agentrigs
+ submit rig
~ / rigs / jpc4729 / setup

jpc4729/setup

My agent setup for Claude Code, Codex, Cursor, Grok and opencode: shared rules, six subagents, a git guard hook and 14 skills, with an installer that copies files and merges settings.

↗ GitHub ★ 0 MIT updated today personal setup Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~9.9k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add --transport http context7 https://mcp.context7.com/mcp -H 'CONTEXT7_API_KEY: YOUR_VALUE'
$ npx degit jpc4729/setup/agents ./rig-setup/agents

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.

$ claude mcp add --transport http context7 https://mcp.context7.com/mcp -H 'CONTEXT7_API_KEY: YOUR_VALUE'
$ npx degit jpc4729/setup/agents/skills/agent-browser .claude/skills/agent-browser
$ npx degit jpc4729/setup/agents/skills/grilling .claude/skills/grilling
$ npx degit jpc4729/setup/agents/skills/ponytail-audit .claude/skills/ponytail-audit
$ npx degit jpc4729/setup/agents/skills/ponytail-debt .claude/skills/ponytail-debt
$ npx degit jpc4729/setup/agents/skills/ponytail-review .claude/skills/ponytail-review
$ npx degit jpc4729/setup/agents/skills/ponytail .claude/skills/ponytail
$ npx degit jpc4729/setup/agents/skills/thermo-nuclear-code-quality-review .claude/skills/thermo-nuclear-code-quality-review
$ npx degit jpc4729/setup/agents/skills/typesafe-ai .claude/skills/typesafe-ai

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 *)"
    ]
  }
}

MCP servers (2)

serversourceest. tokens
Context7 remote · remote 1.2k
paper local / custom · remote 2.5k

Skills (8)

agent-browsergrillingponytail-auditponytail-debtponytail-reviewponytailthermo-nuclear-code-quality-reviewtypesafe-ai

Similar rigs

DietrichGebert/ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
★ 155k project CodexCursorCopilot 6 skills 4d ago
Pragmatist 1.6k tok ·
saqie803/ponytail
Ship production-ready code with one line of AI-generated output, built for 20 agents and zero ceremony.
★ 2 project Codex 6 skills today
Pragmatist 714 tok ·
contextmux/contextmux
Turn a ticket into a reviewed pull request, under gates that stop work which drifted out of scope or weakened tests. Compiles one source of coding rules to CLAUDE.md, AGENTS.md, .cursor/rules and copilot-instructions.
★ 1 project Claude CodeCodexCursor 1 mcp 8 skills 1 agents 17d ago
Pragmatist 10.1k tok ·
Cygnux-Labs/Tracekit
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
★ 2 project Claude CodeCodex 12 skills 1 agents 4 hooks today
Skill Collector 2.1k tok ·
copied ✓