self-improving-loop

Name: self-improving-loop
Author: DYNO-SOFT

DYNO-SOFT ★ 0

Self-improving-loop integrates verify-before-done audits, durable memory capture with auto-promotion into project rules, and skill degradation detection to prevent agents from repeating mistakes across sessions. It runs on Claude Code, Codex, Cursor, Hermes, and DeepSeek Harness through hooks, shell scripts, and a reusable skill that learns from execution outcomes.

Productivity Code Review No API key detected runs shell

Install

> /plugin marketplace add DYNO-SOFT/self-improving-loop

> /plugin install self-improving-loop

Source: https://github.com/DYNO-SOFT/self-improving-loop

What it's made of

3 commands · 1 skill · 4 hooks

Commands: 3
Agents: 0
Skills: 1
MCP servers: 0
Hooks: 4 · PostToolUse, PreToolUse, SessionStart, Stop

What it needs & plugs into

API keys: none
Paid services: none detected
External tools: self-improve-hook.sh skill-telemetry.sh
Talks to: nothing external detected

Analyzed 2026-11-05. Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.

Is this your plugin?

Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (DYNO-SOFT).