agentrigs
+ submit rig
~ / rigs / bharvey88 / claude-code-setup

bharvey88/claude-code-setup

How I've wired Claude Code for real work: custom skills, a file-based memory pattern, and the plugins I layer on.

↗ GitHub ★ 1 MIT updated today personal setup Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~698 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit bharvey88/claude-code-setup/skills ./rig-claude-code-setup/skills

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 bharvey88/claude-code-setup/skills/blog .claude/skills/blog
$ npx degit bharvey88/claude-code-setup/skills/close .claude/skills/close
$ npx degit bharvey88/claude-code-setup/skills/ha-automations .claude/skills/ha-automations
$ npx degit bharvey88/claude-code-setup/skills/ha-dashboards .claude/skills/ha-dashboards
$ npx degit bharvey88/claude-code-setup/skills/ha-debug .claude/skills/ha-debug
$ npx degit bharvey88/claude-code-setup/skills/update-skills .claude/skills/update-skills
$ npx degit bharvey88/claude-code-setup/skills/upstream-contrib .claude/skills/upstream-contrib
$ npx degit bharvey88/claude-code-setup/skills/wled-docs .claude/skills/wled-docs
$ npx degit bharvey88/claude-code-setup/skills/writing-voice .claude/skills/writing-voice

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (9)

blogcloseha-automationsha-dashboardsha-debugupdate-skillsupstream-contribwled-docswriting-voice

Similar rigs

fabaindaiz/agents-knowledge
A portable .agents/ bundle for AI coding assistants
★ 1 project Claude CodeCodexCopilot 4 skills 2 agents 2 hooks today
Fort Knox 4.0k tok ·
alpersonalwebsite/ai-workstation-setup
Personal AI coding workstation: an idempotent setup script, tmux and shell config, and template Claude Code instructions, skills, agents and hooks for spec-driven development.
★ 0 setup Claude Code 7 skills 2d ago
Pragmatist 341 tok ·
LayerTM/ClaudeInHA
Claude Code CLI as a polished web console inside Home Assistant — tabs, clipboard, file attachments, and full HA access.
★ 1 project Claude Code 13 skills today
Skill Collector 964 tok ·
HuntsDesk/ve-kit
VE Harness — run Claude Code for hours without babysitting it. A hosted task board that survives the session, hooks that deny the commit until a review ran, real-time shared memory for your team's agents, and a Docker worker that works your
★ 3 project Claude Code 15 skills 9d ago
Skill Collector 1.1k tok ·
copied ✓