learned-behavior
lisn0 v0.2.0
Self-improving memory for Claude Code. Observes hooks (tool use, edits, errors, guard blocks), distills recurring patterns into durable rules, and surfaces relevant approved lessons before each tas...
From the developer
License
MIT
Works with
Claude Code
Description
From the marketplace listing
Self-improving memory for Claude Code. Observes hooks (tool use, edits, errors, guard blocks), distills recurring patterns into durable rules, and surfaces relevant approved lessons before each task. No LLM in the loop, no self-report, purely behavioral. Local SQLite, zero dependencies, no telemetry.
What changed
No changes recorded yet. Follow this plugin to keep track of future changes.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Security guard hook for Claude Code. Evaluates every tool call (Bash, Edit, Write, Read, MCP) against 864 pattern-matching rules to block...
Shared terms: block, edit, guard, rule
-
A self-improving agent loop with plain-text Obsidian memory. Skills for capture, reflect, and improve; a SessionStart hook injects workin...
Shared terms: improving, memory, self, hook
-
Self-improving measurement layer for Claude Code. Reads JSONL session data, computes effectiveness metrics, writes behavioral rules into ...
Shared terms: improving, rule, self, code
-
Persistent, cross-session task management for Claude Code. 24 tools, 7 skills, and hooks that sync Claude's built-in tasks to a durable b...
Shared terms: durable, hook, code, dependencie
-
vardoger personalizes Claude Code by analyzing your own conversation history and turning recurring patterns into tailored rules. How it ...
Shared terms: recurring, rule, pattern, code
Keywords
Files & skills
learned-behavior · catalog manifest
Saved declaration
{}
learned-behavior · catalog manifest
Saved declaration
{
"name": "learned-behavior",
"source": {
"sha": "6ff565e0837ef4f5ac9c675959794d63423fbc8e",
"url": "https://github.com/lisn0/learned-behavior.git",
"source": "url"
},
"homepage": "https://github.com/lisn0/learned-behavior",
"description": "Self-improving memory for Claude Code. Observes hooks (tool use, edits, errors, guard blocks), distills recurring patterns into durable rules, and surfaces relevant approved lessons before each task. No LLM in the loop, no self-report, purely behavioral. Local SQLite, zero dependencies, no telemetry."
}
learned-behavior · catalog manifest
Saved declaration
{
"name": "learned-behavior",
"author": {
"name": "lisn0",
"email": "bilelzened@gmail.com"
},
"license": "MIT",
"version": "0.2.0",
"homepage": "https://github.com/lisn0/learned-behavior",
"keywords": [
"memory",
"rules",
"learning",
"hooks",
"observability"
],
"repository": "https://github.com/lisn0/learned-behavior",
"description": "Self-improving memory for AI coding agents. Observes tool use, distills recurring patterns into rules, surfaces relevant lessons before each task."
}
plugin.json observed Nov 6, 2026 · 10:45 UTC. Manifest source ↗
Catalog declarations and available plugin.json metadata are saved. Referenced skills and executable source files are not downloaded or tested. Missing components in a manifest do not prove that the plugin has none.
Installation instructions
Community
/plugin marketplace add anthropics/claude-plugins-community
/plugin install learned-behavior@claude-communityTechnical details
- Sources
- Community
- First seen
- Oct 3, 2026 · 22:13 UTC
- Last seen
- Nov 7, 2026 · 00:08 UTC
- Latest observed change
- Oct 3, 2026 · 22:13 UTC
- Collection status
- Listed
- Reported installs
- Not provided
Installation counts are source-reported, not independently verified active users. Observation dates are not release dates.
Download plugin data (JSON)Plugin history: freshly prepared. Prepared . Refreshed when catalog data changes or after 6 hours. Your account and Follow status are live.