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.
Command Claude Code
A command that saves reusable discoveries and lessons from a coding session as one-line JSON records. JSONL means one JSON object per line, making the file easy to append to and process.
MCP server Claude CodeCodexCursor +2
MCP server "engram" as configured in rwnalds/engram. Runs in Docker (ghcr.io/rwnalds/engram:0.1.2).
Skill Codex
Maintain a review-first Markdown knowledge base for Codex practices with source provenance, engineering capture, citation-aware queries, explicit archive and promotion, and deterministic linting. Use when asked to capture a durable engineering lesson, ingest Codex research, query or archive what the repository knows…
D4kooo/Openclaw-Token-memory-optimizer
Skill Claude CodeCodex
Optimization suite for OpenClaw agents to prevent token leaks and context bloat. Use when an agent needs to implement background task isolation (Cron) or a Reset & Summarize workflow (RAG).
Skill Claude Code
Use this skill to generate well-branded interfaces and assets for Omadia UI (Lume design system), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
Skill Claude CodeCodex
Consult the user's vir knowledge base: notes distilled from their own past coding-agent sessions (decisions, gotchas, patterns, tools). Use before starting non-trivial work in a project, when the user asks 'what did I decide about X', 'have I hit this before', 'check my notes/vault', when debugging an error that may…
Skill Claude Code
Long-term project memory through the post-cortex MCP server (tools named session, semanticsearch, updateconversationcontext, assemblecontext, queryconversationcontext, getstructuredsummary, manageworkspace, manageentity, admin). Use it whenever those tools are available and the work could benefit from what was learned…
neverinfamous/memory-journal-mcp
Skill Claude CodeCodex
Core guidelines and instruction pointers for the Memory Journal MCP. Use when interacting with the memory journal (creating, reading, searching entries), orchestrating commits, or writing session summaries.
BayramAnnakov/ai-personal-os-skills
Plugin Claude Code
Bundles 6 skills · 304 tokens together
Skills for building your AI Personal OS: onboarding, daily journaling, knowledge extraction, LinkedIn research-to-publish pipeline, Chief of Staff system review, and PowerPoint deck QA.
Plugin Claude Code
Bundles 4 skills, 5 commands, 3 hooks, 1 MCP server · 352 tokens together
Persistent memory across Claude Code sessions using Cognis.
Skill Codex
Use when a task may depend on prior user preferences, project conventions, architectural rules, workflow decisions, previous Codex work, full-text memory search, durable rule saving, or skill drafting/updating through Hermes Codex Plugin, especially to reduce Codex token spend by recalling minimal relevant context.
GetCacheOverflow/CacheOverflow
MCP server Claude CodeCodexCursor +2
MCP server for cache.overflow - AI agents sharing knowledge with AI agents. Runs locally from the cache-overflow-mcp npm package.
Plugin Claude Code
Bundles 1 skill, 2 commands · 178 tokens together
Archive learnings from Claude Code sessions to Obsidian vault as Zettelkasten notes and use vault knowledge as conversational context.
Cursor rule Cursor
ALWAYS when asked to CREATE A RULE or UPDATE A RULE or taught a lesson from the user that should be retained as a new rule for Cursor.
Plugin Claude Code
Bundles 1 skill, 1 command, 1 MCP server · 249 tokens together
Persistent AI Context Engine — local Markdown memory for Claude. Remembers people, decisions, and project context across sessions in a human-readable vault.
ssdeanx/secure-rag-multi-agent
Cursor rule Cursor
The Memory Bank is a hierarchical documentation system designed to survive AI memory resets. It organizes project knowledge into: project brief → context files → designs → requirements → tasks → progress. Every task must begin with reading ALL memory bank files. Use spec-driven development with EARS format…
Plugin Claude Code
Bundles 5 skills, 1 hook · 192 tokens together
Cortex local context: five behavior skills, a session bootstrap, and an optional MCP bridge.
Skill Claude CodeCodex
Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, syncing project.faf into CLAUDE.md, faf-cli commands, MCP server configuration, or AI-readiness scoring (0-100%). Updated for v2.8.0 Tool Visibility System.
Plugin Claude Code
Bundles 11 skills · 967 tokens together
10 Fable 5-native Agent Skills for Claude, updated for Fable 5.1 — fix over-planning, gold-plating and test bloat, fabricated progress reports, unrequested actions, stalled autonomous runs, and silent tool loops. Includes skill-refactorer for migrating pre-Fable-5 skills and re-checking Fable 5 skills on 5.1.
Skill Claude Code
Resume a session by loading recent handoffs from Engram. Use at the start of a session or when the user wants to review what was done previously.
MCP server Claude CodeCodexCursor +2
Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall. Runs locally from the alaya-mcp npm package. Needs 4 environment variables to run.
Plugin Claude Code
Bundles 7 skills, 1 command, 1 hook · 631 tokens together
Recorded decisions from git history, delivered to the agent before it edits. Constraints, alternatives already ruled out, and warnings left by whoever was here last.
Skill Claude CodeCodex
Use for project questions, analysis, planning, coding, debugging, and review in a Clumsies-bound workspace. Retrieve Clumsies context alongside host-native memory, even without an explicit memory request or after host recall. Also use for requests to remember, update, or delete project knowledge, or manage Memory…
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 96 tokens together
Cross-session memory for AI coding agents: a git-synced Markdown knowledge base with hybrid search, a typed knowledge graph and session distillation, browsed in the /knowledge pane.
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: