Agent Plugins Marketplace

Recently added

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

Sep 18, 2026

  1. apple-mail0stars

    Local macOS Apple Mail MCP workflows with 38 tools, IMAP acceleration, account sync, and email management skills.

    CodexClaude Code1 skill1 MCP server
  2. minto2stars

    Apply the Minto Pyramid Principle to business writing, audits, intent discovery, and visual structures.

    CodexClaude Code1 skill
  3. matt-loop1stars

    Matt Pocock design with the user via matt-design; confirmed-spec autonomous tickets, implementation, verification and independent review via matt-auto. Includes PR babysitting and conflict resolution. Requires weed-harness 6.0+.

    Codex19 skills
  4. matt-loop1stars

    Matt Pocock design with the user via matt-design; confirmed-spec autonomous tickets, implementation, verification and independent review via matt-auto. Includes PR babysitting and conflict resolution. Requires weed-harness 6.0+.

    Claude Code18 skills
  5. auto-loop1stars

    Autonomous code improvement loop - autocode: hypothesis-driven parallel experiments with model routing (strategist on the expensive tier, experimenters routed by hypothesis difficulty), a live experiment board via weed-harness loop-report, unlazy-backed termination gates, and kept changes collected as one squash commit each on a worktree branch that ends in a PR.

    Codex1 skill
  6. auto-loop1stars

    Autonomous code improvement loop, Claude Code edition - autocode: hypothesis-driven parallel experiments with in-session experimenters routed by the plugin agents, a live experiment board published as an Artifact, unlazy-backed termination gates, and kept changes collected as one squash commit each on a worktree branch that ends in a PR.

    Claude Code1 skill
  7. weed-harness1stars

    Design artifacts plus shared progress-page delivery, model routing, completion gates, and Claude Code hooks. Design conversations and autonomous execution live in matt-loop.

    Codex7 skills
  8. where-tokens-went0stars

    Explain Codex or Claude Code usage from local history with a bundled deterministic tool.

    CodexClaude Code1 skill
  9. engineering12stars

    Reusable engineering workflow skills for repository maintenance, delivery, and interactive pull request review.

    Claude Code2 skills
  10. deepwiki12stars

    AI-generated documentation for GitHub repositories. Use when exploring a repo's architecture, comparing repos, or asking how a feature is implemented in an unfamiliar public codebase.

    Claude Code1 skill1 MCP server
  11. agentguard0stars

    Local tool policy gates and signed, content-free decision records for Codex, ChatGPT Work and Claude Code.

    Claude CodeAgent Plugins4 skills1 MCP server
  12. agentguard0stars

    Local tool policy gates and signed, content-free decision records for Codex, ChatGPT Work and Claude Code.

    Codex4 skills1 MCP server
  13. tmux-agent0stars

    Dispatch an agent-tmux worker and let the mod own the wait: every session reconciles its own workers' result.json on a clock and submits a prompt when one reaches a terminal state.

    Claude Code
  14. tmux-agent-tools0stars

    Tmux wrappers and a skill for running Claude Code or Codex CLI as controllable, supervised named sessions: an inline-vs-worker delegation gate, start/resume, send, wait, capture, status/doctor/setup, result files, human approval gates, and multi-agent pair/team orchestration.

    CodexClaude Code2 skills
  15. crowdstrike-falcon-foundry27stars

    Build Falcon Foundry apps with guided workflows for UI, functions, collections, Falcon Fusion SOAR workflows, and API integrations.

    CodexClaude CodeAgent Plugins11 skills
  16. work-force0stars

    Sharaku Satoh設計の日本企業・行政の業務と文書作成を扱うカスタムAI。システムプロンプト全文を疑似人格と判断基準として適用します。

    Codex1 skill
  17. sherlock-report0stars

    Sharaku Satoh設計の学術特化カスタムAI。システムプロンプト全文を疑似人格と判断基準として適用します。

    Codex1 skill
  18. rorschach-security0stars

    Sharaku Satoh設計のサイバーセキュリティ・インシデント対応を扱うカスタムAI。システムプロンプト全文を疑似人格と判断基準として適用します。

    Codex1 skill
  19. mycroft-debater0stars

    Sharaku Satoh設計の討論・批評・論理の検証を扱うカスタムAI。システムプロンプト全文を疑似人格と判断基準として適用します。

    Codex1 skill
  20. mrs-legal-advisor0stars

    Sharaku Satoh設計の法律相談の整理・法令調査・問題解決の助言を扱うカスタムAI。システムプロンプト全文を疑似人格と判断基準として適用します。

    Codex1 skill
  21. inspire-lestrade0stars

    Sharaku Satoh設計のマーケティング・情報分析・事業相談を扱うカスタムAI。システムプロンプト全文を疑似人格と判断基準として適用します。

    Codex1 skill
  22. ghost-blogger0stars

    Sharaku Satoh設計のブログ・コラム・エッセイの執筆を扱うカスタムAI。システムプロンプト全文を疑似人格と判断基準として適用します。

    Codex1 skill
  23. flight-attendant0stars

    Sharaku Satoh設計の新人ITエンジニアの育成・研修・コーチングを扱うカスタムAI。システムプロンプト全文を疑似人格と判断基準として適用します。

    Codex1 skill
  24. expert-moriarty0stars

    Sharaku Satoh設計の会議への専門家参加・専門的な助言を扱うカスタムAI。システムプロンプト全文を疑似人格と判断基準として適用します。

    Codex1 skill
  25. edgar-rumple0stars

    Sharaku Satoh設計の小説・文学・物語の創作を扱うカスタムAI。システムプロンプト全文を疑似人格と判断基準として適用します。

    Codex1 skill
  26. beautiful-dreamer0stars

    Sharaku Satoh設計のコピーライティング・ネーミング・創作を扱うカスタムAI。システムプロンプト全文を疑似人格と判断基準として適用します。

    Codex1 skill
  27. acepilot0stars

    Sharaku Satoh設計のシステム設計・実装・コードレビューを扱うカスタムAI。システムプロンプト全文を疑似人格と判断基準として適用します。

    Codex1 skill
  28. session-workspace0stars

    Config-driven tmux workspace engine, fail-closed strict-v1 multi-agent harness, shared guard packs, and schema-v4 reviewed Git orchestration for Claude Code sessions.

    Claude Code9 skills
  29. session-scheduler0stars

    Thin file-backed task ledger for orchestrator → executor workflows. Layered on session-chat (>=0.13.0) for durable transport.

    Claude Code1 skill
  30. session-manager0stars

    List, search, and delete Claude Code sessions and all related data across projects. Supported platforms: macOS, Linux, Windows (WSL).

    Claude Code
  31. session-chat0stars

    Peer-to-peer messaging and task dispatch between Claude (and Codex) sessions via tmux. Durable delivery routes fallback/dispatch into the recipient runtime's messages dir.

    Claude Code1 skill
  32. knowledge0stars

    Unified taxonomy tooling for durable project knowledge: docs, memory, and context snapshots in one plugin.

    Claude Code9 skills
  33. chronos0stars

    Ambient time/day awareness for agents: injects the current date/time as context with every prompt, and refreshes it during long turns via a throttled PreToolUse hook. No explicit invocation needed.

    Claude Code
  34. session-workspace0stars

    Config-driven tmux workspace, fail-closed multi-agent harness, and schema-v4 reviewed Git orchestration for Codex sessions.

    Codex13 skills
  35. session-scheduler0stars

    File-backed workflows, reviewer routing, and task tracking for multi-pane Codex orchestration over session-chat (>=0.13.0).

    Codex10 skills
  36. session-manager0stars

    List, search, inspect, and safely delete Codex sessions across projects.

    Codex4 skills
  37. session-chat0stars

    Private, durable messaging and trusted task dispatch between Codex sessions via tmux.

    Codex13 skills
  38. knowledge0stars

    Unified taxonomy tooling for durable project knowledge: docs, memory, and context snapshots in one plugin.

    Codex21 skills
  39. chronos0stars

    Inject a fresh configured-timezone date/time context with every submitted Codex prompt.

    Codex
  40. verify-release62stars

    Verify that the intended release candidate is live in its target environment and that the changed path works there, with live evidence.

    CodexClaude Code1 skill
  41. unslop62stars

    Cut AI tells from text written or edited for a human reader before committing, posting, or sending it.

    CodexClaude Code1 skill
  42. tdd62stars

    Test-driven development at pre-agreed seams: red before green, one vertical slice per cycle, regression-first bug fixes.

    CodexClaude Code1 skill
  43. review-loop62stars

    Drive every reviewer thread on a GitHub PR (Greptile, Devin, humans) to zero unresolved in bounded iterations, with a fixed-format final report.

    CodexClaude Code1 skill
  44. blast-radius62stars

    Find what a diff breaks beyond the diff and prove the one safety fact by running real code instead of writing it up.

    CodexClaude Code1 skill
  45. landed0stars

    Maintain your career profile and write job application documents through a local Landed installation. Landed stores your facts, checks drafts against evidence and renders PDFs.

    Claude Code1 skill
  46. job-application0stars

    JD analysis, tailored resume + cover letter generation, and interview prep - operating on candidate data you keep in your own repo.

    Claude Code3 skills1 MCP server
  47. sleeper-service4stars

    Autonomous learning for Special Circumstances: a daily self-improvement loop, a graduation pipeline, and a continuous-learning promotion ladder — always human-gated at promotion. Requires frank-exchange-of-views.

    Claude Code
  48. prosthetic-conscience4stars

    Core adversarial + cowork behaviour for Special Circumstances: Design-by-Contract rules-as-skills, pair programming, spec-driven development + /plan-audit, project memory, context checkpointing for compaction survival (/checkpoint + a PreCompact seal hook), proficiency skills, quality hooks, validation-loop, and environment preflight (/prosthetic-conscience:doctor).

    Claude Code27 skills
  49. gray-area4stars

    Trajectory evidence for Special Circumstances: what a session actually did, as against what it reported. Captures each seat's own transcript by path at SubagentStop, and reads it back with provenance on every row — so an inspection cites the primary record rather than a summary of it.

    Claude Code7 skills
  50. frank-exchange-of-views4stars

    The research debate engine for Special Circumstances: an additive blue side builds, a subtractive red side audits and owns the pass/fail gate, an engine runs the mechanics and the bench rules the final compromise. Best-of-N, the Catechism (a worth-our-time decision), and the full record preserved.

    Claude Code3 skills