Agent skill · alinaqi
context-shunt
Offload large / multi-file reads to a cheap worker model so raw files never enter Claude's context (token savings)
What it needs
About 1k tokens when loaded.
What this skill does
Context Shunt — Read Cheap, Keep Context Small Reading big files into context is the most expensive thing an agent does for the least reasoning value. The shunt hands those reads to a cheap worker model (bulk-read) that answers a question about the files and returns a compact summary. The raw bytes never enter this session's context. This is orthogonal to whole-turn routing (srooter / route-task): those pick the model for the turn; the shunt trims what a tool call pulls into context when the turn is legitimately here. Decision: read raw, shunt, or graph? Editing this exact file — read it raw. You need every line; never edit against a summary. A fact/answer across large or many files — bulk-read "<question>" file.... A code symbol (function/class/route) — getcodesnippet(qualifiedname): free and exact. Small file (under threshold) you need in full — read it raw. A shunt answer is for understanding, not for producing a diff. Usage bulk-read prints structured bullets citing path:line, or NOT FOUND IN PROVIDED FILES. A token-savings report goes to stderr. Configuration Env vars or ~/.claude/shunt.conf (see templates/shunt.conf): SHUNT — on/off master switch for the PreToolUse hook. SHUNTMINLINES — large-read threshold (default 350). SHUNTMODE — suggest (default) / block / off for the hook's large-read action. SHUNTGRAPHNUDGE — on/off once-per-session graph nudge. SHUNTMODEL — worker command (default deepseek --flash; also gemini-api --flash-lite, qwen3, glm). The context-shunt-gate PreToolUse hook enforces the thresholds; this skill tells you when to reach for bulk-read yourself.
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills alinaqi/context-shunt