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.
Skill Codex
Bootstrap a repository-level "super harness" for long-running agent and human collaboration, so durable team knowledge, experiment progress, and verification evidence live in the repo rather than individual chat history. Use when initializing or normalizing the harness structure in a new or messy repository…
navendubrajesh/context-management-for-agents
Skill Claude CodeCodex
This skill should be used for designing and evaluating compression strategies for long-running agent sessions — hierarchical summarization, selective retention, compaction triggers, quality thresholds, and handoff summaries. Route foundational context concepts to context-fundamentals, failure diagnosis to…
MCP server Claude CodeCodexCursor +2
MCP server "cliplin-context" as configured in Rodrigonavarro23/cliplin. Runs locally from the cliplin Python package.
Skill Claude CodeCodex
Persistent continuity management for AI agents. Ensures continuity across sessions, prevents data loss from compaction, and maintains reliable audit trails. Logs all human interactions and agent responses for complete conversational continuity. Works with base OpenClaw — no external dependencies. Continuity data stays…
Skill Claude CodeCodex
Use the ASIMOV CLI to join the user's personal knowledge (such as mail, messages, documents) and public data in one knowledge base. Use when the user mentions ASIMOV, wants their own data in the task, or needs a data source an ASIMOV module handles.
Skill Claude CodeCodex
Set up, maintain, or operate a personal wiki vault (second brain). Three branches: Setup, Maintain, Operate. Trigger for: "set up my second brain", "lint my wiki", "schedule my vault operator", "check wiki health", "operate my second brain", or any vault bootstrap, maintenance, or operator task — even phrased casually.
Skill Claude CodeCodex
A handoff and return workflow for continuing work with an AI agent after hours or days away. It records task status, decisions, next steps, unanswered questions, and gaps in understanding.
Skill Claude CodeCodex
Preserve the minimum sufficient working state required for another coding agent to continue a task without repeating repository discovery, reconstructing prior decisions, or losing task-specific constraints.
Plugin Claude Code
Bundles 5 skills · 652 tokens together
Global, cross-repo agent skills: capture durable session learnings (memory.remember), periodically compact MEMORY.md (memory.compact), run a personal five-phase dev workflow (workflow), run a read-first workspace health check (checkup), and grade candidate models against eval golden sets (evals).
Skill Codex
Initialize, plan, run, inspect, and review resumable Ralph-style autonomous implementation loops with sequential chunks, persistent scratchpad memory, manifests, and idempotent post-sprint hooks. Use for .ralph orchestration or similar long-running coding-agent sprint systems.
Skill Claude CodeCodex
Multi-tier (L1/L2) memory management skill for OpenClaw agents. Use when: (1) reading, writing, organizing, or searching memories, (2) deciding what to remember or forget, (3) performing memory hygiene (L1↔L2 sync, promotion, demotion), (4) answering questions about prior sessions, decisions, or preferences. Supports…
Skill Claude CodeCodex
File-based persistent memory for sub-agents and skills — where to store it, memory types (user, feedback, project, reference), save/recall rules, and MEMORY.md indexing. Read this skill when an agent definition says it uses persistent memory, or when saving or recalling learnings across sessions.
mikonos/zettelkasten-agent-skills
Skill Claude CodeCodex
High-output meeting/conversation notes (decisions, alignment, disagreements, decision trail, assumptions, risks/opportunities, action items) + Zettelkasten links. Use when asked to summarize meeting notes or turn a conversation into reusable knowledge.
Agent Claude Code
Spawn after a work phase settles or when knowledge needs maintenance: pass work refs, changed files, and target repos. Mines decisions, maintains existing docs (delete stale, reorganize misplaced), writes updates into the right knowledge layers, commits each touched repo without pushing, and reports contradictions and…
Plugin Claude Code
Bundles 5 skills · 364 tokens together
Create and edit Obsidian vault files including Markdown, Bases, and Canvas. Use when working with .md, .base, or .canvas files in an Obsidian vault.
qqabcv520/my-claude-marketplaces
Plugin Claude Code
Bundles 1 skill, 3 commands, 1 agent · 185 tokens together
A project knowledge-base plugin for managing shared technical notes and retrieving them with help from another agent. A knowledge base is an organized collection of project information that can be reused later.
Plugin Claude Code
Bundles 1 skill · 186 tokens together
Handoff session context.
Plugin Claude Code
Bundles 18 commands · 129 tokens together
Agent-maintained Zettelkasten knowledge graph.
Plugin Claude Code
Bundles 1 command, 1 hook · 36 tokens together
Audit and prune Claude Code's persistent memory: verify stale claims against the project, catch contradictions and duplicates, then fix them through one confirmed docket, never silently rewriting what a memory means. Nudges at session start when the store needs attention; /garden schedule adds a scheduled dry-run…
abossenbroek/abossenbroek-claude-plugins
Plugin Claude Code
Bundles 1 skill, 4 commands · 64 tokens together
Production-grade context engineering tool for expert LLM engineers. Analyzes and improves plugin architectures using SOTA orchestration patterns - Four Laws of Context Management, tiered fidelity, severity-batched grounding, and firewall architectures.
verygoodplugins/claude-plugins
Plugin Claude Code
Bundles 1 skill, 3 commands, 3 hooks, 1 MCP server · 105 tokens together
Persistent memory for Claude Code - store decisions, patterns, and context across sessions.
IDisposable/claude-transcript-plugin
Plugin Claude Code
Bundles 1 skill, 1 hook · 30 tokens together
Automatically saves readable Markdown transcripts of Claude Code sessions before context compaction.
Plugin Claude Code
Bundles 4 commands · 54 tokens together
A plugin that stores project knowledge in Markdown files across four categories: user, feedback, project, and reference. It includes rules for indexing and updating those notes.
Plugin Claude Code
Bundles 4 skills, 4 commands, 1 hook, 1 MCP server · 320 tokens together
Automatically captures and generates project memory from your development work — team-shareable and synced across devices, so you can recall and search past decisions and context across sessions and agents. Backed by the jolli CLI bundled as an MCP server.
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: