. Use after writing or modifying a skill. |
| tauri-architect model: claude-opus-4-7 | Designs Tauri v2 desktop app architecture — frontend framework choice, IPC command surface, capability/permission scoping, state management, and plugin selection. Use when planning a new Tauri app, ad |
| tauri-debugger model: claude-sonnet-4-6 | Diagnoses bugs in Tauri v2 desktop applications — build/bundle failures, IPC command errors, capability permission-denied errors, and webview rendering issues. Use when encountering a Tauri-specific b |
| tauri-reviewer model: claude-sonnet-4-6 | Reviews Tauri v2 command handlers, capability/permission files, and frontend invoke() call sites for security and correctness. Use when reviewing code that defines #[tauri::command] functions, capabil |
Hooks (16)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | echo "Session started at $(date). Branch: $(git branch --show-current 2>/dev/null || echo 'N/A'). Last commit: $(git log --oneline -1 2>/dev/null || echo 'N/A')." |
| SessionStart | * | ~/.claude/skills/work/session_context.sh |
| PreToolUse | Bash(git commit:*) | ~/.claude/hooks/protect-main.sh |
| PreToolUse | Bash(git commit:*) | ~/.claude/hooks/ruff-format-gate.sh |
| PreToolUse | Bash(git push:*) | ~/.claude/hooks/protect-main.sh |
| PreToolUse | Bash(git push:*) | ~/.claude/hooks/conflict-check.sh |
| PreToolUse | Edit|Write | ~/.claude/hooks/tdd-remind.sh |
| PreToolUse | Edit|Write | ~/.claude/hooks/electron-browserwindow-check.sh |
| PreToolUse | Read | ~/.claude/hooks/sensitive-file-warn.sh |
| PostToolUse | Edit|Write | ~/.claude/hooks/lint.sh |
| PostToolUse | Bash(git commit:*) | ~/.claude/hooks/commit-msg.sh |
| UserPromptSubmit | * | ~/.claude/hooks/secret-scan.sh |
| PreCompact | * | ~/.claude/hooks/pre-compact.sh |
| Stop | * | ~/.claude/hooks/session-stop.sh |
| Stop | * | echo "If there is remaining work, keep going. Check your task list." |
| Stop | * | echo "If this session involved a correction or a repeated mistake, capture the guard before ending: update the relevant rule/skill/CLAUDE.md, and record repo-committed insights in LEARNINGS.md (per CLAUDE.md # Self-Improvement)." |
Slash commands (8)
/bdd/branch-from-main/check-branch-merged/conventional-commit-msg/gotcha-check/open-pr/test-and-fix/workflow
Plugins (5)
gopls-lsp@claude-plugins-officiallua-lsp@claude-plugins-officialpyright-lsp@claude-plugins-officialtypescript-lsp@claude-plugins-officialrust-analyzer-lsp@claude-plugins-official
Permissions
deny (0)
—
ask (0)
—
allow (7)
Edit(**)
Write(**)
Bash(*)
mcp__context7__*
mcp__claude_ai_Jedi-Knights_NWSL__*
WebFetch
Skill(update-config)
Similar rigs
assaio/assaio
Is your AI coding spend delivering? Offline-first analytics for Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI and Cline — $/100 AI lines per project, every verdict carrying its own confidence, a self-contained dashboard, exec plugi
Fort Knox 4.7k tok ·
bradtraversy/skillpass
A validated directory of AI skills to help your workflow. Post your skills and install others.
Skill Collector 6.1k tok ·
DongDuong2001/pudo-code-system
Modular, scalable, automated development intelligence.
Pragmatist 1.9k tok ·
Xia-Ataraxia/craft-skills
Vendor-neutral Agent Skills (SKILL.md) for software and research work across Claude Code, Codex, Hermes, GJC, Cursor, and Grok.
Skill Collector 6.7k tok ·