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 3 skills, 6 commands, 4 hooks · 712 tokens together
A per-project state layer for long Claude Code sessions: keeps a .claude/state.json (objective / current focus / deliverables), prints a WHERE YOU ARE orientation block at session start, re-injects the goal as you work, and nudges when state goes stale — with /where-am-i, /update-state, and /re-anchor.
Plugin Claude Code
Bundles 5 skills, 4 hooks · 185 tokens together
Cross-device session storage, shared memory, and reminders for Claude Code. Sync sessions, memory files, and reminders across multiple devices via an encrypted private Git repository.
Plugin Claude Code
Bundles 11 skills, 3 hooks · 337 tokens together
Installable mneme MCP server for Claude Code: persistent cross-project memory (remember / recall with staging), shipped as a self-contained compiled binary.
Plugin Claude Code
Bundles 39 skills, 11 commands, 1 agent · 977 tokens together
Universal cognitive kernel. Stack-agnostic thinking patterns, memory management, and planning tools. The foundation for all Craftsman plugins.
Plugin Claude Code
Bundles 1 command, 2 hooks · 21 tokens together
Close the engineering-memory loop: auto-inject relevant prior lessons on session start and on symptom-shaped prompts, plus a /recall command for explicit deep dive.
Plugin Claude Code
Bundles 23 commands, 3 agents · 333 tokens together
Engine for an LLM-curated second brain. Karpathy LLM-wiki pattern with anti-lissage spec, FR-by-default content, three query postures.
Plugin Claude Code
Bundles 13 skills, 6 commands, 3 agents, 2 hooks, 1 MCP server · 494 tokens together
A knowledge graph that maps your codebase into layered, navigable neural nodes — understand any function without reading the entire file.
Plugin Claude Code
Bundles 1 skill · 209 tokens together
Long-term memory for Claude Code and Open Claw — stores notes as .md files with YAML frontmatter, syncs via GitHub, indexes via Neon Postgres. Progressive setup: works with just files, scales to full cross-machine sync.
Plugin Claude Code
Bundles 3 skills, 3 hooks · 239 tokens together
Scratch-notebook context management for any project: per-thread STATE.md handoff docs with one-command create-or-resume (/ccx:start-thread), a compiled parallel-session-safe INDEX dashboard that recompiles itself on every STATE write (/ccx:save-state · /ccx:tidy-scratch), a Stop-hook freshness guard so working state…
jim4226/claude-workspace-brain
Command Claude Code needs its repo
Migrate stale completed threads + old sessions to WORKSPACEBRAINARCHIVE.md.
Republicofhaitigoodstory6175/engram
Plugin Claude Code
Bundles 3 skills, 1 MCP server · 146 tokens together
The context spine that 10x's your Claude Code sessions. Local-first SQLite knowledge graph + MCP server that intercepts file reads and replaces them with structural summaries. Measured 89% token reduction on a real codebase. Apache 2.0, no cloud, no telemetry.
takashito/claude-obsidian-chronicle
Plugin Claude Code
Bundles 2 commands, 1 agent · 300 tokens together
Auto-records Claude Code sessions as structured Obsidian notes + Daily Note entries (via the SessionEnd/PreCompact hooks and /done), and ships the obsidian-vault agent — the unified handler for all Obsidian vault work (create, edit, search, organize notes, tasks, canvases, bases). Configure with…
Cursor rule Cursor
Aether · 5-mode auto-activation + cross-session memory handshake. User doesn't type activate manually.
Skill Claude Code
Documents the current Claude Code session by writing what changed, what broke, how problems were solved, and what's next into DECISIONS.md, CONTEXT.md, and CLAUDE.md. Then commits everything to git. Use this skill when the user says they are done, wrapping up, finishing, handing off, ending the session, switching…
odere-pro/claude-wiki-pages-plugin
Plugin Claude Code
Bundles 26 skills, 5 commands, 17 agents, 7 hooks · 4,803 tokens together
A Claude Code plugin for Obsidian — Karpathy's LLM Wiki shipped as a four-layer, hook-enforced agent stack with multi-agent orchestration.
chrisfentiman/claude-context-cli
Plugin Claude Code
Auto-indexing for claude-context-mcp. Keeps your codebase index fresh on session start, after git operations, and on session end. Includes /insights skill for promoting memsearch patterns to auto-memory.
Plugin Claude Code
Bundles 1 skill · 247 tokens together
End-of-session handoff with bucket-aware dispatch across the canonical 7-bucket docs/ taxonomy (aligned with memory-hygiene v3.3), doc-freshness reverse-lint + skill-freshness audit, and future-to-do emission as GitHub issues. Captures knowledge, routes artifacts to…
Plugin Claude Code
Bundles 5 skills, 1 command · 600 tokens together
Distill technical discussions into compact, tagged decision entries with a live registry of open questions, all version-controlled in your repo and queryable by Claude.
Plugin Claude Code
Bundles 4 commands, 3 hooks · 56 tokens together
Carry a multi-session programme across session boundaries: a durable ledger, an interviewed handoff, and a guard that fires when a session changes code without moving the record.
Skill Claude CodeCodex
A command that lists recent multi-turn coding sessions and lets you choose one to restore in full.
Skill Claude CodeCodex
Teaches AI agents to manage long-term NeuralVaultCore MCP memory securely and efficiently.
dadion123/agent-context-doctor
Cursor rule Cursor
Agent Context Doctor project rule adapter.
Plugin Claude Code
Bundles 2 skills, 5 agents, 3 hooks, 1 MCP server · 809 tokens together
Turn scattered information into a durable, provenance-tracked knowledge base. Bundles the Odin skill (judgment) and the neutral Core MCP server (deterministic, invariant-guaranteeing ops). AI is the enabler, not the substrate — the knowledge persists as Markdown + links + git with no vendor lock-in (ADR-0008).
langlanglanglanglang/rules-architect
Skill Claude CodeCodex
A set of rules for organizing Claude Code instructions across hooks, personal memory, path-specific rules, shared project instructions, and team lessons. It is written partly in Chinese and includes a five-question placement process.
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: