studioromeo-at-boxuk/claude-dotfiles
My claude, versioned
ARCHETYPE
Fort Knox
Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.
GUARDRAILS
4/5
Blocks destructive commands · Protects secrets · No YOLO mode · Sandbox or ask-first rules · details
Copy this rig
# review before running: this installs third-party code $ npx degit studioromeo-at-boxuk/claude-dotfiles/agents ./rig-claude-dotfiles/agents $ npx degit studioromeo-at-boxuk/claude-dotfiles/commands ./rig-claude-dotfiles/commands $ npx degit studioromeo-at-boxuk/claude-dotfiles/skills ./rig-claude-dotfiles/skills $ npx degit studioromeo-at-boxuk/claude-dotfiles/hooks ./rig-claude-dotfiles/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 studioromeo-at-boxuk/claude-dotfiles/skills/adhd .claude/skills/adhd $ npx degit studioromeo-at-boxuk/claude-dotfiles/skills/caveman .claude/skills/caveman $ npx degit studioromeo-at-boxuk/claude-dotfiles/skills/review-claude-md .claude/skills/review-claude-md $ npx degit studioromeo-at-boxuk/claude-dotfiles/skills/review-memory .claude/skills/review-memory
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/studioromeo-at-boxuk/claude-dotfiles/main/agents/code-reviewer.md Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Bash(git push --force*)",
"Bash(git push -f*)",
"Read(**/.env)",
"Read(**/.env.*)",
"Read(**/*.pem)",
"Read(**/*.key)",
"Read(**/id_rsa*)",
"Read(**/*.keystore)",
"Read(**/*.jks)",
"Read(**/credentials.json)"
],
"ask": [
"Bash(rm -rf*)",
"Bash(git clean -f*)",
"Bash(git branch -D*)",
"Bash(git checkout -- *)",
"Bash(git restore *)"
]
}
} Skills (4)
Subagents (1)
| code-reviewer model: inherit | Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. |
Hooks (2)
| event | matcher | runs |
|---|---|---|
| SessionStart | * | jq -Rs '{hookSpecificOutput:{hookEventName:"SessionStart",additionalContext: ("Adopt ADHD-friendly output shaping for this entire session (stays on until the user says \"stop adhd mode\"/\"normal mode\"), per this skill:\n\n" + .)}}' ~/.cla |
| SessionStart | * | node ~/.claude/hooks/mentor-day.mjs 2>/dev/null || true |
Slash commands (1)
/handover-report
Permissions
deny (10)
Bash(git push --force*)
Bash(git push -f*)
Read(**/.env)
Read(**/.env.*)
Read(**/*.pem)
Read(**/*.key)
Read(**/id_rsa*)
Read(**/*.keystore)
Read(**/*.jks)
Read(**/credentials.json)
ask (5)
Bash(rm -rf*)
Bash(git clean -f*)
Bash(git branch -D*)
Bash(git checkout -- *)
Bash(git restore *)
allow (0)
—
Similar rigs
ayghri/i-have-adhd
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
Minimalist 1.4k tok ·
alihassanijr/.dotfiles
Ali's dotfiles & programs
Minimalist 435 tok ·
AizenvoltPrime/claude-setup
—
Pragmatist 1.2k tok ·
IvanKuzyshyn/dotfiles
Dotfiles optimized for speed, coffee, and questionable life choices. 😜
Pragmatist 3.0k tok ·