Agent Plugins Marketplace

Recently added

Plugins grouped by the day they were added to the directory, newest first.

Sep 24, 2026

  1. notion0stars

    Search and work with your Notion workspace.

    Agent Plugins1 MCP server
  2. obsidian-vault-test0stars

    Test — plugin.json imbriqué dans une skill pour vérifier la propagation via npx skills

    Claude Code1 skill
  3. markdown-obsidian-toolkit0stars

    Markdown notes and Obsidian skills collection for writing, reading, and organizing notes. (Agent Plugins 1.0.0) Markdown and Obsidian Flavored style (wikilinks, embeds, callouts, properties), vault MCP access, Obsidian CLI, Bases (.base), and JSON Canvas (.canvas). Portable across Claude Code, Claude Desktop, and compatible agent frameworks.

    Agent Plugins5 skills
  4. dev-general0stars

    General dev tools: code-explain, doc-generate.

    Agent Plugins2 skills
  5. mnemoverse0stars

    Persistent memory for AI agents, shared across tools. Connects the hosted Mnemoverse memory server over MCP with a one-time OAuth sign-in: recall relevant memories before acting, save durable decisions and corrections, keep shared memory rooms across accounts. Bundles the CC0 agent-memory-discipline skill so the agent actually uses the memory it has.

    Claude CodeAgent Plugins2 skills1 MCP server
  6. dapta-agentic-os0stars

    Dapta Agentic OS — Ecosistema de herramientas, habilidades y conectores MCP para implementadores de Dapta

    Agent Plugins
  7. dapta-agentic-os-client0stars

    Dapta Agentic OS — Workspace de cliente con herramientas y conectores MCP estandarizados

    Agent Plugins
  8. tabnas0stars

    Tabnas parser-fleet skills and MCP servers: author, debug, test and ship grammars for the tabnas engine.

    Claude Code5 skills2 MCP servers
  9. vibelore-plugin0stars

    Write consistent fiction and adapt existing novels into vertical webtoons with storyboards, lettering, and approvals through a local MCP server.

    Codex2 skills1 MCP server
  10. ibr1stars

    UI/UX design and building for Codex, with auditing, validation, and iterative editing as supporting capabilities.

    CodexClaude Code27 skills
  11. skill-provenance7stars

    Version, validate, bootstrap, package, verify, and hand off portable Agent Skill bundles.

    CodexClaude Code5 skills
  12. memories3stars

    Memories discipline plus a portable Codex setup guide; the published npm installer owns hooks and MCP wiring.

    Codex1 skill
  13. memories3stars

    Self-hosted semantic memory with graph-aware search (PPR multi-hop traversal), temporal reasoning (version preservation, date-range filters), multi-backend routing, 6-signal hybrid search, auto-feature metrics, operator workbench, lifecycle policies, and full audit trail

    Claude Code1 skill
  14. agentkit1stars

    Board-aware parallel issue and PR review skills, with lifecycle hooks and a per-repository contract.

    CodexClaude Code
  15. wwed1stars

    What Would Elon Do — execution and simplification judgment run through Musk's five-step algorithm (question the requirement, delete, simplify, accelerate, automate), fenced off from human gates and irreversible surfaces.

    CodexClaude Code1 skill
  16. wwbd1stars

    What Would Boris Do — engineering judgment channeled from Boris Cherny's published guidance, calibrated for a product-led, agent-maintained builder.

    CodexClaude Code1 skill
  17. bootstrap-workflow1stars

    Seven team delivery skills, proportional independent review, and bounded safe publication.

    Claude Code7 skills
  18. bootstrap-workflow-agents1stars

    Seven team delivery skills, proportional independent review, and bounded safe publication.

    Codex7 skills
  19. bootstrap-orchestrate1stars

    The /orchestrate skill: delegate one task to a sub-agent of the model and effort you name, in one continuous thread. Invoke-only.

    CodexClaude Code1 skill
  20. instruction-audit1stars

    Read-only audit of the always-on instruction surface — host and container — for context waste, dead rules, cross-layer contradictions, and unclear authority.

    CodexClaude Code
  21. concise1stars

    Session-only concise chat with proper grammar and complete technical artifacts.

    CodexClaude Code1 skill
  22. bootstrap-commands1stars

    Bootstrap commands: analyze any codebase and generate CLAUDE.md, project skills, and AI-assisted development setup.

    Claude Code1 skill
  23. gamussa-coding-policy0stars

    Coding policy for Viktor Gamov's AI agents: language-agnostic quality rules, autonomous shipping discipline, and stack defaults for JVM, Swift, TypeScript, and Python

    Codex4 skills
  24. shared-forest0stars

    Plant a tree in the Shared Forest, read its live state, or sponsor custom trees for a user.

    CodexAgent Plugins2 skills2 MCP servers
  25. chatgpt-esra1stars

    Evidence-driven ESRA improvement workflows and a local Codex runtime.

    CodexAgent Plugins5 skills
  26. agent-project-issues0stars

    MCP server for GitHub/GitLab issue management on Codex. Read/create/update tickets and add comments with automatic safety markers (ai-generated / ai-modified labels, #ai-generated comment prefix). Per-project permissions; falls back to read-only auto-discovery from the git remote when no config is present.

    CodexClaude Code1 skill1 MCP server
  27. mega-mcp2stars

    Codex plugin for operating a MEGA cloud account through the local MEGAcmd MCP server.

