agentrigs
+ submit rig
~ / rigs / regression-io / coder-config

regression-io/coder-config

Configuration manager for AI coding tools - Claude Code, Gemini CLI, Codex CLI, Antigravity. Manage MCPs, rules, permissions, memory, and workstreams.

↗ GitHub ★ 47 MIT updated 7d ago personal setup Codex Claude plugin
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~251 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 regression-io/coder-config/skills ./rig-coder-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 regression-io/coder-config/plugin/skills/flush .claude/skills/flush
$ npx degit regression-io/coder-config/plugin/skills/refactor .claude/skills/refactor
$ npx degit regression-io/coder-config/plugin/skills/update-docs .claude/skills/update-docs
$ npx degit regression-io/coder-config/skills/ralph-loop .claude/skills/ralph-loop

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 (4)

flushrefactorupdate-docsralph-loop

Similar rigs

sjhalani7/vaen
Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets.
★ 8 project Codex 2 skills 5mo ago
Minimalist 20 tok ·
yylo-dev/yylo
YYLO (why-lo): AI coding-agent orchestration CLI with equivalent yylo and yy launchers.
★ 63 project Claude CodeCodex 4 skills 6d ago
Minimalist 219 tok ·
choiyounggi/auto-velog
Claude Code 세션의 실제 개발 경험을 자동 포착해 사람이 쓴 듯한 글로 다듬어 Velog에 발행하는 플러그인
★ 1 project Claude Code 4 skills today
Minimalist 183 tok ·
lbb00/ai-rules-sync
Synchronize, manage, and share your ai rules, skills, commands, subagents (Cursor, Claude Code, Copilot, OpenCode, Trae AI, Codex, Gemini CLI, Warp) with ease.
★ 39 project Claude CodeCodexCursor 5 skills 2mo ago
Pragmatist 1.2k tok ·
copied ✓