← Back to list
Layered Context Loading
L0/L1/L2 three-layer context protocol — cuts token consumption on /resume boot.
8.3Overall rating
0Views
0Downloads
35Stars
Installation
🤖 Install via AI
Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.
Install the "Layered Context Loading" skill by following the instructions at https://skill123.me/install/layered-context.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/layered-context.sh | bash
📦 Download ZIP
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v3.7.1 · 2 KB🛡 Dynamic test
—
Not live-tested yet — this skill is rated on static analysis only.
About this skill
MUSE's token-economy layer: load a 10-line summary first, escalate only when the decision tree says to. Borrowed from ByteDance's OpenViking and made plain-Markdown.
Documentation
MUSE's token-economy layer: load a 10-line summary first, escalate only when the decision tree says to. Borrowed from ByteDance's OpenViking and made plain-Markdown.
Score breakdown
Trigger
8.0
Activates on /resume boot — clear, narrow scope.
Structure
9.0
Why → Three Layers → L0 Format → Boot Sequence → Decision Tree → Maintenance: textbook spec structure.
Workflow
8.5
The decision tree for when to upgrade a layer is directly actionable.
Content
9.0
Concrete L0 line format and boot sequence; inspired by ByteDance OpenViking architecture.
Engineering
7.5
Pure protocol skill, no scripts — the L0 format is the engineering.
Security
8.0
Explicit bloat-check discipline prevents context stuffing.
MUSE's token-economy layer: load a 10-line summary first, escalate only when the decision tree says to. Borrowed from ByteDance's OpenViking and made plain-Markdown.
Assessment methodology
Assessment in progress
This skill has not been assessed yet — use with caution.
Version history
v3.7.1
2026-09-26
— Imported from GitHub myths-labs/muse