    Codex1 MCP server
  28. chess-review10stars

    Chess.com 用户名自动取谱与中文互动复盘；累计 10 盘复盘后可开启持续更新的常见漏洞与进步档案。

    Codex2 skills
  29. noootwo-vibe0stars

    A Noootwo multi-skill workspace for controlled AI software development, user-centered product decisions, design, code review, and project state persistence.

    Codex10 skills
  30. java-developer-skills0stars

    Java/Spring 后端开发、设计、Review、测试与问题修复的多入口 Skill 插件。

    Codex7 skills
  31. anti-hall1stars

    Verify-first discipline for Codex. Bundles Codex-native skills (including session handover — a comprehensive handoff so a fresh session can resume without re-deriving or guessing anything) plus an installer for the Codex hook subset that can be enforced today: session/prompt nudges, a codex-availability PATH probe, shell-command guards, Stop guards, task discipline, and speculation checks. Claude Code plugin files are kept separate and unchanged.

    CodexClaude Code13 skills
  32. gaxia-skills1stars

    Portable workflow skills for coding agents, with Claude Code and Codex adapters.

    CodexClaude Code11 skills
  33. awards0stars

    Design and build award-worthy websites and components with eleven skills, a visual reference guide, 59 focused recipes plus one complete composition (60 verifiable entries), and an evidence-based jury.

    CodexClaude Code11 skills
  34. iphone-duo-fit0stars

    Fit an existing iPhone app (SwiftUI or web/Capacitor) to every iPhone Duo pose

    Claude Code1 skill
  35. juninmd2stars

    Production-grade agent skills and custom agents for AI coding assistants.

    Claude Code30 skills
  36. akari185stars

    AKARI Video の編集スキル一式 + .akari/ プロジェクトの進捗を SessionStart で注入 + /akari 導線を束ねるプラグイン。3 入口（ターミナル akari / セッション内 /akari / アプリ接続ボタン）が同じファイル契約に収束する背骨。

    Claude Code
  37. deck-studio0stars

    premium-decks: turn source files into editable consulting-, banking-, and keynote-grade decks with documented sources, checked calculations, and an explicit review report. Ingests xlsx/csv/docx/pdf/pptx/md into a fact base, builds an answer-first storyline and ghost deck for approval, and renders client-editable .pptx (slide master, native charts, finance recipes) or HTML. Every number is verified against a cited fact or a recomputed calculation; QA reports PASS/WARN/SKIP/FAIL per check. Rules derived from a study of 131 public consulting and banking decks plus 8 banker discussion books.

    Claude Code1 skill
  38. cloud-harness11stars

    Safe operating guidance for private Cloud Harness MCP coding workspaces.

    CodexClaude Code1 skill
  39. fiction-writer0stars

    Discovery writing system for fiction authors. Intent-driven skills for scene writing, worldbuilding, session tracking, search, and manuscript compilation.

    Claude Code8 skills
  40. respeak0stars

    Two-lane communication for agent swarms: an efficient machine-facing shorthand lexicon for long-running sessions, plus a translator agent that renders human-facing narratives (ELI5, BLUF, technical) tuned by a layered tone configuration: plugin defaults, user (~/.claude/respeak), project (.claude/respeak), and per-folder .respeak.yaml files, nearest wins. Session overrides (/respeak:off, /respeak:on, RESPEAK_HOOKS, RESPEAK_GATE) silence or force the hooks for one session without editing any file.

    Claude Code5 skills
  41. swarm1stars

    Alternative-model fan-out engine. Manifest-driven parallel runs across capable :cloud models and Claude — background execution, digest compression, worktree isolation, and a governance-gated provider path.

    CodexClaude Code3 skills
  42. slack-bridge1stars

    Two-way Slack ↔ Claude Code bridge via Socket Mode. Zero dependencies, Node 22+.

    Claude Code2 skills1 MCP server
  43. pipeline1stars

    Pipeline orchestration — queue, dev/test/review automation, merge runner, spend governance.

    Claude Code3 skills
  44. discipline1stars

    Per-model discipline deltas injected on every prompt (Sonnet 5 first: verify-before-claiming, provenance tagging, evidence-gated pushback, redundancy brake), plus a baseline scanner and blind judge grader for measuring violation rates.

    Claude Code
  45. claude-peers1stars

    Peer discovery and real-time messaging between local Claude Code sessions — per-session stdio MCP server plus a self-healing singleton localhost broker.

    Claude Code1 MCP server
  46. checkpoint1stars

    Durable cross-session handoff via STATE.md. /checkpoint skill (reconciles state), SessionStart resume offer, PreCompact backstop, and an observable self-correcting cache-keepalive.

    Claude Code2 skills
  47. agent-investigation1stars

    Investigate agent transcripts — locate, summary, errors, retries, pivots, report.

    Claude Code1 skill
  48. nextbillion-mcp0stars

    NextBillion.ai location APIs as MCP tools: geocoding, place search and browse, routing, distance matrix, isochrones, and static maps with overlays

    Codex1 MCP server
  49. nextbillion-mcp0stars

    NextBillion.ai location APIs as MCP tools: geocoding, place search and browse, routing, distance matrix, isochrones, and static maps with overlays

    Claude Code1 MCP server
  50. coslash16stars

    Use local coSlash sessions, handoffs, agent launches, and diagnostics.

    CodexClaude Code5 skills