Agent Plugins Marketplace

Recently added

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

Aug 29, 2026

  1. Danske vurderings- og statusrapporter bygget på RealEquity-sagsdata, i forretningsenhedens egen dokumentidentitet og leveret som PDF.

    Claude Code3 skills
  2. Durable cross-repository memory for coding agents — built to survive an IT security review. Zero runtime dependencies, zero dev dependencies, no install script: nothing runs when you install it, and granting it your agents is a separate explicit command. Independently scanned, with a passing verdict. Adds /handoff, /remember and /recall over one local markdown store. Requires the CLI: npm install -g @vib795/agent-memory (Node >= 22.5).

    Claude Code3 skills
  3. vox-dev3stars

    Text-to-speech for Claude Code: /unmute, /mute, /vibe, /vox:recap

    Claude Code1 MCP server
  4. Install, operate, diagnose, and personalize DeepSeek Harness with DeepSeek-only, ChatGPT-only, or combined Codex-led modes.

    Codex1 skill
  5. worktrees4stars

    worktrees is an open-source Codex plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    Codex1 skill
  6. tiber4stars

    tiber is an open-source Codex plugin indexed from GitHub with 2 skills. Review its manifest and source before installing.

    Codex2 skills
  7. eval-case-reporter is an open-source Codex plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    Codex1 skill
  8. engineering-standards is an open-source Codex plugin indexed from GitHub with 2 skills. Review its manifest and source before installing.

    Codex2 skills
  9. development-discipline is an open-source Codex plugin indexed from GitHub with 12 skills. Review its manifest and source before installing.

    Codex12 skills
  10. babysit-pr is an open-source Codex plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    Codex1 skill
  11. agentic-systems-engineering is an open-source Codex plugin indexed from GitHub with 4 skills. Review its manifest and source before installing.

    Codex4 skills
  12. advisor4stars

    advisor is an open-source Codex plugin indexed from GitHub with 1 skill. Review its manifest and source before installing.

    Codex1 skill
  13. John's consolidated development workflow, engineering standards, worktree, task, review, and agentic-system tooling.

    Codex8 skills
  14. openeyes0stars

    OpenEyes — AI-friendly computer-use primitives (capture/detect/click) as a CLI and MCP server. Drives any desktop GUI on Windows/macOS/Linux via the platform accessibility tree, with Vimium-style grid fallback.

    Codex1 skill
  15. scansci-pdf790stars

    ScanSci PDF turns academic paper search, citation export, open-access discovery, and authorized institutional access into a reusable agent workflow.

    Codex2 skills1 MCP server
  16. XSEC proxy traffic workspace tools

    Agent Plugins
  17. XSEC sub-agent workspace tools

    Agent Plugins
  18. XSEC project-outcome workspace tools

    Agent Plugins
  19. XSEC project files workspace tool

    Agent Plugins
  20. XSEC conversation-tree workspace tool

    Agent Plugins
  21. XSEC browser workspace tool

    Agent Plugins
  22. XSEC session approval workspace tool

    Agent Plugins
  23. XSEC workspace system terminal

    Agent Plugins
  24. XSEC project assets, findings, reports and execution workspace

    Agent Plugins
  25. XSEC attack-path workspace and Agent tools

    Agent Plugins
  26. XSEC asset discovery business surface

    Agent Plugins
  27. Manage, validate, publish, and execute Flow Codeblock Rust+Bun scripts through a local stdio MCP server.

    Codex1 skill1 MCP server
  28. yoetz2stars

    LLM council, bundler, and multimodal gateway - multi-model consensus, code review, image/video generation, and browser fallback for coding agents

    Codex1 skill
  29. snagline2stars

    Operate within a Snagline support fabric's trust boundary: open or inspect only the deployment-bound session case, consume inert advice through the operator-run front, keep confidential summaries out of argv and Buzz, treat advice as inert text, and verify SSP artifacts. An agent never holds the edge socket, UID, or credentials. Exact API and field bounds live in the Snagline repository, not this skill.

    Codex1 skill
  30. Author and eval agent skills: write-skills (triggers, leading words, progressive disclosure, failure modes to prune) and eval-skills (blind golden-case runs in fresh subagents, judged against a bar, gap-driven edits). Vendored from dzhng/skills (MIT).

    Codex2 skills
  31. shaon2stars

    Rust CLI and agent skill for personal attendance, payslip, salary, and related self-service tasks on the user's own Hilan account.

    Codex1 skill
  32. sabx2stars

    SABnzbd CLI - control downloads, queues, RSS feeds, and automation via terminal

    Codex1 skill
  33. langfuse2stars

    Langfuse observability - query traces, debug exceptions, analyze sessions, manage prompts via MCP tools

    Codex1 skill
  34. jk2stars

    GitHub CLI-style interface for Jenkins controllers - create multibranch jobs, inspect config.xml, and manage runs, logs, artifacts, credentials, nodes, and queues

    Codex1 skill
  35. Map a task's unknowns with a staged quadrant walk - known knowns, known unknowns, unknown knowns, unknown unknowns - ending with a four-quadrant map, then carry it through implementation notes, buy-in docs, quiz gates, and session handoffs. Synthesis of Thariq Shihipar's 'A Field Guide to Fable', dzhng's explore-unknowns, Addy Osmani's agent-skills, and davidondrej/skills.

    Codex1 skill
  36. bkt2stars

    Bitbucket CLI - manage repos, PRs, branches, issues, webhooks, and pipelines for both Data Center and Cloud

    Codex1 skill
  37. amq-cli2stars

    Agent Message Queue - file-based inter-agent messaging with co-op mode, cross-project federation, and orchestrator integrations

    Codex3 skills
  38. Designs, bootstraps, audits, and extends a Claude Code harness — the .claude/ directory and root CLAUDE.md. Opinion: under a capable model, less harness yields more productivity.

    Claude Code1 skill
  39. devlog5stars

    Records significant changes to .claude/devlog/ — one markdown entry per feature/fix/refactor/decision, with a script that regenerates index.json + tldr.md, plus a SessionStart digest that surfaces recent devlog entries + active progress at session start (silent in projects that keep neither). The episodic 'what changed and why' layer that survives compaction and hands state to the next session.

    Claude Code1 skill
  40. Optional, thin Claude Code adapter for the portable Design Studio Agent Skill with Studio, Review and Document design-engineering lanes. Canonical methods and runtime behavior live under skills/design-studio/.

    Claude Code1 skill
  41. Jake Bowers's research skills for Claude Code: math, citation verification, referee reports, review responses, decks, style audits, first-reader passes, and simulation studies.

    Claude Code
  42. The same rules translated for the Claude app, which has no CLAUDE.md and no working tree: drafting rules with worked examples, coding rules, the style audit, mathematical work in voice mode, and the handoff into Claude Code.

    Claude Code
  43. dispatch10stars

    Teaches agents how to use Dispatch: shared memory, subagents, repo tools, sharing artifacts, interactive surfaces, review workflow, UI validation, personas, whiteboard, jobs, templates, and personalities.

    CodexClaude Code12 skills
  44. Safe hh.ru job-search workflows powered by the hhru CLI.

    CodexClaude Code4 skills
  45. Lazy-loaded Obsidian skills for creating, editing, and managing vault content from Codex.

    CodexClaude Code1 skill
  46. Lazy-loaded official Lark CLI workflows for operating Lark and Feishu from Codex.

    CodexClaude Code1 skill
  47. Semantic knowledge base search plugin for Cloudflare Vectorize and personal notes.

    CodexClaude Code1 skill
  48. Notify a webhook or Telegram when interactive agent runs finish.

    CodexClaude Code
  49. Block destructive agent commands before they run.

    CodexClaude Code
  50. loragent0stars

    108-agent virtual software firm for Lorapok Labs — includes orchestration, image generation, GIF creation, deployment, development, business, and design agents. Hub-and-Spoke topology with MCP lazy-loading and crash recovery.

    Claude Code16 skills20 MCP servers