5 tagged self-improvement, measured the same way as everything else here.
Plugin Claude Code
Bundles 1 skill, 5 commands, 7 hooks · 155 tokens together
Self-improving Claude Code, Codex, and OpenCode plugin that turns corrections and successful workflows into Preferences, Project-specific skills, and Shared skills.
quantsquirrel/claude-forge-smith
Plugin Claude Code
Bundles 3 skills, 2 hooks · 102 tokens together
A Claude Code plugin for upgrading skills with test-driven development (TDD), which means checking expected results as part of making changes.
Plugin Claude Code
Bundles 2 commands, 1 hook · 68 tokens together
A companion plugin that records whether skills succeed or fail when the agent stops, then uses those results to help optimise the skills.
Plugin Claude Code
Bundles 1 skill · 138 tokens together
Reviews how a Claude Code session was conducted rather than what it shipped — classifies its shape, scores the run, flags where the context window went, and turns recurring cost into wire-ins for the skills it used or a named lever on the environment that caused it.
Feynman520/d06-p01-self-improve
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 46 tokens together
Agent-neutral self-improvement loop: log correction moments, auto-apply rules on recurrence, grow skills and guarded scripts, mine session transcripts.