Context Audit
Analyzes conversation history to identify missing context & suggests prompts for improved AI responses.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add hjewkes-context-audit npx -- -y @trustedskills/hjewkes-context-audit
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"hjewkes-context-audit": {
"command": "npx",
"args": [
"-y",
"@trustedskills/hjewkes-context-audit"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The hjewkes-context-audit skill provides a mechanism to analyze and evaluate the context being used by an AI agent. It helps identify potential issues like excessive length, irrelevant information, or outdated data impacting performance. This allows for optimization of prompts and improved agent accuracy.
When to use it
- Debugging unexpected behavior: If an agent is producing inconsistent or incorrect results, audit its context to see if extraneous information is interfering.
- Optimizing prompt efficiency: Determine if the current context length is unnecessarily long, impacting speed and cost.
- Maintaining data freshness: Regularly check the context for outdated information that could lead to inaccurate responses.
- Improving agent reliability: Ensure the context consistently provides relevant information for better decision-making.
Key capabilities
- Context analysis
- Identification of irrelevant information
- Evaluation of context length
- Detection of outdated data
Example prompts
- "Audit the current context being used by the agent."
- "Show me the longest sections in the agent's context."
- "Identify any data points older than one week within the agent’s context."
Tips & gotchas
The skill requires access to the agent's active context. Ensure appropriate permissions are granted for accurate analysis and reporting.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.