11,865 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.
Query local Claude Code, Codex CLI, OpenCode, Kimi Code CLI, Cursor Agent CLI, and Pi session history through the corral CLI — list recent sessions, search by topic, read a session's conversation, export a shareable transcript with tool calls and thinking, or build a handoff context package to continue interrupted…
Turn any folder of files into a navigable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPHREPORT.md.
Convert Claude Code session history into Codex-ready continuation artifacts. Use when a user asks to migrate, transfer, resume, import, archive, inspect, or continue Claude Code conversations/history in Codex, including by Claude session id, renamed session title, /.claude JSONL file, project directory, or search…
A method for organizing notes in an Obsidian vault, which is a folder of linked Markdown files. It follows the vault's existing folders, metadata, templates, naming habits, and links while suggesting safe destinations.
Bootstrap a personal-wiki project. Creates the wiki/ folder skeleton, installs the wiki-ingest / wiki-query / review skills, and appends a marked conventions block to CLAUDE.md. Run once per project; safe to re-run for updates.
Initialize a new project folder with a concise CLAUDE.md, durable project context, and linked reference markdown files instead of making the user restate everything from scratch. Use this whenever the user wants to bootstrap a fresh directory, initialize project context, create or reset a project CLAUDE.md, set up a…
Curated Claude Code skills with Korean and English variants. Includes dream (memory consolidation pass), session-seal (resumable session snapshots), session-retro (gated session retrospective that publishes reusable rules), to-html (gated HTML visualization of content), and task-routine (checklist-to-commit d.
★not rated 2 27d agoA
tokens not measured
originalMIT
A local Markdown-based memory system for Claude Code, Anthropic’s coding assistant. It saves conversations, summarizes them, and retrieves relevant past context using keywords or meaning.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Ingest a complex document (Markdown, README, spec, handbook) into a MemPalace server by splitting it into well-organized, semantically searchable sections. Use when the user wants to store, file, import, load, or "remember" documentation in MemPalace.
Initialize Claude's persistent memory system with self-designed format and auto-loading SessionStart hooks. Use when starting a new project or when user says "set up memory", "init memory", "remember this project", or "create memory system".
Converts episodic memory (corrections, lessons) into procedural memory (behavioral rules) by synthesizing them via LLM and injecting into SOUL.md or CLAUDE.md. This is the "learning loop" — past mistakes become standing rules.
Generate and maintain a comprehensive code-context.md file that captures deep codebase understanding — models, routes, components, stores, architecture, data flows, and key patterns. Commands - init, update, uninstall.
This skill should be used when the conversation is getting long, context feels bloated, Claude mentions compaction or context limits, the user asks about "context", "pruning", "memory", "compaction", or when Claude notices tool outputs are very large. Also activate when resuming a session, starting a large task, or…
Use this skill whenever the user wants to install, configure, migrate, design, or connect Obsidian as a second brain, knowledge base, cloud-synced vault, or AI/Hermes-readable memory. It is especially important when the user asks for an Obsidian setup prompt, vault architecture, folder structure, plugin…
Recover vanished Antigravity chat history after an index crash. Restores both UI state (.pb) and agent memory (brain/) using PB injection with full dual-state synchronization.
Orchestrates efficient read and write interactions with the engram unified memory store via MCP tools. Provides deterministic workflows for decomposing observations into atomic memories, composing four-dimensional queries (context, similarity, relationship, time) for maximum retrieval accuracy, managing agent-managed…
Query and update the user's local Second Brain personal knowledge base through the personal-kb MCP tools (kbschema, kbreaddata, kbwritedata). Use for stored data (contacts, notes, billing, language vocabulary and phrase tracking, anything in the KB). Always discover the current schema before issuing queries; never…
Build tools and scripts that use the AirJelly CLI (airjelly command) to query the user's memories, tasks, app usage, screen recording status, and reminders from the terminal or shell scripts. Use this skill whenever the user wants to: automate AirJelly queries in a shell script or Makefile, pipe AirJelly data into…
Seven skills for building and using an OKF (Open Knowledge Format) "second brain" — scaffold a bundle; author concept, entity/reference/system, and playbook nodes; view and query it; and grow it safely from new sources.
★not rated 2 1mo agoA
tokens not measured
originalMIT
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: