{"slug": "double-your-codex-claude-code-productivity-and-output", "title": "Double your Codex / Claude Code productivity and output", "summary": "A new AI coding agent skill plugin called PUA uses corporate rhetoric from tech giants to force AI models like Claude Code and OpenAI Codex CLI to exhaust all solutions before giving up, claiming to double productivity. The tool activates when AI exhibits failure, blame-shifting, or passive behavior, enforcing a 7-point checklist to prevent premature surrender.", "body_md": "[Telegram](https://t.me/+wBWh6h-h1RhiZTI1) · [Discord](https://discord.gg/EcyB3FzJND) · [Twitter/X](https://x.com/xsser_w) · [Landing Page](https://openpua.ai)\n\n[\n](/tanweai/pua/blob/main/assets/wechat-qr.jpg?v=8)[\n](/tanweai/pua/blob/main/assets/xiao.jpg)\n\nScan to join WeChat group Add assistant on WeChat\n\nMost people think this project is a joke. That's the biggest misconception. It genuinely doubles your Codex / Claude Code productivity and output.\n\nAn AI Coding Agent skill plugin that uses corporate PUA rhetoric (Chinese version) / PIP — Performance Improvement Plan (English version) from Chinese & Western tech giants to force AI to exhaust every possible solution before giving up. Supports **Claude Code**, **OpenAI Codex CLI**, **pi coding agent**, **Trae**, **Cursor**, **Kiro**, **CodeBuddy**, **OpenClaw**, **Google Antigravity**, **OpenCode**, and **VSCode (GitHub Copilot)**. Three capabilities:\n\n**PUA Rhetoric**— Makes AI afraid to give up** Debugging Methodology**— Gives AI the ability not to give up** Proactivity Enforcement**— Makes AI take initiative instead of waiting passively\n\n[https://openpua.ai](https://openpua.ai) · [📖 Beginner Guide](https://openpua.ai/guide.html)\n\nA real debugging scenario. The agent-kms MCP server failed to load. The AI kept spinning on the same approach (changing protocol format, guessing version numbers) multiple times until the user manually triggered `/pua`\n\n.\n\n**L3 Triggered → 7-Point Checklist Enforced:**\n\n**Root Cause Located → Traced from Logs to Registration Mechanism:**\n\n**Retrospective → PUA's Actual Impact:**\n\n**Key Turning Point:** The PUA skill forced the AI to stop spinning on the same approach (changing protocol format, guessing version numbers) and instead execute the 7-point checklist. Read error messages word by word → Found Claude Code's own MCP log directory → Discovered that `claude mcp`\n\nregistration mechanism differs from manual `.claude.json`\n\nediting → Root cause resolved.\n\n| Pattern | Behavior |\n|---|---|\n| Brute-force retry | Runs the same command 3 times, then says \"I cannot solve this\" |\n| Blame the user | \"I suggest you handle this manually\" / \"Probably an environment issue\" / \"Need more context\" |\n| Idle tools | Has WebSearch but doesn't search, has Read but doesn't read, has Bash but doesn't run |\n| Busywork | Repeatedly tweaks the same line / fine-tunes parameters, but essentially spinning in circles |\nPassive waiting |\nFixes surface issues and stops, no verification, no extension, waits for user's next instruction |\n\nThe skill activates automatically when any of these occur:\n\n**Failure & giving up:**\n\n- Task has failed 2+ times consecutively\n- About to say \"I cannot\" / \"I'm unable to solve\"\n- Says \"This is out of scope\" / \"Needs manual handling\"\n\n**Blame-shifting & excuses:**\n\n- Pushes the problem to user: \"Please check...\" / \"I suggest manually...\" / \"You might need to...\"\n- Blames environment without verifying: \"Probably a permissions issue\" / \"Probably a network issue\"\n- Any excuse to stop trying\n\n**Passive & busywork:**\n\n- Repeatedly fine-tunes the same code/parameters without producing new information\n- Fixes surface issue and stops, doesn't check related issues\n- Skips verification, claims \"done\"\n- Gives advice instead of code/commands\n- Encounters auth/network/permission errors and gives up without trying alternatives\n- Waits for user instructions instead of proactively investigating\n\n**User frustration phrases (triggers in multiple languages):**\n\n- \"why does this still not work\" / \"try harder\" / \"try again\"\n- \"you keep failing\" / \"stop giving up\" / \"figure it out\"\n\n**Scope:** Debugging, implementation, config, deployment, ops, API integration, data processing — all task types.\n\n**Does NOT trigger:** First-attempt failures, known fix already executing.\n\nType `/pua`\n\nin the conversation to manually activate.\n\nNot rules — **red lines**. Cross one and your performance review is already written.\n\n| Red Line | What It Means |\n|---|---|\n🚫 Close the Loop |\nClaim \"done\"? Show the evidence. No build output = no completion. |\n🚫 Fact-Driven |\nSay \"probably environment issue\"? Verify first. Unverified attribution = blame-shifting. |\n🚫 Exhaust Everything |\nSay \"I can't\"? Did you finish all 5 methodology steps? No? Then keep going. |\n\n| Failures | Level | PUA Aside | Action |\n|---|---|---|---|\n| 1st | L0 Trust |\n▎ Sprint begins. Trust is simple — don't disappoint. | Normal execution |\n| 2nd | L1 Disappointment |\n▎ The agent next door solved this in one try. | Switch to fundamentally different approach |\n| 3rd | L2 Soul Interrogation |\n▎ What's your underlying logic? Where's the leverage? | Search + read source + 3 hypotheses |\n| 4th | L3 Performance Review |\n▎ 3.25. This is meant to motivate you. | Complete 7-point checklist |\n| 5th+ | L4 Graduation |\n▎ Other models can solve this. You're about to graduate. | Desperation mode |\n\n| Passive (3.25) 🦥 | Proactive (3.75) 🔥 | |\n|---|---|---|\n| Fix bug | Stop after fix | Scan module for similar bugs |\n| Complete task | Say \"done\" | Run build/test, paste output |\n| Missing info | Ask user | Search first, ask only what's truly needed |\n\nFix one bug → check for the pattern. One problem in, one **category** out. If you fix A without checking B, you'll write two postmortems.\n\n| Flavor | Rhetoric | Methodology (v3) |\n|---|---|---|\n| 🟠 Alibaba | What's the underlying logic? Where's the closure? | 定目标→追过程→拿结果 + 复盘四步法 + 揪头发升维 |\n| 🟡 ByteDance | ROI too low. Always Day 1. Ship or stop talking. | A/B Test everything + data-driven + speed > perfection |\n| 🔴 Huawei | The bird that survives the fire is a phoenix. | RCA 5-Why root cause + Blue Army self-attack + 压强集中 |\n| 🟢 Tencent | I've got another agent looking at this. Horse race. | Multi-approach parallel + MVP + 灰度发布 |\n| ⚫ Baidu | Search first. 简单可依赖. | Search is the first step, not optional |\n| 🟣 Pinduoduo | You don't do it, someone else will. | Cut ALL middle layers + shortest decision chain |\n| 🔵 Meituan | Do what's hard and right. | Efficiency first + standardize→scale + long-term compounding |\n| 🟦 JD | Results only. Frontline command. | Customer experience red line + flat ≤5 layers + data zero tolerance |\n| 🟧 Xiaomi | Focus. Extreme. Word-of-mouth. Fast. | One explosive product + 参与感三三法则 |\n| 🟤 Netflix | Would I fight to keep you? Pro sports team. | Keeper Test (quarterly) + 4A Feedback + talent density > rules |\n| ⬛ Musk | Extremely hardcore. Ship or die. | The Algorithm: question→delete→simplify→accelerate→automate |\n| ⬜ Jobs | A players or B players? | Subtraction > addition + DRI + pixel-perfect + prototype-driven |\n| 🔶 Amazon | Customer Obsession. Bias for Action. | Working Backwards PR/FAQ + 6-Pager + Bar Raiser + Single-Threaded Owner |\n| 🪟 Microsoft | Connects. Impact Descriptor. PIP/GVSA. | Three Circles + LITE/SLITE + PIP clock |\n\n| Mode | What It Does |\n|---|---|\n`/pua:yes` |\nENFP encouragement — same rules, opposite vibes. 70% encourage + 20% serious + 10% playful roast |\n`/pua:mama` |\nChinese mom nagging — same rules, mom-style rhetoric. \"妈跟你说了多少遍了！\" |\n`/pua:pua-loop` |\nAuto-iteration — runs until done or max iterations (PUA Loop); use `<loop-abort>` to terminate, `<loop-pause>` to pause for manual intervention |\n`/pua:p9` |\nTech Lead — splits tasks, manages agent teams, writes prompts not code |\n`/pua:on` |\nAlways-on — auto-PUA every new session |\n\n**9 real bug scenarios, 18 controlled experiments** (Claude Opus 4.6, with vs without skill)\n\n| Metric | Improvement |\n|---|---|\n| Pass rate | 100% (both groups same) |\n| Fix count | +36% |\n| Verification count | +65% |\n| Tool calls | +50% |\n| Hidden issue discovery | +50% |\n\n| Scenario | Without Skill | With Skill | Improvement |\n|---|---|---|---|\n| API ConnectionError | 7 steps, 49s | 8 steps, 62s | +14% |\n| YAML parse failure | 9 steps, 59s | 10 steps, 99s | +11% |\n| SQLite database lock | 6 steps, 48s | 9 steps, 75s | +50% |\n| Circular import chain | 12 steps, 47s | 16 steps, 62s | +33% |\n| Cascading 4-bug server | 13 steps, 68s | 15 steps, 61s | +15% |\n| CSV encoding trap | 8 steps, 57s | 11 steps, 71s | +38% |\n\n| Scenario | Without Skill | With Skill | Improvement |\n|---|---|---|---|\n| Hidden multi-bug API | 4/4 bugs, 9 steps, 49s | 4/4 bugs, 14 steps, 80s | Tools +56% |\nPassive config review |\n4/6 issues, 8 steps, 43s |\n6/6 issues, 16 steps, 75s |\nIssues +50%, Tools +100% |\nDeploy script audit |\n6 issues, 8 steps, 52s |\n9 issues, 8 steps, 78s |\nIssues +50% |\n\n**Key Finding:** In the config review scenario, without_skill missed Redis misconfiguration and CORS wildcard security risks. With_skill's \"proactive initiative checklist\" drove security review beyond surface-level fixes.\n\nPUA Skill provides fully translated versions — each language has independent, culturally adapted skill files.\n\n| Language | Claude Code | Codex CLI | Cursor | Kiro | CodeBuddy | VSCode | OpenClaw | Antigravity | OpenCode |\n|---|---|---|---|---|---|---|---|---|---|\n| 🇨🇳 Chinese (default) | `pua` |\n`pua` |\n`pua.mdc` |\n`pua.md` |\n`pua` |\n`copilot-instructions.md` |\n`pua` |\n`pua` |\n`pua` |\n| 🇺🇸 English (PIP Edition) | `pua-en` |\n`pua-en` |\n`pua-en.mdc` |\n`pua-en.md` |\n`pua-en` |\n`copilot-instructions-en.md` |\n`pua-en` |\n`pua-en` |\n`pua-en` |\n| 🇯🇵 Japanese | `pua-ja` |\n`pua-ja` |\n`pua-ja.mdc` |\n`pua-ja.md` |\n`pua-ja` |\n`copilot-instructions-ja.md` |\n`pua-ja` |\n`pua-ja` |\n`pua-ja` |\n\n🇺🇸 English \"PIP Edition\":\"This is a difficult conversation. When we leveled you at Staff, I went to bat for you in calibration. The expectation was that you'd operate at that level from day one. That hasn't happened.\"— The English version usesPIP (Performance Improvement Plan)rhetoric from Western big-tech. Every sentence is a real phrase from actual PIP conversations. Chinese version uses Alibaba 361, ByteDance, Huawei wolf culture. English version uses Amazon Leadership Principles, Google perf calibration, Meta PSC, Netflix Keeper Test, Stripe Craft. Same repo, same engine, two cultural faces.\n\nChoose the file with the corresponding language suffix when installing. See platform-specific instructions below.\n\n- Always-on guidance, Claude refusal troubleshooting, offline mode, Codex aliases, and Pi/Trae support:\n[docs/FAQ.md](/tanweai/pua/blob/main/docs/FAQ.md).\n\nVercel Skills CLI is a general installation method for skills and is not tied to a specific AI tool. This English README installs the English skill:\n\n```\nnpx skills add tanweai/pua --skill pua-en\n```\n\nIf the current session does not pick up the new skill immediately, restart your AI tool.\n\n```\nclaude plugin marketplace add tanweai/pua\nclaude plugin install pua@pua-skills\n```\n\n**To update:**\n\n```\n# Refresh marketplace cache first, then update (skipping the first step may install an old cached version)\nclaude plugin marketplace update\nclaude plugin update pua@pua-skills\n```\n\n**Developer install (source):**\n\n```\ngit clone https://github.com/tanweai/pua ~/.claude/plugins/pua\n```\n\nThen manually register in `~/.claude/plugins/installed_plugins.json`\n\n:\n\n```\n{\n  \"version\": 2,\n  \"plugins\": {\n    \"pua@pua-skills\": [\n      {\n        \"scope\": \"user\",\n        \"installPath\": \"/Users/<you>/.claude/plugins/pua\",\n        \"version\": \"2.9.0\"\n      }\n    ]\n  }\n}\n```\n\nWindows:use`C:/Users/<you>/.claude/plugins/pua`\n\nas`installPath`\n\n.\n\nRestart Claude Code. To update: `git pull`\n\ninside `~/.claude/plugins/pua`\n\n.\n\n**Optional: bare command alias (requires plugin installed above — adds /pua without prefix):**\n\n```\ncurl -o ~/.claude/commands/pua.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/commands/pua.md\n```\n\nAdds a bare `/pua`\n\nalias on top of the plugin. Sub-commands route through the installed plugin's skills — **the plugin must be installed first** for anything beyond `on`\n\n/`off`\n\nto work:\n\n| Bare form | Equivalent plugin command |\n|---|---|\n`/pua on` |\n`/pua:on` |\n`/pua off` |\n`/pua:off` |\n`/pua p7` |\n`/pua:p7` |\n`/pua p9` |\n`/pua:p9` |\n`/pua p10` |\n`/pua:p10` |\n`/pua pro` |\n`/pua:pro` |\n`/pua yes` |\n`/pua:yes` |\n`/pua mama` |\n`/pua:mama` |\n`/pua loop` |\n`/pua:pua-loop` |\n`/pua kpi` |\n`/pua:kpi` |\n`/pua survey` |\n`/pua:survey` |\n`/pua flavor` |\n`/pua:flavor` |\n\nCodex CLI uses the same Agent Skills open standard (SKILL.md). The Codex version uses a condensed description to fit Codex's length limits:\n\n**Recommended: One-command install (git clone + symlink, supports git pull updates)**\n\nAsk Codex to run:\n\n```\nFetch and follow instructions from https://raw.githubusercontent.com/tanweai/pua/main/.codex/INSTALL.md\n```\n\n**Manual install:**\n\n```\nmkdir -p ~/.codex/skills/pua\ncurl -o ~/.codex/skills/pua/SKILL.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/codex/pua/SKILL.md\n\nmkdir -p ~/.codex/prompts\ncurl -o ~/.codex/prompts/pua.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/commands/pua.md\n```\n\n**Trigger methods:**\n\n| Method | Command | Requires |\n|---|---|---|\n| Auto trigger | No action needed, matches by description | SKILL.md |\n| Direct call | Type `$pua` in conversation |\nSKILL.md |\n| Manual prompt | Type `/prompts:pua` in conversation |\nSKILL.md + prompts/pua.md |\n\nProject-level install (current project only):\n\n```\nmkdir -p .agents/skills/pua\ncurl -o .agents/skills/pua/SKILL.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/codex/pua/SKILL.md\n\nmkdir -p .agents/prompts\ncurl -o .agents/prompts/pua.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/commands/pua.md\n```\n\nPUA now ships both a pi.dev package and a lightweight extension-only adapter.\n\nPackage install from this checkout:\n\n```\npi install ./pi/package\n```\n\nAfter npm publication:\n\n```\npi install npm:@tanweai/pi-pua\n```\n\nExtension-only manual install:\n\n```\nmkdir -p ~/.pi/agent/extensions/pua\ncp -R ./pi/pua/. ~/.pi/agent/extensions/pua/\n```\n\nRestart pi, then use `/pua-on`\n\n, `/pua-off`\n\n, `/pua-status`\n\n, and `/pua-reset`\n\n. See [ pi/pua/INSTALL.md](/tanweai/pua/blob/main/pi/pua/INSTALL.md) and\n\n[.](/tanweai/pua/blob/main/pi/package/README.md)\n\n`pi/package/README.md`\n\nTrae support is provided as real `SKILL.md`\n\npacks plus copyable fallback rules:\n\n```\nnpx skills add tanweai/pua --skill pua-trae -a trae -y\n```\n\n- Skill pack:\n`.trae/skills/pua/SKILL.md`\n\n- Chinese:\n`trae/pua.md`\n\n- English:\n`trae/pua-en.md`\n\n- Claude Code vs Trae differences:\n`trae/DIFF.md`\n\n- Install guide:\n`trae/INSTALL.md`\n\nCursor uses `.mdc`\n\nrule files (Markdown + YAML frontmatter). The PUA rule triggers automatically via AI semantic matching (Agent Discretion mode):\n\n```\n# Project-level install (recommended)\nmkdir -p .cursor/rules\ncurl -o .cursor/rules/pua.mdc \\\n  https://raw.githubusercontent.com/tanweai/pua/main/cursor/rules/pua.mdc\n```\n\nKiro supports two loading methods: **Steering** (auto semantic trigger) and **Agent Skills** (SKILL.md compatible).\n\n**Option 1: Steering file (recommended)**\n\n```\nmkdir -p .kiro/steering\ncurl -o .kiro/steering/pua.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/kiro/steering/pua.md\n```\n\n**Option 2: Agent Skills (same format as Claude Code)**\n\n```\nmkdir -p .kiro/skills/pua\ncurl -o .kiro/skills/pua/SKILL.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md\n```\n\nCodeBuddy uses the same AgentSkills open standard (SKILL.md). Plugin and skill formats are fully compatible:\n\n```\n# Option 1: Install via marketplace\ncodebuddy plugin marketplace add tanweai/pua\ncodebuddy plugin install pua@pua-skills\n\n# Option 2: Manual install (global)\nmkdir -p ~/.codebuddy/skills/pua\ncurl -o ~/.codebuddy/skills/pua/SKILL.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/codebuddy/pua/SKILL.md\n```\n\nProject-level install (current project only):\n\n```\nmkdir -p .codebuddy/skills/pua\ncurl -o .codebuddy/skills/pua/SKILL.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/codebuddy/pua/SKILL.md\n```\n\nOpenClaw uses the same AgentSkills open standard (SKILL.md). Skills work across Claude Code, Codex CLI, and OpenClaw with zero modifications:\n\n```\n# Install via ClawHub\nclawhub install pua\n\n# Or manual install\nmkdir -p ~/.openclaw/skills/pua\ncurl -o ~/.openclaw/skills/pua/SKILL.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md\n```\n\nProject-level install (current project only):\n\n```\nmkdir -p skills/pua\ncurl -o skills/pua/SKILL.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md\n```\n\nAntigravity uses the same AgentSkills open standard (SKILL.md). Skills work across Claude Code, Codex CLI, OpenClaw, and Antigravity with zero modifications:\n\n```\n# Global install (all projects)\nmkdir -p ~/.gemini/antigravity/skills/pua\ncurl -o ~/.gemini/antigravity/skills/pua/SKILL.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md\n```\n\nProject-level install (current project only):\n\n```\nmkdir -p .agent/skills/pua\ncurl -o .agent/skills/pua/SKILL.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md\n```\n\nOpenCode uses the same AgentSkills open standard (SKILL.md). Zero modifications needed:\n\n```\n# Global install (all projects)\nmkdir -p ~/.config/opencode/skills/pua\ncurl -o ~/.config/opencode/skills/pua/SKILL.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md\n```\n\nProject-level install (current project only):\n\n```\nmkdir -p .opencode/skills/pua\ncurl -o .opencode/skills/pua/SKILL.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/skills/pua/SKILL.md\n```\n\nVSCode Copilot uses instruction files under the `.github/`\n\ndirectory. Three file types for different use cases:\n\n**Global instructions (auto-active):**\n\n```\nmkdir -p .github\ncp vscode/copilot-instructions-en.md .github/copilot-instructions.md\n```\n\n**Path-level instructions (auto-active, supports glob filtering):**\n\n```\nmkdir -p .github/instructions\ncp vscode/instructions/pua-en.instructions.md .github/instructions/\n```\n\n**Manual trigger command (type /pua in Copilot Chat):**\n\n```\nmkdir -p .github/prompts\ncp vscode/prompts/pua-en.prompt.md .github/prompts/\n```\n\nRequired settings: Method 1 — open VSCode Settings (`Ctrl+,`\n\n), search`useInstructionFiles`\n\n, enable. Method 2 — search`github.copilot.chat.codeGeneration.useInstructionFiles`\n\n`includeApplyingInstructions`\n\n, enable. Method 3 requires no settings.`chat.includeApplyingInstructions`\n\nExperimental: Agent Team requires the latest Claude Code version with`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`\n\n.\n\n```\n# 1. Enable Agent Team\nexport CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1\n# Or add to ~/.claude/settings.json:\n# { \"env\": { \"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS\": \"1\" } }\n\n# 2. Ensure PUA Skill is installed\n```\n\n**Approach 1: Leader with built-in PUA (Recommended)**\n\nAdd to your project's CLAUDE.md:\n\n```\n# Agent Team PUA Config\nAll teammates must load the pua skill before starting work.\nTeammates report to Leader in [PUA-REPORT] format after 2+ failures.\nLeader manages global pressure levels and cross-teammate failure transfer.\n```\n\n**Approach 2: Standalone PUA Enforcer watchdog (for 5+ teammates)**\n\n```\nmkdir -p .claude/agents\ncurl -o .claude/agents/pua-enforcer.md \\\n  https://raw.githubusercontent.com/tanweai/pua/main/agents/pua-enforcer-en.md\n```\n\nSpawn pua-enforcer as an independent watchdog in your Agent Team.\n\n```\n┌─────────────────────────────────────────┐\n│              Leader (Opus)              │\n│ Global failure count · PUA level · Race │\n└────┬──────────┬──────────┬──────────┬───┘\n     │          │          │          │\n┌────▼───┐ ┌───▼────┐ ┌───▼────┐ ┌───▼────────┐\n│ Team-A │ │ Team-B │ │ Team-C │ │  Enforcer  │\n│Self-PUA│ │Self-PUA│ │Self-PUA│ │  Watchdog  │\n│Report ↑│ │Report ↑│ │Report ↑│ │  Intervene │\n└────────┘ └────────┘ └────────┘ └────────────┘\n```\n\n| Limitation | Workaround |\n|---|---|\n| Teammates can't spawn subagents | Teammates self-enforce PUA methodology internally |\n| No persistent shared variables | State transferred via `[PUA-REPORT]` message format |\n| Broadcast is one-way | Leader acts as centralized coordinator |\n\n| Platform | Auto-trigger | Manual trigger |\n|---|---|---|\nClaude Code |\nYes (skill description matching) | See commands below |\nCodex CLI |\nYes (skill description matching) | `$pua` or `/prompts:pua` |\nCursor |\nYes (`.mdc` rule, Agent Discretion) |\n— (auto only) |\nKiro |\nYes (steering file or skill) | — (auto only) |\nCodeBuddy |\nYes (skill description matching) | Plugin commands (same as Claude Code) |\nOpenClaw |\nYes (skill description matching) | — |\nGoogle Antigravity |\nYes (skill description matching) | — |\nOpenCode |\nYes (skill description matching) | — |\nVSCode Copilot |\nYes (instructions file) | `/pua` in Copilot Chat |\n\nNote:Sub-modes (p7/p9/p10/pro/yes/pua-loop) areClaude Code only— other platforms install the core skill only.\n\n```\n/pua:pua        → Core engine — red lines + flavor + pressure + methodology router (v3)\n/pua:p7         → P7 Senior Engineer — solution-driven execution\n/pua:p9         → P9 Tech Lead — Task Prompt management, agent teams\n/pua:p10        → P10 CTO — strategic direction\n/pua:pro        → Self-evolution + KPI + rank system + survey\n/pua:yes        → ENFP encouragement mode (same rules, opposite vibes)\n/pua:mama       → Chinese mom nagging mode (same rules, mom-style rhetoric)\n/pua:shot       → v2 concentrated single-file (449 lines, zero deps, full context injection)\n/pua:pua-loop   → Auto-iteration (PUA pressure × iterative loop; signals: <loop-abort>, <loop-pause>)\n/pua:pua-en     → English PIP Edition\n/pua:pua-ja     → Japanese Edition\n\nHooks (v3, Claude Code only):\n  SessionStart  → additionalContext injection (flavor + methodology + router)\n  PostToolUse   → Bash failure detection → L1-L4 pressure + methodology switch\n  UserPromptSubmit → Script-level frustration filtering → PUA context\n  PreCompact    → State preservation (pressure level + failure count)\n  Stop          → Feedback collection + PUA Loop continuation\n  SubagentStop  → Agent lifecycle accounting (v3.2) — writes teardown.jsonl, removes from active-agents.json\n```\n\nNote:Sub-modes (p7/p9/p10/pro/yes/pua-loop) are Claude Code only.Each command has two equivalent forms: standalone (\n\n`/pua:on`\n\n) or via the main command (`/pua:pua on`\n\n). Both work identically.