agentrigs
+ submit rig
~ / rigs / Dart-ilder / claude-config

Dart-ilder/claude-config

My Claude Code configuration: custom skills, slash commands, settings, and proxy setup guide

↗ GitHub ★ 1 no license updated 7mo ago personal setup Claude Code
share on X
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
CONTEXT TAX · EVERY TURN
~424 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 Dart-ilder/claude-config/commands ./rig-claude-config/commands
$ npx degit Dart-ilder/claude-config/skills ./rig-claude-config/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 Dart-ilder/claude-config/skills/critique .claude/skills/critique
$ npx degit Dart-ilder/claude-config/skills/rpi-workflow .claude/skills/rpi-workflow
$ npx degit Dart-ilder/claude-config/skills/sync-servers .claude/skills/sync-servers

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 (3)

critiquerpi-workflowsync-servers

Slash commands (10)

/commit/describe_pr/handoff/implement/iter/modify_plan/plan/receive_handoff/research/validate_plan

Plugins (4)

code-simplifier@claude-plugins-officialclaude-md-management@claude-plugins-officialpyright-lsp@claude-plugins-officialskill-creator@claude-plugins-official

Permissions

deny (0)
—
ask (0)
—
allow (40)
Read
Edit
Write
Glob
Grep
Agent
NotebookEdit
WebSearch
WebFetch
Skill(keybindings-help)
Bash(git *)
Bash(cd *)
Bash(ls *)
Bash(cat *)
Bash(head *)
Bash(tail *)
Bash(python *)
Bash(python3 *)
Bash(pip *)
Bash(uv *)
Bash(mkdir *)
Bash(cp *)
Bash(mv *)
Bash(wc *)
Bash(find *)
Bash(grep *)
Bash(rg *)
Bash(which *)
Bash(echo *)
Bash(source *)
Bash(conda *)
Bash(nvidia-smi*)
Bash(du *)
Bash(df *)
Bash(ss *)
Bash(curl *)
Bash(xargs *)
Bash(env *)
Bash(bash *)
Bash(date *)

Similar rigs

drader/researcher_agent
An LLM-driven research assistance framework for Claude Code (CC BY-NC 4.0)
★ 2 project Claude Code 4 skills 5mo ago
Pragmatist 1.9k tok ·
ARPeeketi/claude-resume-kit
Extract your papers once, generate tailored LaTeX resumes for every JD. Anti-fabrication controls, multi-perspective critique, AI fingerprint avoidance.
★ 283 project Claude Code 6 skills 7mo ago
Pragmatist 1.6k tok ·
LarryStanley/pi-delegate
Delegate coding work from Claude Code to a local pi agent — MCP tools with mid-run steer/abort, plus per-project discipline hooks.
★ 2 project Claude Code 1 mcp 9 skills 2mo ago
Pragmatist 2.9k tok ·
serbanghita/plan-critique-skills
Planning skills for Claude Code, Copilot, Agy, etc.
★ 13 collection Claude CodeGemini CLI 10 skills 22d ago
Skill Collector 1.4k tok ·
copied ✓