context-audit

Audit session context and report largest contributors to usage.

4|1|Updated May 31, 2015

Search Tags:#context #optimization #audit #memory #efficiency #conversational-ai #waste-detection

Ready to run

npx skills add https://github.com/samcdavid/dotfiles --skill context-audit-samcdavid

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: context-audit
Source: https://github.com/samcdavid/dotfiles/tree/main/claude/skills/context-audit
Command: npx skills add https://github.com/samcdavid/dotfiles --skill context-audit-samcdavid

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audits the conversation context to identify what's consuming the context window and helps reclaim available space by flagging waste and offering to compact or shed load.

Core Features & Use Cases

Inventory current context: CLAUDE.md files, rules, loaded tools, and recent turns to understand context consumption.
Waste identification: detect stale reads, oversized outputs, duplicated context, and unused data.
Actionable recommendations: propose compact or focused context reduction, or starting a fresh session when needed.

Quick Start

Run a context audit on the active session to reveal top contributors to context usage and suggested reductions.

Frequently Asked Questions about context-audit

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

FAQPage Schema

How do I audit conversation context to find what is consuming the context window?▼

Audit conversation context by inventorying loaded CLAUDE.md files, rules, skill definitions, file reads, tool results, and conversation turns to identify the largest contributors to context usage. The audit generates a structured report detailing top space consumers and detected waste types.

What is context window waste detection in conversational AI?▼

Context window waste detection identifies stale reads, oversized outputs, duplicated context, and unused data occupying valuable space. This process flags unnecessary items consuming context bandwidth, enabling targeted compaction or load shedding to optimize long-running sessions.

How do I reduce context usage in long-running AI sessions?▼

Reduce context usage in long-running sessions by applying actionable recommendations from the audit report, which proposes compacting existing context or shedding load. The Skill requires explicit user confirmation before applying any context reduction changes.

Can I identify which file reads or tool outputs are taking up the most context space?▼

Identify specific file reads and tool outputs consuming context space by running an audit on the active session. The resulting structured report details the largest contributors to context usage, highlighting specific items for potential removal or compaction.

When should I start a fresh conversational AI session instead of compacting context?▼

Start a fresh conversational AI session when the audit report recommends it, specifically when context reduction through compaction is insufficient to reclaim necessary bandwidth. This action is suggested alongside compact or focused context reduction options during long-running sessions.

Does the context audit automatically delete unused data from the session?▼

The context audit does not automatically delete unused data from the session. It outputs a structured report with recommended actions for compaction or shedding load, requiring explicit user confirmation before applying any changes to the context window.