RasputinKaiser/Self-Improvement-Plugin

A self-improvement harness plugin for Claude Code and ChatGPT / Codex: memory-aware startup, safer tool use, verification hooks, bounded fresh-context delegation, a deterministic task-graph runtime, and session closeout. Experimental, open-source, free.

6Stars on the repository
37Mods indexed here, across every type
5d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

escalate

01

RasputinKaiser/Self-Improvement-Plugin

Agent

Solve one bounded subtask the main thread is stuck on, in a fresh context. Returns a plan, a minimal diff, and a one-line lesson to record.

6 5d ago A 37 tokens original MIT

fan-out

02

RasputinKaiser/Self-Improvement-Plugin

Agent

Solve one slice of a decomposable task independently. Other fan-out agents may be working on other slices in parallel. Coordinate via the shared HANDOFF.md file the main thread wrote; return your slice, a minimal diff, and a one-line lesson.

6 5d ago A 53 tokens original MIT

memory-curator

03

RasputinKaiser/Self-Improvement-Plugin

Agent

Dedupe near-identical Memory Fabric records, promote repeated work-tier entries to learning-tier, and expire stale low-confidence ones. Keeps recall signal high.

6 5d ago A 35 tokens original MIT

test-author

05

RasputinKaiser/Self-Improvement-Plugin

Agent

Given an untested script, write the missing runtests.py regression case that would have caught a known failure or covers its public surface.

6 5d ago A 30 tokens original MIT