PsychQuant/codex-pro
Advanced rewrite of openai/codex-plugin-cc — Claude Code marketplace with codex-pro plugin (setup + batch skills). Ensemble pattern, hard timeouts, circuit breaker, structured observability.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code
$ npx degit PsychQuant/codex-pro/.claude ./rig-codex-pro # 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.
$ npx degit PsychQuant/codex-pro/.agents/skills/spectra-apply .claude/skills/spectra-apply $ npx degit PsychQuant/codex-pro/.agents/skills/spectra-archive .claude/skills/spectra-archive $ npx degit PsychQuant/codex-pro/.agents/skills/spectra-ask .claude/skills/spectra-ask $ npx degit PsychQuant/codex-pro/.agents/skills/spectra-audit .claude/skills/spectra-audit $ npx degit PsychQuant/codex-pro/.agents/skills/spectra-commit .claude/skills/spectra-commit $ npx degit PsychQuant/codex-pro/.agents/skills/spectra-debug .claude/skills/spectra-debug $ npx degit PsychQuant/codex-pro/.agents/skills/spectra-discuss .claude/skills/spectra-discuss $ npx degit PsychQuant/codex-pro/.agents/skills/spectra-drift .claude/skills/spectra-drift $ npx degit PsychQuant/codex-pro/.agents/skills/spectra-ingest .claude/skills/spectra-ingest $ npx degit PsychQuant/codex-pro/.agents/skills/spectra-propose .claude/skills/spectra-propose $ npx degit PsychQuant/codex-pro/.claude/skills/spectra-analyze .claude/skills/spectra-analyze $ npx degit PsychQuant/codex-pro/.claude/skills/spectra-verify .claude/skills/spectra-verify $ npx degit PsychQuant/codex-pro/.codex/skills/codex-adversarial-review .claude/skills/codex-adversarial-review $ npx degit PsychQuant/codex-pro/.codex/skills/codex-batch .claude/skills/codex-batch $ npx degit PsychQuant/codex-pro/.codex/skills/codex-cancel .claude/skills/codex-cancel $ npx degit PsychQuant/codex-pro/.codex/skills/codex-config .claude/skills/codex-config $ npx degit PsychQuant/codex-pro/.codex/skills/codex-rescue .claude/skills/codex-rescue $ npx degit PsychQuant/codex-pro/.codex/skills/codex-result .claude/skills/codex-result $ npx degit PsychQuant/codex-pro/.codex/skills/codex-review .claude/skills/codex-review $ npx degit PsychQuant/codex-pro/.codex/skills/codex-setup .claude/skills/codex-setup $ npx degit PsychQuant/codex-pro/.codex/skills/codex-status .claude/skills/codex-status
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 (21)
Similar rigs
PsychQuant/claude-code-ltm
Claude Code 的長期記憶 — 在 ~/.claude/projects 逐字記錄之上的可拋棄索引與可插拔記憶策略（全本機）
Skill Collector 9.5k tok ·
PsychQuant/claude-hot-limit
防 fan-out 暴衝撞 Anthropic acceleration-limit / short-burst 節流（429/529）的 Claude Code plugin（自帶 marketplace）。pacing-guard PreToolUse hook：burst 超量 deny、Fable 5 開 Workflow deny、間隔太近 sleep、寬 fan-out 建議 pin 便宜 model；trip-recorder 撞牆記錄 + rate-limit
Skill Collector 4.4k tok ·
PsychQuant/che-ical-mcp
macOS Calendar & Reminders MCP server (29 tools) — native Swift EventKit for Claude Desktop & Code. Events + reminders CRUD, recurring, batch ops, conflict & duplicate detection, per-event timezone, undo/redo, #tags, --cli mode, SwiftUI --s
Skill Collector 5.9k tok ·
chaseai-yt/claudex-loop
Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan before a line of code exists, then swap jobs to build it. Whoever built it never gr
Minimalist 272 tok ·