agentrigs
+ submit rig
~ / rigs / kitepon / dotagents

kitepon/dotagents

Claude Code / Codex のカスタムスキル・コマンドを複数端末で symlink 同期する個人 dotfiles

↗ GitHub ★ 0 no license updated 1d ago personal setup Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~5.6k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/kitepon/dotagents

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 kitepon/dotagents/claude/skills/1<redacted>
$ npx degit kitepon/dotagents/claude/skills/auto-deploy-on-push .claude/skills/auto-deploy-on-push
$ npx degit kitepon/dotagents/claude/skills/gpt-connector .claude/skills/gpt-connector
$ npx degit kitepon/dotagents/codex/skills/oracle .claude/skills/oracle
$ npx degit kitepon/dotagents/codex/skills/polish-github .claude/skills/polish-github
$ npx degit kitepon/dotagents/docs/archive/2026-09_orchestrate/claude/skills/orchestrate .claude/skills/orchestrate

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 (6)

1passwordauto-deploy-on-pushgpt-connectororaclepolish-githuborchestrate

Similar rigs

snaplyze/claude-orchestration
Claude Code plugin for orchestration: five specialist subagents with explicit model and effort, subscription profiles, user-scope install, and runtime verification
★ 0 project Codex 1 skills today
Pragmatist 3.2k tok ·
ChristianBlevens/RaiGolmi
A computer you build by talking to an AI.
★ 0 project Claude Code 1 mcp 2 skills 3d ago
Pragmatist 2.7k tok ·
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 ·
XXX1694/Vanguard
Command center for Claude Code: live pane for your subagent squad, limits and context, an orchestrator with specialist agents, bundled MCP servers and skills, levels and achievements.
★ 1 project Claude Code 4 skills today
Minimalist 307 tok ·
copied ✓