# @dynosoft/self-improving-loop

> Self-improvement loop and cognitive-error guardrails for coding agents: verify before done, capture durable lessons and reusable skills, curate auto-memory, and detect silent skill degradation. One package, five platforms (Claude Code / Codex / Cursor / H

Latest version **0.3.0** (published 2026-11-19) · MIT license · 0 weekly downloads

_The full health report (score, vulnerabilities, README, dependency tree, version history) is being computed; this document will grow once it lands._

## Install

```sh
npm install @dynosoft/self-improving-loop
pnpm add @dynosoft/self-improving-loop
yarn add @dynosoft/self-improving-loop
bun add @dynosoft/self-improving-loop
```

## Facts

| | |
|---|---|
| Version | 0.3.0 |
| Published | 2026-11-19 |
| First published | 2026-11-05 |
| Weekly downloads | 0 |
| License | MIT |
| TypeScript types | none |
| Module format | ESM + CommonJS |
| Dependencies | 0 |
| Unpacked size | 42.1 KB |
| Author | DYNO SOFT |
| Maintainers | dynosoft |
| Keywords | claude-code, claude-code-plugin, codex, cursor, hermes, self-improvement, learning-loop, skills, verification, cognitive-hygiene, memory, curation, skill-degradation, agent-memory, ai-agents |

## Links

- npm: https://www.npmjs.com/package/@dynosoft/self-improving-loop
- Repository: https://github.com/DYNO-SOFT/self-improving-loop
- Homepage: https://dynosoft.md
- npm.io page: https://npm.io/package/@dynosoft/self-improving-loop

---
_Source: https://npm.io/package/@dynosoft/self-improving-loop · Machine-readable twin of the npm.io package page. Health data is recomputed on every publish._
