skills.rest
InsightfulAnalytics
InsightfulAnalyticsCOMMUNITY
Explore all skills by this author →
GitHub

audit-context

Reviews agent configuration and memory files to recommend context improvements.

6|3|Updated Jul 4, 2026
Search Tags:#audit#codex#context engineering#claude.md#agents.md#agent configuration#memory files
One-click install
npx skills add https://github.com/InsightfulAnalytics/PBI_Agentic_Dev --skill audit-context-insightfulanalytics
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: audit-context
Source: https://github.com/InsightfulAnalytics/PBI_Agentic_Dev/tree/main/codex/command-skills/audit-context
Command: npx skills add https://github.com/InsightfulAnalytics/PBI_Agentic_Dev --skill audit-context-insightfulanalytics

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Agent context files like AGENTS.md, CLAUDE.md, and memory files often become outdated, bloated, or AI-generated noise, degrading agent performance. This Skill audits those files and provides grounded recommendations for improvement. ## Core Features & Use Cases - Configuration Discovery: Locates and reads AGENTS.md, CLAUDE.md, .codex/config.toml, .claude/settings.json, SKILL.md files, and referenced memory files across the project. - Structured Evaluation: Assesses each file against criteria like length, relevance, structure, personalization, standard conventions, and progressive disclosure. - Grounded Recommendations: Backs suggestions with vendor guidance on context engineering from Anthropic, OpenAI, and Claude documentation. - Use Case: After months of accumulated agent instructions, run an audit to identify which memory files are stale, which conventions are missing, and where context rot is occurring. ## Quick Start Ask the agent to audit my project context files and suggest improvements to my AGENTS.md and memory configuration.

Frequently Asked Questions about audit-context

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

FAQPage Schema
How do I audit my AGENTS.md or CLAUDE.md files?▼

Invoke the audit-context skill, which searches for AGENTS.md, CLAUDE.md, agent config files, SKILL.md files, and memory files, then evaluates each against criteria like length, relevance, structure, and conventions before summarizing recommendations.

What files does an agent context audit review?▼

The audit covers AGENTS.md and CLAUDE.md files at root and nested directories, .codex/config.toml, .claude/settings.json and settings.local.json, any SKILL.md files, and memory or scratchpad files referenced by those configurations.

Does the audit modify my configuration files?▼

No, the skill explicitly does not modify any files. It only reads and evaluates the context files, then provides a summary report with recommendations for you to apply manually.

How long should agent memory files be?▼

The audit flags memory and configuration files that exceed roughly 500 lines as too long, and files under 50 lines as potentially too short. Concise, well-structured files with headings and examples perform best.

Why does AI-generated agent context cause problems?▼

AI-generated context is often verbose, generic, or incorrect, leading to context rot. The audit warns about attractor basins from training data and hermeneutic reasoning loops, recommending iterative human refinement and evals with reusable prompts.

Related Skills

Explore More Software Engineering Skills→
wendeus0wendeus0

onboard-project

Create project scaffolds with context, memory, and architecture templates.

Community
Intermediate
vltanskyvltansky
10

roast-my-agents-md

Audit AI instruction files for redundancy and ineffectiveness using static analysis and A/B testing.

Community
Advanced
flightctlflightctl
6

ai-ready

Scan codebase structure and convention files to generate or refresh AGENTS.md.

Official
Intermediate
AndurilCodeAndurilCode
7

context-eval

Evaluate context engineering harnesses against no-harness baselines with graded assertions.

Official
Advanced