Skip to content
Development
Skill

/context-shunt

Offload large / multi-file reads to a cheap worker model so raw files never enter Claude's context (token savings)

From plugin
maggy
71073 skills1 agent25 commands1 hook

Claude Code

$ npx -y skills add alinaqi/maggy --skill context-shunt --agent claude-code

SKILL.md

context-shunt.SKILL.md
name: context-shunt
description: Offload large / multi-file reads to a cheap worker model so raw files never enter Claude's context (token savings)
when-to-use: When answering a question that requires reading large or many files, reviewing logs, or scanning generated output — anything you don't need to edit
user-invocable: false
effort: low

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)** — `get_code_snippet(qualified_name)`: 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 "how does token refresh work?" src/auth/session.ts src/auth/refresh.ts
bulk-read "which config keys are read at startup?" $(git ls-files 'config/*.yaml')

`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.
  • `SHUNT_MIN_LINES` — large-read threshold (default 350).
  • `SHUNT_MODE` — `suggest` (default) / `block` / `off` for the hook's large-read action.
  • `SHUNT_GRAPH_NUDGE` — `on`/`off` once-per-session graph nudge.
  • `SHUNT_MODEL` — 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.

Read more
@alinaqi
Ships withmaggy

Turn Claude Code into a self-reviewing, test-enforced engineering system that remembers context across sessions — then route work across 13 models from a single dashboard.

71073 skills1 agent
Get the whole plugin

Stars on GitHub

Momentum

stars in total
710
Star history of alinaqi/maggy on GitHub, a chart by star-history.com

Other skills on maggy.

aeo-optimization

aeo-optimization

AI Engine Optimization - semantic triples, page templates, content clusters for AI citations

@alinaqi@alinaqiInstall Skill
agent-teams

agent-teams

Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement

@alinaqi@alinaqiInstall Skill
ai-models

ai-models

Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate

@alinaqi@alinaqiInstall Skill
android-kotlin

android-kotlin

Android Kotlin development with Coroutines, Jetpack Compose, Hilt, and MockK testing

@alinaqi@alinaqiInstall Skill

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills11d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc12d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react2d252k
@facebook@facebookInstall Skill

Questions about context-shunt.

Which coding agents can use context-shunt?
context-shunt installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.