agentmods.dev

PGHH84/claude-layered-learning

Two-loop self-improvement system for Claude Code: immediate learning (wrap-up) + deferred pattern recognition (diary/reflect)

This repository also configures its own agents. See what claude-layered-learning tells them →

Open on GitHub
2Stars on the repository
4Mods indexed here, across every type
7mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Sort RelevanceRecently updatedFewest tokensSecurity gradeRepo starsStars this weekTop rated 2 mods

diary

01

PGHH84/claude-layered-learning

Command Claude Code

Create a structured diary entry from the current session.

not rated 2 7mo ago A 9 tokens original MIT

reflect

02

PGHH84/claude-layered-learning

Command Claude Code

Analyze diary entries to identify cross-session patterns and propose durable updates to repo CLAUDE.md and canonical global instructions.

not rated 2 7mo ago A 22 tokens original MIT