~ / rigs / runnithan / claudex-setup

runnithan/claudex-setup

Portable Claude Code and Codex configuration: slash commands, subagents, hooks, skills, and a transcript-to-lessons pipeline. Installable as a plugin.

↗ GitHub ★ 1 MIT updated 5d ago personal setup Claude Code Codex Claude plugin

share on X

ARCHETYPE

Fort Knox

Deny lists, pre-tool hooks, sandboxing. Nothing touches prod without a signature.

CONTEXT TAX · EVERY TURN

~3.2k tokens

Moderate · median rig: 2.3k · breakdown

GUARDRAILS

4/5

Blocks destructive commands · Protects secrets · Pre-tool screening hook · No YOLO mode · details

Copy this rig

# review before running: this installs third-party code
$ npx degit runnithan/claudex-setup/.claude ./rig-claudex-setup  # inspect, then merge into .claude/

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.

Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.

{
  "permissions": {
    "deny": [
      "Read(backend/.env)",
      "Edit(backend/.env)",
      "Read(frontend/.env)",
      "Edit(frontend/.env)",
      "Read(firebase-service-account.json)",
      "Edit(firebase-service-account.json)",
      "Read(**/.env)",
      "Edit(**/.env)",
      "Read(**/.env.*)",
      "Edit(**/.env.*)",
      "Read(**/*.pem)",
      "Edit(**/*.pem)",
      "Read(**/*.key)",
      "Edit(**/*.key)",
      "Read(**/*.p12)",
      "Edit(**/*.p12)",
      "Read(**/id_rsa)",
      "Edit(**/id_rsa)",
      "Read(**/.ssh/**)",
      "Edit(**/.ssh/**)",
      "Read(**/.aws/**)",
      "Edit(**/.aws/**)",
      "Read(**/*service-account*.json)",
      "Edit(**/*service-account*.json)",
      "Bash(cat *.env*)",
      "Bash(cat *.pem)",
      "Bash(cat *.key)",
      "Bash(cat *.p12)",
      "Bash(cat *id_rsa*)",
      "Bash(cat *service-account*.json)",
      "Bash(cat *.ssh/*)",
      "Bash(git push --force:*)",
      "Bash(git push -f:*)",
      "Bash(git push --delete:*)",
      "Bash(git push --mirror:*)",
      "Bash(git push --prune:*)",
      "Bash(git push --force:*)",
      "Bash(git push -f:*)",
      "Bash(git push --delete:*)",
      "Bash(git push --mirror:*)",
      "Bash(git push --prune:*)"
    ]
  },
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Edit|Write|MultiEdit",
        "hooks": [
          {
            "type": "command",
            "command": "python3 .claude/hooks/security_reminder_hook.py"
          }
        ]
      },
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "python3 .claude/hooks/block-destructive-push.py"
          },
          {
            "type": "command",
            "command": "for f in \"$CLAUDE_PROJECT_DIR/.claude/hooks/block-destructive-push.py\" .claude/hooks/block-destructive-push.py \"$CLAUDE_PROJECT_DIR/hooks/block-destructive-push.py\" hooks/block-destructive-push.py; do [ -f \"$f\" ] && exec python3 \"$f\"; done;"
          }
        ]
      }
    ]
  }
}

Skills (3)

claude-md-improver frontend-design session-handoff

Subagents (6)

backend-dev model: sonnet	Backend engineer. Handles code changes, backend tests, database migrations, and commits. Use for any backend-only work.
code-reviewer model: opus	Use this agent when you need to review code for adherence to project guidelines, style guides, and best practices. Use when asked, or after completing a multi-file coding task, especially before commi
code-simplifier model: opus	\|
frontend-dev model: sonnet	Frontend engineer. Handles UI code changes, component development, lint/build verification, and commits. Use for any frontend-only work.
pr-test-analyzer model: inherit	Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new fun
qa model: sonnet	QA engineer. Runs tests, lint, and build checks. Validates PRs before merge. Reports failures to team lead. Does NOT modify code.

Hooks (10)

event	matcher	runs
SessionStart	*	node .claude/hooks/gsd-check-update.js
PreToolUse	Edit\|Write\|MultiEdit	python3 .claude/hooks/security_reminder_hook.py
PreToolUse	Bash	python3 .claude/hooks/block-destructive-push.py
PostToolUse	*	node .claude/hooks/gsd-context-monitor.js
PostToolUse	Write	bash .claude/hooks/auto-format.sh
PostToolUse	Edit	bash .claude/hooks/auto-format.sh
Stop	*	printf '{"terminalSequence":"\\u0007"}'
Stop	*	.claude/scripts/ralph-stop-hook.sh
Notification	*	printf '{"terminalSequence":"\\u0007"}'
PreToolUse	Bash	for f in "$CLAUDE_PROJECT_DIR/.claude/hooks/block-destructive-push.py" .claude/hooks/block-destructive-push.py "$CLAUDE_PROJECT_DIR/hooks/block-destructive-push.py" hooks/block-destructive-push.py; do [ -f "$f" ] && exec python3 "$f"; done;