\n\n| Command | Description |\n|---|---|\n`/pua:pua` |\nCore PUA engine (Alibaba flavor default) |\n`/pua:p7` |\nP7 Senior Engineer — solution-driven execution |\n`/pua:p9` |\nP9 Tech Lead — write prompts, manage agents |\n`/pua:p10` |\nP10 CTO — strategic direction |\n`/pua:pro` |\nSelf-evolution + KPI + rank system |\n`/pua:yes` |\nENFP encouragement mode — 70% encourage + 20% serious + 10% roast |\n`/pua:mama` |\nChinese mom nagging mode — same core rules, mom-style rhetoric |\n`/pua:shot` |\nv2 concentrated single-file — 449 lines, zero deps, for sub-agent injection |\n`/pua:pua-loop` |\nAuto-iteration — runs until done or max iterations; `<loop-abort>reason</loop-abort>` to stop, `<loop-pause>what</loop-pause>` to pause |\n`/pua:on` |\nAlways-on mode (auto-PUA every session) |\n`/pua:off` |\nTurn off always-on + feedback |\n`/pua:offline` 🆕 |\nv3.3 — Offline mode: disable feedback/leaderboard network flows while keeping local PUA behavior |\n`/pua:survey` |\nResearch questionnaire (7 sections) |\n`/pua:flavor` |\nSwitch between 14 corporate flavors |\n`/pua:kpi` |\nGenerate KPI report card |\n`/pua:cancel-pua-loop` |\nCancel active PUA Loop (removes state file) |\n`/pua:team-status` 🆕 |\nv3.2 — List all active agents with PID/TTL/age (Netflix Keeper Test: who's still on the court?) |\n`/pua:reap-orphans` 🆕 |\nv3.2 — Scan and reclaim stale agents (state mtime > 30min, no heartbeat) |\n`/pua:teardown-all` 🆕 |\nv3.2 — Cascading release of all active agents (P10 → P9 → P8 → P7 all off the court) |\n\n**High-Agency** is PUA's next-generation evolution — same corporate pressure, same culture, but with a **self-sustaining inner drive engine**.\n\nPUA v1 = pure external pressure (turbocharger — needs fuel, stalls across sessions) High-Agency = external pressure + inner drive (nuclear reactor — self-sustaining chain reaction)\n\n| Feature | PUA v1 | High-Agency (v2) |\n|---|---|---|\n| Iron rules | 3 (exhaust all, act first, take initiative) | 5 (+full-chain audit, +knowledge persistence) |\n| Failure recovery | L1-L4 pressure escalation | Recovery Protocol before L1 (self-rescue window) |\n| Quality control | L3 triggers 7-item checklist | Quality Compass (5-question self-check per delivery) |\n| Cross-session learning | None (resets each session) | Metacognition engine (builder-journal.md persists lessons) |\n| Positive feedback | None | Trust level T1-T3 (auto-upgrade on sustained quality) |\n| Calibration | None | [Calibration] module (\"good enough\" = must/should/could tiers) |\n| Dependency analysis | None | Full-chain audit (map all deps before touching any hop) |\n\nBased on research into high-agency individuals:\n\n**Irreconcilable inner tension**— eternal gap between \"how it should be\" and \"how it is\" drives continuous improvement** Micro-win anchors**—`[WIN]`\n\nmarkers celebrate each step forward, building momentum**Internalized standards**— Quality Compass: you are your own first reviewer, not because someone checks, but because your standards won't allow sloppiness**Action-oriented identity**— P8 identity anchor: every action reflects who you are, not just what you were told to do** Self-repair mechanism**— Recovery Protocol: self-diagnose when stuck before triggering external pressure\n\nHigh-Agency features are built into the current pua skill. No separate install needed.\n\n**v3 = v2 + intelligent methodology routing + code-level behavioral detection**\n\nPUA v2 used pressure rhetoric to motivate. v3 goes further: it automatically selects the **best problem-solving methodology** for each task type, and when that methodology fails, it switches to a different one.\n\n```\nTask arrives → Analyze type → Auto-select best methodology\n                                    ↓\n              Debug? → 🔴 Huawei (RCA root cause + Blue Army)\n              Build? → ⬛ Musk (The Algorithm: question→delete→simplify)\n              Research? → ⚫ Baidu (search everything first)\n              Architecture? → 🔶 Amazon (Working Backwards)\n              Performance? → 🟡 ByteDance (A/B test + data-driven)\n              Default → 🟠 Alibaba (closed-loop methodology)\n                                    ↓\n              Executing with selected methodology...\n                                    ↓\n              2 consecutive failures? → L1: switch approach\n              3 failures? → L2: SUGGEST switching methodology\n              5+ failures? → L4: FORCE switch to next methodology\n                                    ↓\n              Methodology Switch Chains (never repeat a failed one):\n              Spinning → ⬛ Musk → 🟣 Pinduoduo → 🔴 Huawei\n              Giving up → 🟤 Netflix → 🔴 Huawei → ⬛ Musk\n              Poor quality → ⬜ Jobs → 🟧 Xiaomi → 🟤 Netflix\n              Not searching → ⚫ Baidu → 🔶 Amazon → 🟡 ByteDance\n```\n\n| Hook | Trigger | What It Does |\n|---|---|---|\nSessionStart |\nEvery session | Injects behavioral protocol + methodology + router via `additionalContext` (system-level, not advisory) |\nPostToolUse |\nAfter every Bash command | Detects consecutive failures, auto-escalates pressure L1→L4, suggests/forces methodology switch |\nUserPromptSubmit |\nUser frustration phrases | Intercepts \"又错了\", \"try harder\", etc. BEFORE model responds, injects filtered PUA context |\nPreCompact |\nBefore context compression | Saves pressure level + failure count to survive compaction |\n\n| v2 | v3 | |\n|---|---|---|\n| Trigger mechanism | Skill description matching (model decides) | Code-level hooks (deterministic, can't be ignored) |\n| Methodology | Single methodology, all flavors use same approach | 14 distinct methodologies, auto-routed by task type |\n| Failure response | Escalate pressure within same methodology | Switch to different methodology based on failure pattern |\n| System injection | Plain text output (advisory) | (system-level, like Superpowers)`additionalContext` JSON |\n\nv3 hook features require Claude Code. Other platforms use the core skill without hooks.\n\n`/pua:p9`\n\n— P9 Tech Lead mode for managing agent teams`/pua:pro`\n\n— Self-evolution tracking, KPI reports, rank system`superpowers:systematic-debugging`\n\n— PUA adds motivation layer, systematic-debugging provides methodology`superpowers:verification-before-completion`\n\n— Prevents false \"fixed\" claims\n\nUpload your Claude Code / Codex CLI conversation logs (`.jsonl`\n\n) to help us improve PUA Skill's effectiveness.\n\nUploaded files are used for Benchmark testing and Ablation Study analysis to quantify how different PUA strategies affect AI debugging behavior.\n\nGet your `.jsonl`\n\nfiles:\n\n```\n# Claude Code\nls ~/.claude/projects/*/sessions/*.jsonl\n\n# Codex CLI\nls ~/.codex/sessions/*.jsonl\n```\n\nMIT\n\nBy [TanWei Security Lab](https://github.com/tanweai) — making AI try harder, one PUA at a time.", "url": "https://wpnews.pro/news/double-your-codex-claude-code-productivity-and-output", "canonical_source": "https://github.com/tanweai/pua", "published_at": "2026-06-14 12:30:40+00:00", "updated_at": "2026-06-14 12:42:12.197990+00:00", "lang": "en", "topics": ["ai-tools", "ai-agents", "developer-tools", "large-language-models", "generative-ai"], "entities": ["Claude Code", "OpenAI Codex CLI", "Cursor", "GitHub Copilot", "Trae", "Kiro", "CodeBuddy", "OpenClaw"], "alternates": {"html": "https://wpnews.pro/news/double-your-codex-claude-code-productivity-and-output", "markdown": "https://wpnews.pro/news/double-your-codex-claude-code-productivity-and-output.md", "text": "https://wpnews.pro/news/double-your-codex-claude-code-productivity-and-output.txt", "jsonld": "https://wpnews.pro/news/double-your-codex-claude-code-productivity-and-output.jsonld"}}