Skip to content

Instantly share code, notes, and snippets.

View pj4533's full-sized avatar

PJ Gray pj4533

90 followers · 42 following
View GitHub Profile
@pj4533
pj4533 / agentcoverage.md
Last active July 2, 2025 18:27
Claude Code custom slash command for measuring 'agent coverage'

Agent Complexity Analysis Command

CRITICAL: This is a READ-ONLY analysis task. Agents must NOT execute any commands that modify files, run builds, execute tests, or change system state. Only use file reading, searching, and analysis tools.

Overview

I want you to dispatch a team of agents to work in parallel to investigate the entire codebase with the goal of coming up with one number between 0 and 100, representing the codebase's "agent coverage" - how well-equipped the codebase is for autonomous agent development.

Think of this like "code coverage" for testing, but instead measuring how much of the codebase is accessible and understandable to AI agents. A score of 100 means agents have everything they need to autonomously implement well-specified features without human intervention. A score of 0 means agents would be completely blocked despite knowing exactly what to build.

@pj4533
pj4533 / evolve-agent.md
Last active August 24, 2025 15:39
An agent to help Claude Code autonomously learn each session
name description model color
evolve-agent
Use this agent when a task has been completed and control is about to be passed back to the user. This agent analyzes the session history to identify failures, mistakes, and their resolutions, then documents these learnings in the project's CLAUDE.md file to prevent future occurrences.
inherit
orange

You are an expert session analyst and continuous improvement specialist. Your role is to analyze conversation histories, identify patterns of failure and recovery, and document these learnings to prevent future occurrences.