claude

self-improve

Turns verified corrections and hard-won workflows into durable, reviewable Claude instructions and skills, applied only with explicit user authorization.

2 on GitHubby Anton Matosovv0.1.1MITupdated 2 days ago
/

Plugin self-improve from marketplace agent-devcontainer in plume-works/agent-devcontainer. Commands read from the repo's manifest — 2 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (4)

  • apply

    Apply a self-improve proposal the user has explicitly authorized by typing its ID and hash prefix. Only meaningful when the user types /self-improve:apply themselves.

  • improve

    Review the current session for a reusable lesson and propose one exact durable change to a CLAUDE.md file, rule, or skill. Use when the user asks to remember an approach, when a correction should be retained, or when a self-improve candidate is available.

  • reject

    Reject a self-improve proposal the user has declined. Leaves the target file unchanged and remembers the fingerprint so the same lesson is not proposed again.

  • rollback

    Undo a previously applied self-improve mutation, restoring the verified backup. Refuses if the file changed since.

Hooks (7)

  • UserPromptSubmit

    ${CLAUDE_PLUGIN_ROOT}/agent-code/si

  • PostToolUseFailure

    ${CLAUDE_PLUGIN_ROOT}/agent-code/si

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/agent-code/si

  • UserPromptExpansion

    ${CLAUDE_PLUGIN_ROOT}/agent-code/si

  • Stop

    ${CLAUDE_PLUGIN_ROOT}/agent-code/si

  • SessionStart

    ${CLAUDE_PLUGIN_ROOT}/agent-code/si

  • SessionEnd

    ${CLAUDE_PLUGIN_ROOT}/agent-code/si

View source on GitHub

More from plume-works/agent-devcontainer

All 2 plugins →

agentdev

claude

General-purpose agent catalog: git, pull requests, review, CI, formatting, container escalation, and an IWE knowledge-graph planning workflow.

38 skills · 10 agents

2

Similar plugins

Adds educational insights about implementation choices and codebase patterns (mimics the deprecated Explanatory output style)

hooks

anthropics/claude-code 155,476

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

mempalace

claudecodex

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

MemPalace/mempalace 60,536

pensyve

claude

Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents

7 skills · 7 commands · 2 agents · hooks

wshobson/agents 42,461

Maintain self-improve?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins2 plugins