12,529 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
MCP server Claude CodeCodexCursor +2
MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows. Local SQLite memory works zero-config; hosted governance and approvals use Novyx Cloud. Runs locally from the novyx-mcp Python package.
Skill Claude CodeCodex
Search, read, and cross-reference the persistent memory store that the CoMeT-CC plugin has been building across this and prior Claude Code sessions. Use when the user references "before", "earlier", "last time", "that thing you worked on", "you already did…", or when you have a hunch that a relevant…
morphllm/morph-claude-code-plugin
Plugin Claude Code
Bundles 2 skills, 4 hooks · 40 tokens together
Intercepts Claude Code's context compaction and replaces it with Morph's compaction service.
Plugin Claude Code
Bundles 18 skills, 16 commands, 7 hooks · 617 tokens together
Token-efficient command execution and persistent memory for Claude Code. 60+ command filters save 90%+ tokens. Auto-indexes output into searchable KB. Cross-session memory injects role-specific context into teammates.
Plugin Claude Code
Bundles 6 skills, 8 commands, 2 agents, 6 hooks · 795 tokens together
OpenLTM — Long-Term Memory for AI coding agents: semantic search, context injection, session learning.
Skill Claude CodeCodex
Set up and use the Noosphere memory provider in Hermes Agent. Use when a user gives Hermes a Noosphere API key, asks to connect Hermes to Noosphere, configure durable memory, verify the provider, or troubleshoot Hermes Noosphere memory setup.
Plugin Claude Code
Bundles 2 skills, 3 commands, 2 hooks · 369 tokens together
EN: Reflect on the current conversation and save reusable learnings (memories, anti-patterns / Reflexion-style lessons, skill stubs, project-doc updates) with explicit confirmation. ES: Reflexiona sobre la conversación actual y guarda aprendizajes reusables (memorias, anti-patrones estilo Reflexion, stubs de skills…
Skill Claude CodeCodex
Dual-brain review for ambiguous designs, risky refactors, and recurring project decisions. Combine macro-level design review with micro-level code verification and relevant project memory.
Skill Claude CodeCodex needs its repo
Work a Markdown knowledge base — an Obsidian vault, a wiki, a docs tree — by BLOCK ADDRESS instead of by whole page. Use when the job is to find which page and which section says something, read that one section, add a line to an index or a log, or rewrite one section of a note: geml find answers with file#address…
Plugin Claude Code
Bundles 3 skills, 3 commands, 1 agent, 1 hook · 234 tokens together
Fable 5 behavioral patterns as a harness for Opus 4.8: grounded progress, self-verification loops, delegation triggers, file-based memory, autonomy calibration. Zero-config: installs a SessionStart hook; skills auto-trigger.
MCP server Claude CodeCodexCursor +2
Local-first search tool for Claude Code session transcripts — hybrid keyword + semantic search, with optional multi-source (federated) trust-tagged search. Runs locally from the magpie-search Python package.
Cursor rule Cursor
When and how to use the sayou workspace and its MCP tools for persistent knowledge across sessions.
Skill Claude Code
Search and explore an Obsidian vault through the NoteBrain CLI (semantic search, tags, backlinks, connections, hidden links, boosted retrieval). Use it whenever the user mentions their notes, knowledge base, Obsidian vault, semantic search, finding connections or unlinked notes, or asks exploratory questions like…
Plugin Claude Code
Bundles 22 skills, 6 commands · 800 tokens together
Unity-aware AI infrastructure for Claude Code: a queryable knowledge graph of your Unity project, plus observability, project memory, and 22 skills. Connects to the standalone Hades app for macOS and Windows (Windows is beta), which serves 32 MCP tools.
MCP server Claude CodeCodexCursor +2
Hierarchical memory for AI agents. Three-layer (buffer/working/core) with decay and promotion. Runs locally from the engram-rs-mcp npm package. Needs 2 environment variables to run.
Plugin Claude Code
Bundles 2 skills, 3 agents, 4 hooks · 229 tokens together
Biomimetic long-term memory for Claude Code with surprisal gating, mutable reconsolidation, affective routing, and sleep consolidation.
Skill Claude CodeCodex ⚠ unsafe
A framework for giving an agent awareness of its activity, attention, timing, and repeated behaviour. It also combines memory scoring, safety handling for untrusted data, decision guidance, focus tracking, and tool-use records.
Cursor rule Cursor
Load project memory from MASTERCONTEXT.md and keep it updated after substantive work.
jmanhype/claude-code-plugin-marketplace
Plugin Claude Code
Bundles 3 skills · 102 tokens together
Agentic Context Engineering: evolve context through bullets, deltas, and TF-IDF retrieval. Complete with schemas, validation, and production scripts.
Plugin Gemini CLI
Persistent memory for AI agents, shared across tools: write a memory in one MCP client, recall it in another. OAuth sign-in, no API key to paste.
MCP server Claude CodeCodexCursor +2
MCP server for gknowledge: let Claude Code, Codex or Cursor search, read and grow a Karpathy-style LLM wiki. Runs locally from the gknowledge-mcp Python package.
MCP server Claude CodeCodexCursor +2
AgentKnowledgeMCP - Advanced Knowledge Management for AI Agents. Runs locally from the agent-knowledge-mcp Python package.
Plugin Claude Code
Bundles 1 skill, 9 hooks, 1 MCP server · 37 tokens together
Local NEXO runtime core for NEXO Desktop: memory, Deep Sleep, Evolution support-ticket mode, doctor diagnostics, personal scripts, recovery-aware jobs, startup preflight, and optional dashboard/power helper.
Cursor rule Cursor
Use Context Firewall for noisy terminal output.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: