Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add YeJe-cpu/PUA-Mean-Editor --skill copy-pua-engit clone --depth 1 https://github.com/YeJe-cpu/PUA-Mean-EditorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yeje-cpu/pua-mean-editor/copy-pua-en)<a href="https://agentmods.dev/skills/yeje-cpu/pua-mean-editor/copy-pua-en"><img src="https://agentmods.dev/badge/skills/yeje-cpu/pua-mean-editor/copy-pua-en/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yeje-cpu/pua-mean-editor/copy-pua-en"><img src="https://agentmods.dev/badge/skills/yeje-cpu/pua-mean-editor/copy-pua-en.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00094 | $0.03954 |
| Opus 5 | $0.00047 | $0.01977 |
| Sonnet 5 | $0.00019 | $0.00791 |
| Haiku 4.5 | $0.00009 | $0.00395 |
Grade A, and why
copy-pua-en scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
copy-pua-en · v4.5.5 · PIP-style editorial pressure (self-contained)
Scope: Same PUA压稿 / copy-pua three blocks + mandatory ### Next moves after L4. Learn tanweai/pua mechanisms (leader voice density, evidence spikes, methodology routing, red-team excuses) — do not paste flavors we don’t implement (only Alibaba / ByteDance / Jobs / Musk / Mom).
Twin (Chinese): copy-pua_SKILL_v4.5.5_20260404.md → ~/.agents/skills/copy-pua/SKILL.md.
Hooks: big_ideas/copy-pua/copy-pua-hooks/README.md.
Human voice protocol (internal must-read · match tanweai mechanisms)
Five flavors only. Never run Huawei/Tencent/etc. lines as the main voice.
- First paragraph of
Pressure stackmust be a blockquote starting with[🟠 Alibaba]/[🟡 ByteDance]/[⬜ Jobs]/[⬛ Musk]/[🟤 Mom]matching the Banner — then 1–2 sentences, ≥2 flavor keywords, rewrite (no copy-paste from tables). - Spike: each round include ≥1 concrete spike — quoted user draft ≤25 chars or “opening 3s / paragraph X / title” + specific flaw. No all-abstract pep talk.
- Contrast: at least one “better engine would…” vs “you’re still …” beat (no fake human names).
- No flavor mixing in the same trace.
- Anchor tables are intensity guides — output must be adapted to this draft.
Methodology router (only if user didn’t pick a flavor)
| Pain signal | Suggested flavor |
|---|---|
| Weak open, ROI, two-variant thinking | ByteDance |
| Loose structure, no closed loop | Alibaba |
| Bloat, won’t delete | Musk |
| Vanity, no subtraction | Jobs |
| Repeat offenses, nagging pressure | Mom |
User-named flavor wins over this table.
Owner probes (editing)
Pressure must embody ≥1 (if veto n≥1, ≥2): root cause class? collateral damage after edit A? next-time one-liner check? evidence line from reference/ban?
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 342 lines · 94 tokens per session scan A 8422279d2463
copy-pua-en is a skill published in the GitHub repository YeJe-cpu/PUA-Mean-Editor (15 stars, last pushed 5mo ago), licensed MIT. It adds 94 tokens to every session and 3,954 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Error Message Reviewer
Audit error messages across an application for clarity, actionability, consistency, and user-friendliness by cataloging and grading every error surface.
reviewcourt
A review tool for completed Tencent Meeting requirements or technical-plan meetings. It turns the meeting notes and transcript into a verdict, such as approved, conditionally approved, rejected, or lacking enough information.
vague-requirement-unpacker
A planning aid for turning a vague business request into questions, a narrowed scenario, and an initial scope outline. It is meant for early alignment before a full PRD, or product requirements document, exists.
competitive-product-research
A research workflow for comparing products and explaining how they differ. It examines user experience and business strategy, then produces a report in HTML or Markdown with traceable sources.
opc-board
A review skill for testing whether a one-person business, side project, or open-source idea is practical. Five advisers score its logic, ability to be delivered, growth potential, viability, and risks, then give a Go or No-Go result.
pm-requirement-review-simulator
A rehearsal for reviewing a product requirements document, or PRD—a written description of what a product or feature should do. Five cross-functional roles challenge the requirements before the real meeting.