CJK Multilingual Token Safety Guard
Prevents catastrophic LLM token explosions and 15GB OOM crashes on CJK text with script-aware glyph weighting (~0.7) and F51b chunk guards.
Free
Works with the AI Agents you already use
About this skill
Prevents catastrophic token explosions, memory blowouts, and OOM crashes when processing CJK (Chinese, Japanese, Korean) and multi-script documents. Implements script-aware word counting with CJK glyph weighting (~0.7), enforces F51b hard chunk guards (<8,000 characters) with sentence-boundary splitting, handles unspaced scripts, and guards against mojibake.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account