agentrigs
+ submit rig
~ / rigs / JustinThomas2 / agentrc

JustinThomas2/agentrc

Portable dev environment from one source of truth: zsh, git aliases, and cross-agent config (Claude Code, Codex) via symlink.

↗ GitHub ★ 2 MIT updated 2mo ago project Claude CodeCodex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~1.5k 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 JustinThomas2/agentrc/agents ./rig-agentrc/agents
$ npx degit JustinThomas2/agentrc/skills ./rig-agentrc/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 JustinThomas2/agentrc/skills/address-feedback .claude/skills/address-feedback
$ npx degit JustinThomas2/agentrc/skills/file-issue .claude/skills/file-issue
$ npx degit JustinThomas2/agentrc/skills/open-pr .claude/skills/open-pr
$ npx degit JustinThomas2/agentrc/skills/respond-feedback .claude/skills/respond-feedback
$ npx degit JustinThomas2/agentrc/skills/review-pr .claude/skills/review-pr
$ npx degit JustinThomas2/agentrc/skills/session-retro .claude/skills/session-retro
$ npx degit JustinThomas2/agentrc/skills/tdd .claude/skills/tdd
$ npx degit JustinThomas2/agentrc/skills/update-config .claude/skills/update-config
$ npx degit JustinThomas2/agentrc/skills/work-issue .claude/skills/work-issue
$ npx degit JustinThomas2/agentrc/skills/workflow .claude/skills/workflow

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 (10)

address-feedbackfile-issueopen-prrespond-feedbackreview-prsession-retrotddupdate-configwork-issueworkflow

Similar rigs

Zack-Zz/ai-code
Complete ai Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.
★ 0 project Codex 7 skills today
Pragmatist 1.9k tok ·
ZaaliMohamed123/evolving-claude
A self-improving global Claude Code setup: 10 subagents, on-demand skills, safety hooks, three-tier memory, and a config feedback loop.
★ 4 project Claude Code 8 skills 10 agents 2mo ago
Orchestrator 2.2k tok ·
bforbesc/claudia
My Claude Code setup: custom config, hooks, skills, and workflow automation for reviews, PRs, handoffs, and faster coding.
★ 2 project Claude Code 11 skills 10d ago
Skill Collector 1.3k tok ·
wbern/agent-instructions
Claude Instructions Repository
★ 167 project Claude Code 1 skills 4mo ago
Pragmatist 2.0k tok ·
copied ✓