Plugin

self-improving-agent-pipeline

A pipeline of skills that implements two feedback loops for Claude Code. The inner loop (plan-interview, intent-framed-agent, context-surfing, verify-gate, simplify-and-harden) catches failures during a session — verifying against tests, detecting scope and context drift, and reviewing code before signaling done. The outer loop (learning-aggregator, harness-updater, eval-creator, pre-flight-check) captures learnings, promotes recurring patterns into CLAUDE.md as permanent rules, and turns failures into regression tests. The harness gets stronger with every cycle.

• Published source
• Repository

Analysed

11 October 2026

Last observed

11 October 2026

What the code does

Static analysis found none of the capabilities we track, such as shell commands, network requests or file writes, in the latest version.

Having a capability is not wrongdoing; many tools need these to do their job. It tells you what to check before you install.

This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.