context

Conserve tokens with read and edit discipline during complex tasks.

2|2|Updated Mar 21, 2025
One-click install
npx skills add https://github.com/MeshJS/governance --skill context-meshjs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: context
Source: https://github.com/MeshJS/governance/tree/main/.claude/skills/context
Command: npx skills add https://github.com/MeshJS/governance --skill context-meshjs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Context window conservation rules. Invoke when approaching context limits or before large tasks.

Core Features & Use Cases

  • Grep first, read second to minimize unnecessary reads.
  • Narrow reads with offset/limit to keep context small.
  • One read per edit to reduce redundancy and errors.
  • Parallelize reads and edits when multiple files are involved.
  • Read and edit discipline guide to maintain efficiency and accuracy.

Quick Start

Apply the context conservation rules before starting a large task to maximize token efficiency.

Frequently Asked Questions about context

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I reduce token usage when performing multi-file edits in an AI-assisted workflow?

To reduce token usage during multi-file edits, apply surgical read discipline using offset and limit parameters, and execute single edits or replace_all operations. This minimizes unnecessary token consumption while preserving accuracy.

What is the best way to conserve context window limits during long-running explorations?

Conserving context window limits involves using a grep first, read second methodology. Narrowing reads with offset and limit keeps context small, while parallelizing reads and edits maintains efficiency during complex explorations.

When should I apply context conservation rules for AI-assisted tasks?

Apply context conservation rules when approaching context window limits or before starting large tasks. Invoking these rules before high token cost operations like multi-file edits or long-running explorations maximizes token efficiency.

Why does reading entire files waste tokens before editing?

Reading entire files wastes tokens by loading unnecessary data into the context window. Using surgical reads with offset and limit, and enforcing one read per edit, reduces redundancy and prevents context overflow.

Can I parallelize file reads and edits to maximize productive work?

You can parallelize reads and edits when multiple files are involved to maximize productive work. Combining parallel operations with read and edit discipline maintains efficiency and reduces overall token usage.

Does grep first, read second discipline work for high token cost tasks?

Grep first, read second discipline works for high token cost tasks by filtering content before reading. This approach minimizes unnecessary reads, keeping context small and optimizing token usage during complex workflows.