Slash commands (19)

/cancel-ralph/changelog-claude/changelog-codex/claude-loop/codex-loop/consolidate-lessons/extract-lessons/extract-social-lessons/fact-check/optimise/pr/quiz-me/ralph-help/ralph-loop/review-pr/revise-claude-md/test/ticket/top-tips

Permissions

deny (41)

Read(backend/.env)

Edit(backend/.env)

Read(frontend/.env)

Edit(frontend/.env)

Read(firebase-service-account.json)

Edit(firebase-service-account.json)

Read(**/.env)

Edit(**/.env)

Read(**/.env.*)

Edit(**/.env.*)

Read(**/*.pem)

Edit(**/*.pem)

Read(**/*.key)

Edit(**/*.key)

Read(**/*.p12)

Edit(**/*.p12)

Read(**/id_rsa)

Edit(**/id_rsa)

Read(**/.ssh/**)

Edit(**/.ssh/**)

Read(**/.aws/**)

Edit(**/.aws/**)

Read(**/*service-account*.json)

Edit(**/*service-account*.json)

Bash(cat *.env*)

Bash(cat *.pem)

Bash(cat *.key)

Bash(cat *.p12)

Bash(cat *id_rsa*)

Bash(cat *service-account*.json)

Bash(cat *.ssh/*)

Bash(git push --force:*)

Bash(git push -f:*)

Bash(git push --delete:*)

Bash(git push --mirror:*)

Bash(git push --prune:*)

Bash(git push --force:*)

Bash(git push -f:*)

Bash(git push --delete:*)

Bash(git push --mirror:*)

Bash(git push --prune:*)

ask (0)

—

allow (29)

Bash(npm run *)

Bash(npx prettier *)

Bash(uv run *)

Bash(git *)

Bash(docker compose *)

Bash(ls *)

Bash(pwd)

Bash(cat *)

Bash(wc *)

Bash(psql:*)

Bash(where:*)

Bash(bun:*)

Bash(claude:*)

Bash(cd:*)

Bash(jq:*)

Bash(test:*)

Bash(python3:*)

Bash(ln:*)

Bash(chmod +x:*)

Bash(npx get-shit-done-cc@latest:*)

WebSearch

WebFetch(domain:github.com)

WebFetch(domain:raw.githubusercontent.com)

WebFetch(domain:developers.openai.com)

mcp__github__create_pull_request

mcp__github__merge_pull_request

mcp__github__update_pull_request_branch

mcp__github__create_branch

mcp__github__pull_request_read

Context tax

Instructions: 2.6kMCP tool schemas (est.): 0Skill metadata: 224Subagent metadata: 310

ALWAYS-LOADED FILES (claude-code)

≡

CLAUDE.md · 83 lines · ~2.6k tok

≡

AGENTS.md · 41 lines · ~682 tok

Estimate: characters ÷ 4 for instruction files and skill/subagent descriptions; MCP schema sizes from typical tool counts. Harnesses with deferred tool loading pay less. Method

Guardrails 4/5

✓

Blocks destructive commands

10 deny/ask rule(s) e.g. Bash(git push --force:*)

✓

Protects secrets

Denies reads like Read(backend/.env)

✓

Pre-tool screening hook

3 PreToolUse hook(s)

✓

No YOLO mode

Permission prompts stay on

✗

Sandbox or ask-first rules

No sandbox and no ask-first rules

Badge

Add to your README:

[![AgentRigs](https://agentrigs.dev/badge/rig/runnithan/claudex-setup.svg)](https://agentrigs.dev/r/runnithan/claudex-setup)

Indexed from commit c71199b1a8b8 on 2026-10-09. Data is structure only — env values and anything secret-looking are stripped.

Similar rigs

Rohankundra2009/claude-agents-forge

Build and run production-ready Claude Code agents with full agent specs, including turn limits, permissions, memory, and tool orchestration.

★ 2 project Claude Code 9 agents 4d ago

Orchestrator 1.3k tok ·

Mationetap/claude-agents-forge

Production-hardened agent system for Claude Code — uses the full agent spec (maxTurns, permissionMode, disallowedTools, Task() orchestration, memory scopes, MCP integration)

★ 0 project Claude Code 9 agents 7mo ago

Orchestrator 1.3k tok ·

Iski08/dotclaude

Multi-agent config for Claude Code with specialized agents and templates to speed code review, refactoring, security audits, tech-lead guidance, and UX evaluations across CI pipelines. 🐙

★ 4 setup Claude Code 5 agents today

Orchestrator 677 tok ·

sami-abdul/claude-predev-setup

A portable system that bootstraps any Claude Code project with production-grade infrastructure: multi-agent pipelines, skills, rules, hooks, and a full-stack development orchestrator inspired by the FullStack-Agent paper.

★ 3 setup Claude Code 12 skills 9 agents 8mo ago

Orchestrator 1.3k tok ·