By akarelin
Agentic Cognition — foundational tools for memory, search, sessions, skills, agents, and learning. Primitives consumed by other plugins.
npx claudepluginhub akarelin/a --plugin acAgentic Cognition router. Use when the agent needs to memorize/recall facts, search knowledge, manage sessions, manage skills, coordinate agents, or learn from feedback. Routes to the appropriate AC tool.
Agent coordination and management. Use when the user asks to "list agents", "configure agent", "spawn agent", or needs multi-agent coordination.
Learn from feedback, corrections, and mistakes. Use when the user corrects the agent, says "don't do that", "remember this for next time", reports a mistake, or when the agent needs to record and learn from errors.
Persist and recall facts, secrets, config, and project state. Use when the user says "remember this", "save this", "where does X go", "get secret", "set secret", "archive this project", "add this to daily notes", or any operation involving storing or retrieving persistent state.
Search across knowledge sources scoped by ownership level. Use when the user says "search for", "find", "look up", "where is", "search my email", "search company docs", "find in Confluence", "search Slack", "search files", or any retrieval from external systems.
This skill should be used when the user asks to "manage sessions", "sync sessions", "list sessions", "resume a session", "clean up sessions", "delete empty sessions", or "rename sessions". Manages Claude Code session folders across repos and hosts.
Manage and improve Cowork plugin skills end-to-end. Use when the user asks to "fix a skill", "patch a plugin", "update a skill", "deploy a plugin", "rebuild plugin", "improve skill", "skill has a bug", or references feedback about a skill that needs to be acted on.
Skill memory layer for Claude Code — auto-capture, learn, and reuse skills from Acontext
Agent self-improvement + retrieval. Captures learnings via colon-namespaced sub-skills (reflect, reflect:consolidate, reflect:ingest, reflect:recall, reflect-status) and auto-injects relevant prior learnings at SessionStart via hook.
Stateful agent tools for Claude Code. Learns who you are, remembers what you're working on, schedules tasks, maintains itself.
Skills for AI agent orchestration - memory search, code graph queries, documentation search, inter-agent messaging, and task planning
Knowledge base with semantic search, document storage, and automatic summarization. Perfect for domain-specific knowledge management.
Persistent memory for Claude Code — memories survive across sessions, projects, and machines
Share bugs, ideas, or general feedback.
░████ ░██ ░██░██ ░███ ░██
░██ ░██ ░██ ░██ ░██░██ ░██
░██ ░██ ░███████ ░████████ ░██░██ ░██ ░██ ░████████ ░███████ ░████████ ░████████
░██ ░██ ░██ ░██ ░██ ░██ ░██░██ ░█████████ ░██ ░██ ░██ ░██ ░██ ░██ ░██
░██ ░██ ░█████████ ░██ ░██ ░██░██ ░██ ░██ ░██ ░██ ░█████████ ░██ ░██ ░██
░██ ░██ ░██ ░███ ░██ ░██░██ ░██ ░██ ░██ ░███ ░██ ░██ ░██ ░██
░█████████ ░███████ ░██░█████ ░██░██ ░██ ░██ ░█████░██ ░███████ ░██ ░██ ░████
░██ ░██ ░██
Агент который только говорит ДА ░███████
Multiple workstations, dozens of projects, across hundereds of instances of Claude Code/Gemini/Codex. No problem. Tired of CLI agents asking for permissions in Approve All mode, but afraid to go YOLO. No problem.
An unfinished, evolving collection of everything agentic — prompt engineering patterns, autonomous agent instructions, multi-agent orchestration experiments, and tooling. This is a working dumping ground, not a polished framework.
Superagent to manage cli coding agents, projects, tools. Makes Claude Code compliant (not asking too many questions).
Browse sessions across multiple machines.

Delete, rename, move and merge.

The tree expands to show full session history with timestamps. Selected sessions show recent conversation messages and available actions in the detail panel.

Obsidian vault integrated. Used to manage Projects - an abstraction above sessions.

A tree-based browser for tools, agents, and YAML config files. Da can be fully configured from its own ui or using its own chat interface.


Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim