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

brainstorm

01

RasputinKaiser/Self-Improvement-Plugin

Command

Survey current capabilities, identify gaps, dispatch the escalate agent to draft a concrete build plan for the top gap. Proactive — the complement to /improve (which is reactive).

6 5d ago A 39 tokens original MIT

fan-out

04

RasputinKaiser/Self-Improvement-Plugin

Command

Decompose a parent task into parallel slices and dispatch one fan-out agent per slice. Each slice runs in its own slice directory with a HANDOFF.md describing the parent and its scope. Use /fan-out "parent objective" with slice descriptions as args (semicolon-separated).

6 5d ago A 57 tokens original MIT

goal

05

RasputinKaiser/Self-Improvement-Plugin

Command

Set a goal and enter the RALPH loop — keep working autonomously until the goal is genuinely done or the user stops you. Use /goal "objective" to start, /goal status to check, /goal complete to finish, /goal clear to stop.

6 5d ago A 56 tokens original MIT

retro

09

RasputinKaiser/Self-Improvement-Plugin

Command

Run an evidence-gated retrospective, capture reusable SIPS lessons with provenance, and leave one clear next action.

6 5d ago A 22 tokens original MIT

selfloop

10

RasputinKaiser/Self-Improvement-Plugin

Command

Start or control a persistent SIPS loop whose only objective is improving SIPS and the agent operating it through measured, verified iterations.

6 5d ago A 29 tokens original MIT