11,866 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.
Plugin Claude Code
Bundles 3 skills, 3 hooks, 1 plugin · 231 tokens together
DG Claw — instala e gerencia um agente pessoal seu no Telegram, com nome, personalidade e memoria persistente. Dois modos: LOCAL (roda no seu proprio computador Windows/Mac, so com a assinatura Pro/Max, sem servidor e sem API key) e SERVIDOR (24/7 numa VPS Linux via systemd). O wizard /dgclaw:setup detecta o ambiente.
Plugin Claude Code
Bundles 1 skill, 2 hooks, 1 MCP server · 21 tokens together
Persistent memory using knowledge graphs.
Skill Claude CodeCodex
Compile knowledge increments into project snapshot with conflict detection.
Skill Claude Code
Session close-out — clean up tool-created worktrees/branches, write active state to STATE.md, capture durable insights as memory pages, and commit + push okfmem-store via okfmem sync. Drafts an impl-complete comment on the resolved GitHub issue via gh issue comment. Invoked as /okfmem-save (alias: /primer).
Skill Codex
Use when the user explicitly asks to search, find, retrieve, recall, compare, review stale projects, resume prior work, or answer from an Obsidian vault. Read-only: never create, update, move, or delete notes.
bcharleson/crystallized-intelligence
Skill Claude CodeCodex needs its repo
Layer-first retrieval from a Crystallized Intelligence for Agents brain via CLI or MCP. Use when BRAINROOT is set, brain MCP tools are available, or the user asks to query/bootstrap/expand a domain brain without loading the full corpus.
Skill Claude CodeCodex
Query Corivo for prior facts, preferences, and project decisions when the user refers to past conversations or durable memory.
Phanindra208/universal-context-mode
Cursor rule Cursor
Route large outputs through context-mode to preserve context window.
Cursor rule Cursor
Rules for adding, updating, and organizing knowledge base entries.
maggiecopeland0-prog/pmm_folder
Skill Claude CodeCodex
Teaches Claude how to build and navigate team workspaces using a folder system built on the Interpretable Context Methodology (ICM), a five-layer system of markdown files and folders that structures context delivery for AI agents. Based on the Model Workspace Protocol (MWP) by Van Clief & McDermott. Use this skill…
Agent Claude Code
Decomposes a session transcript into typed topic-units for the recall index. Two-phase (exhaustive inventory, then render one unit per thread).
giovani-junior-dev/claude-wiki
Skill Claude CodeCodex
Persistent knowledge base for Claude Code projects using the LLM Wiki methodology by Andrej Karpathy. Bootstraps a structured wiki (markdown files with cross-references) and configures Claude Code to maintain it automatically across sessions. Integrates with Obsidian via MCP for graph view and visual navigation. Use…
a-s-g93/ai-engineer-neo4j-memory-demo
Cursor rule Cursor
A short demo of the Neo4j Memory MCP server.
Skill Claude CodeCodex
Semantic memory and context - store and retrieve information with embeddings for similarity search. Use for long-term memory, context recall, and knowledge persistence.
mongodb-partners/mongodb-gemini-extension
Skill Claude CodeCodex
Use this skill to store the chat history to MongoDB.
Skill Claude CodeCodex
Assists with memory analysis and forensics using MemProcFS. Use when analyzing memory dumps, investigating system activity, or performing forensic examinations.
Plugin Claude Code
Bundles 1 skill, 1 command, 1 MCP server · 268 tokens together
MCP tools for the herdr CLI, plus session necromancy: find, read, and anchor-extract a previous Claude Code agent session from a herdr space.
Plugin Claude Code
Bundles 20 skills, 4 commands, 1 hook · 268 tokens together
Structured development workflows with persistent memory via Beads.
Plugin Claude Code
Bundles 4 commands, 1 hook · 47 tokens together
Rescues messy, typo-ridden, or half-formed prompts so Claude understands you the first time. Confirms its reading with a one-line '✓ understood · …' and keeps reviewable history and stats.
anthony-at-pieces/pieces-mcp-playbook-skill
Skill Claude CodeCodex
Connect to the Pieces MCP server (StreamableHTTP or SSE) and interact with the full Pieces data plane -- work-history retrieval via searchmemory/askmemory/askpiecesltm, targeted full-text and vector search across workstream events/summaries/conversations/annotations/tags/websites, batch snapshot retrieval, browser…
MCP server Claude CodeCodexCursor +2
MCP server "obsidian-mcp-ts" as configured in duquesnay/obsidian-mcp-ts. Runs locally from the obsidian-mcp-ts npm package.
Monishkumarvr/agent-history-mcp
MCP server Claude CodeCodexCursor +2
MCP server "agent-history-mcp" as configured in Monishkumarvr/agent-history-mcp. Runs locally from the agent-history-mcp Python package.
Plugin Claude Code
Identity persistence and memory continuity across Claude Code sessions — survives context compaction.
MCP server Claude CodeCodexCursor +2
NexMem: Shared Agent Memory for Teams — a plug-and-play MCP memory server with pluggable database backends. Runs locally from the mcp-nexmem Python package.
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: