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.
Plugin Claude Code
Bundles 1 command, 6 hooks · 10 tokens together
Remembers the tool calls that already failed, and says so before your agent runs one again unchanged.
rodrigopg/claude-skill-prime-context
Plugin Claude Code
Bundles 1 skill, 1 hook · 105 tokens together
Self-learning project context — bare /prime-context captures the session's learnings into area context files; /prime-context loads context on demand; thin AGENTS.md router, structure audit (doctor), drift warnings at session start.
Plugin Claude Code
Bundles 4 skills, 4 commands, 1 hook · 316 tokens together
File-based, progressive-disclosure memory for Claude Code.
Plugin Claude Code
Bundles 7 skills, 4 hooks, 1 MCP server · 381 tokens together
Lore — cross-session memory for Claude Code. Every session becomes a markdown note in your Obsidian vault; the next session recalls what you built and where it lives, without searching.
Plugin Claude Code
Bundles 6 commands, 1 hook · 67 tokens together
Capture conversation states as a tree; render mindmap and timeline views of how thinking evolved across sessions and goals.
Plugin Claude Code
Bundles 4 commands · 96 tokens together
Claude Code integration for cocoindex-code (ccc). Slash commands for onboarding, reset, and re-index; git hook installer for automatic incremental indexing; standard exclude presets that avoid common retrieval noise (tests, plans, compiled views, ML embedding data).
Plugin Claude Code
Bundles 1 command · 17 tokens together
Persistent memory for Claude Code. Auto-archives every session to your Obsidian vault, injects recent work at startup, and adds /recall to search your whole history.
Cursor rule Cursor needs its repo
A Claude Code plugin and Obsidian vault that builds persistent, compounding knowledge bases using Andrej Karpathy's LLM Wiki pattern. This repo works with Cursor's AI through the cross-platform Agent Skills format.
Plugin Claude Code
Bundles 4 skills, 1 hook · 262 tokens together
Lore (Long-term Organized Reference): a persistent, human-readable knowledge base on disk, maintained by Claude Code skills: drop files into raw/, get an interlinked markdown wiki with a catalog index. Link any project to it with a ## Knowledge Base section in its CLAUDE.md.
Plugin Claude Code
Bundles 2 skills · 183 tokens together
Closes a working session with a summary you can read, a handoff block for compacting now and a resume block for coming back another day.
Plugin Claude Code
Bundles 4 skills, 1 hook · 205 tokens together
Honest session handoff + project memory for Claude Code — context anchored to git facts, progress only with evidence, never guessed.
Plugin Claude Code
Bundles 5 commands, 3 hooks, 1 MCP server · 73 tokens together
Context-budget manager for Claude Code. Warns before auto-compact and long-context accuracy degradation, checkpoints finished work so you can shed it, gates large file reads to subagents, recalls context evicted by compaction, guards against unrelated context switches, and audits unused agents/skills.
Plugin Claude Code
Optional companion to warden. Re-injects your hard rules on every prompt so they survive context compaction. Adds a UserPromptSubmit hook that reads one local file and writes nothing.
Plugin Claude Code
Auto-archive Claude Code sessions to your Obsidian vault as a Karpathy-style LLM wiki.
Plugin Claude Code
Bundles 10 skills · 366 tokens together
A graph of atomic claims that LLMs walk natively as semantic engines. Eight core verbs (extract, connect, walk, audit, learn, init, anneal, dream) plus an opt-in surrender system (no-surrender, teach). No queues, no phase machines, no invisible hooks.
Plugin Claude Code
Bundles 2 skills, 7 commands, 11 agents · 718 tokens together
A knowledge-precipitation harness for Claude Code — a disciplined multi-stage delivery workflow that captures durable learning and matures it through reuse. The workflow is the pipe; knowledge is the moat.
Plugin Claude Code
Tells you when your Claude Code session has gotten too big, and offers a handoff to a fresh one.
Plugin Claude Code
Bundles 2 skills, 9 hooks · 74 tokens together
Persistent memory and background intelligence for Claude Code.
Elliotoh-jin/claude-memory-loop
Skill Claude Code
Bootstrap the memory loop into any repo or Obsidian vault. Triggers: (1) "set up the memory loop / second brain / warm layer here" or "install this structure in another repo/vault", (2) a new project asking "make the AI remember across sessions and surfaces".
Plugin Claude Code
Bundles 1 skill, 3 commands, 4 hooks · 166 tokens together
Session continuity across context resets for Claude Code. Snapshots a session digest before /clear, /compact, or auto-compaction and auto-rehydrates it after. The non-looped companion to cc-repete — stands down whenever a cc-repete loop is active.
Plugin Claude Code
Bundles 1 skill · 107 tokens together
Save project context for persistent memory across Claude Code sessions.
Plugin Claude Code
Bundles 1 skill, 5 hooks · 50 tokens together
Gives Claude a persistent, self-maintained notebook per project: distilled topic notes, a generated index injected into context each turn, and hooks that keep the notes current.
brianschroeder/simple-agent-memory
Plugin Claude Code
Bundles 1 skill · 126 tokens together
Repo-level agent memory for Claude Code: a git-tracked learnings log agents read when stuck and append to as they work.
Plugin Claude Code
Bundles 3 skills, 1 hook · 300 tokens together
Talk to Claude Code like a friend — a complaint or a quick note — and it auto-classifies, timestamps, and files each message into dated category notes, then gives you a suggestion. A UserPromptSubmit safety-net hook means nothing you say is ever lost. Local-first, plain markdown, no cloud.