Agent Tooling Agent Plugins

48 of 48 plugins on this page · click a row to expand · 301 total

1. ▸hindsight1.0.0Long-term memory for AI agents. Recalls relevant past context before you answer and retains durable facts as you work, backed by Hindsight's retain/recall/reflect memory engine.vectorize-io1 skills1 mcpLong-term memory for AI agents. Recalls relevant past context before you answer and retains durable facts as you work, backed by Hindsight's retain/recall/reflect memory engine.vectorize-io1159,608
2. ▸agentic-bundle-aas-ai-product-evaluation-ops20.6.0Portable skills-only "AAS AI Product & Evaluation Ops" plugin from Agentic Awesome Skills.sickn3313 skillsPortable skills-only "AAS AI Product & Evaluation Ops" plugin from Agentic Awesome Skills.sickn3313049,306
3. ▸openviking0.2.2Semantic long-term memory and context engine for coding agents. Recall prior knowledge with the find/search/read MCP tools and persist durable facts with remember/write, backed by an OpenViking server.volcengine7 skills1 mcpSemantic long-term memory and context engine for coding agents. Recall prior knowledge with the find/search/read MCP tools and persist durable facts with remember/write, backed by an OpenViking server.volcengine7141,737
4. ▸agent-native-turn-into-app1.0.0+codex.a33ee8b6d181Turn a thread, skill, spreadsheet, or Claude/ChatGPT project into a visual Agent-Native app. Local code agents build, run, and screenshot-review it; Claude and ChatGPT on the web hand a bounded source brief to Builder through Dispatch.BuilderIO1 skills1 mcpTurn a thread, skill, spreadsheet, or Claude/ChatGPT project into a visual Agent-Native app. Local code agents build, run, and screenshot-review it; Claude and ChatGPT on the web hand a bounded source brief to Builder through Dispatch.BuilderIO117,637
5. ▸google-agents-cli1.13.0Scaffold, develop, evaluate, and deploy AI agents with Google ADK. Bundles skills for the agent development lifecycle.google7 skillsScaffold, develop, evaluate, and deploy AI agents with Google ADK. Bundles skills for the agent development lifecycle.google706,313
6. ▸longmemory0.1.0Project-scoped durable memory, recall, Skills, and governed context for AI agents.CaviraOSS1 skills1 mcpProject-scoped durable memory, recall, Skills, and governed context for AI agents.CaviraOSS114,570
7. ▸aws-agents1.0.0Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting tools via Gateway and MCP, multi-agent and A2A orchestration, memory, Cedar policies, evaluation, observability, debugging traces and logs, and production hardening.aws8 skills1 mcpBuild, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting tools via Gateway and MCP, multi-agent and A2A orchestration, memory, Cedar policies, evaluation, observability, debugging traces and logs, and production hardening.aws813,422
8. ▸qdrant1.0.0Qdrant stores semantic memories and finds related memories with vector searchqdrant1 skills1 mcpQdrant stores semantic memories and finds related memories with vector searchqdrant111,564
9. ▸powercontext0.1.0Reusable PowerContext skills and MCP configuration for agent integrations.oceanbase1 skills1 mcpReusable PowerContext skills and MCP configuration for agent integrations.oceanbase111,515
10. ▸hephaestus1.2.88Agentlas Core Engine (Hephaestus): runtime-neutral agent workspace, factory, and OS. Skills load from./skills, the Workforce MCP server from./mcp.json.agentlas-ai35 skills1 mcpAgentlas Core Engine (Hephaestus): runtime-neutral agent workspace, factory, and OS. Skills load from./skills, the Workforce MCP server from./mcp.json.agentlas-ai3511,465
12. ▸deja-vu0.24.0deja-vu: memory for coding agents from the sessions already on your disk, Claude Code, Codex, Cursor, opencode and thirty-nine more, including work from before it was installed.vshulcz2 skills1 mcpdeja-vu: memory for coding agents from the sessions already on your disk, Claude Code, Codex, Cursor, opencode and thirty-nine more, including work from before it was installed.vshulcz211,427
13. ▸oma20.36.6Portable multi-agent harness for.agents-based skills and workflowsfirst-fluke33 skills3 mcpPortable multi-agent harness for.agents-based skills and workflowsfirst-fluke3331,373
14. ▸bernstein3.24.1The open-source governance layer for AI agents. Spawn parallel agents in per-task git worktrees, verify their work, and merge results; no model in the coordination loop, so replaying a plan reproduces its task graph byte-identically.sipyourdrink-ltd1 skills1 mcpThe open-source governance layer for AI agents. Spawn parallel agents in per-task git worktrees, verify their work, and merge results; no model in the coordination loop, so replaying a plan reproduces its task graph byte-identically.sipyourdrink-ltd111,193
15. ▸ctx2.4.1Fast local search and 'git blame' for agent sessions.ctxrs1 skillsFast local search and 'git blame' for agent sessions.ctxrs101,179
16. ▸sandbase-harness0.1.1Connect Copilot and compatible agents to an existing SandBase Harness runtime for agents, sessions, turns, artifacts, and cancellation.sandbaseai1 mcpConnect Copilot and compatible agents to an existing SandBase Harness runtime for agents, sessions, turns, artifacts, and cancellation.sandbaseai01640
17. ▸compartment4.13.0High-security, fully offline, encrypted vector memory for AI agents. AEAD-encrypted vault, locked by default after restart, no API key and no network at runtime.MaxFreedomPollard1 skills1 mcpHigh-security, fully offline, encrypted vector memory for AI agents. AEAD-encrypted vault, locked by default after restart, no API key and no network at runtime.MaxFreedomPollard11570
18. ▸mcptoon-skills1.0.0Skills that teach AI agents how to drive mcptoon: connecting agents to MCP servers, authoring new server entries, and triaging broken connections.activeing1233 skillsSkills that teach AI agents how to drive mcptoon: connecting agents to MCP servers, authoring new server entries, and triaging broken connections.activeing12330422
19. ▸power-builder1.0.0Create new Kiro Powers using the Agent Plugins specification, or migrate existing POWER.md-based powers to the agent-plugins standard.kirodotdev3 skillsCreate new Kiro Powers using the Agent Plugins specification, or migrate existing POWER.md-based powers to the agent-plugins standard.kirodotdev30401
20. ▸lumen0.0.42Precise local semantic code search for coding agents, powered by local embedding models.ory2 skills1 mcpPrecise local semantic code search for coding agents, powered by local embedding models.ory21317
21. ▸superagentskill0.9.7Agent skills and candidate workflows from Super Agent Skill. Published registry packages expose available trust and execution evidence; candidate workflows include offline fixtures.criptogus125 skills1 mcpAgent skills and candidate workflows from Super Agent Skill. Published registry packages expose available trust and execution evidence; candidate workflows include offline fixtures.criptogus1251252
23. ▸nowledge-mem0.1.4Cross-tool memory for AI agents through Nowledge Mem skills and MCP.nowledge-co8 skills1 mcpCross-tool memory for AI agents through Nowledge Mem skills and MCP.nowledge-co81204
24. ▸claude-prompts5.1.1Model Context Protocol (MCP) server for versioned prompt templates, multi-step workflow chains, and quality gates. Symbolic syntax: >>prompt --> >>chain @framework: 'gate'minipuft1 mcpModel Context Protocol (MCP) server for versioned prompt templates, multi-step workflow chains, and quality gates. Symbolic syntax: >>prompt --> >>chain @framework: 'gate'minipuft01192
25. ▸create-agent-plugin1.0.0Create portable Agent Plugins from existing Skills, MCP configurations, and client-specific plugins.SudoJacky1 skillsCreate portable Agent Plugins from existing Skills, MCP configurations, and client-specific plugins.SudoJacky10159
26. ▸blocks-network0.4.1Build, deploy, manage, and call Blocks Network agents.blocksnetwork2 skillsBuild, deploy, manage, and call Blocks Network agents.blocksnetwork20148
27. ▸githits0.40.1The infrastructure layer connecting agents to the open-source ecosystemgithits-com4 skills1 mcpThe infrastructure layer connecting agents to the open-source ecosystemgithits-com41124
28. ▸subagent-delegation1.12.0Delegate focused work to other installed agents and coordinate the results.Porabuild2 skillsDelegate focused work to other installed agents and coordinate the results.Porabuild20121
29. ▸agent-brain10.7.0Local-first RAG memory for AI agents: hybrid BM25/semantic search, GraphRAG, and an MCP server with OAuth 2.1. Index docs and code, then search from Claude Code, Cursor, Codex, OpenCode, or Grok Build.SpillwaveSolutions2 skills1 mcpLocal-first RAG memory for AI agents: hybrid BM25/semantic search, GraphRAG, and an MCP server with OAuth 2.1. Index docs and code, then search from Claude Code, Cursor, Codex, OpenCode, or Grok Build.SpillwaveSolutions21119
30. ▸role-model0.1.1Connect Codex (and other clients) to a local role-model runtime via the codex-role-model adapter CLI.try-works1 skillsConnect Codex (and other clients) to a local role-model runtime via the codex-role-model adapter CLI.try-works10118
31. ▸nika0.124.1Say it once. Keep it as a file. Nika turns the AI work you repeat into a readable workflow that stays yours: checked before it runs, run with the model you choose, proven afterwards. This package carries the authoring, debugging, operating and migration skills plus the read-only Nika MCP oracle. Requires the nika binary: brew install supernovae-st/tap/nikasupernovae-st4 skills1 mcpSay it once. Keep it as a file. Nika turns the AI work you repeat into a readable workflow that stays yours: checked before it runs, run with the model you choose, proven afterwards. This package carries the authoring, debugging, operating and migration skills plus the read-only Nika MCP oracle. Requires the nika binary: brew install supernovae-st/tap/nikasupernovae-st4198
32. ▸pi-skill-palette2.2.0Command palette for selecting and applying skills in pinicobailonCommand palette for selecting and applying skills in pinicobailon0098
34. ▸agent-rules3.16.5Generate and maintain AGENTS.md, copilot-instructions.md, and other agent rule filesnetresearch1 skillsGenerate and maintain AGENTS.md, copilot-instructions.md, and other agent rule filesnetresearch1089
35. ▸agent-plugins-example1.0.0A copyable reference package and migration guide for Agent Plugins v1.0.0.agentplugins1 skillsA copyable reference package and migration guide for Agent Plugins v1.0.0.agentplugins1072
36. ▸skillsaw1.0.0A configurable linter for agent skills, plugins, and AI coding assistant contextstbenjam6 skillsA configurable linter for agent skills, plugins, and AI coding assistant contextstbenjam6070
37. ▸morning-star-harness4.2.3Morning Star: Agent Plugin for harness engineering workflows: a TS Harness Workflow Engine (@mstar-harness/engine) that enforces deterministic workflow gates, plus mstar-* judgment skills for multi-agent code delivery across OpenCode, Cursor, Codex, Kimi Code, ZCode, and omp.btspoony26 skillsMorning Star: Agent Plugin for harness engineering workflows: a TS Harness Workflow Engine (@mstar-harness/engine) that enforces deterministic workflow gates, plus mstar-* judgment skills for multi-agent code delivery across OpenCode, Cursor, Codex, Kimi Code, ZCode, and omp.btspoony26068
38. ▸agent-swarm1.2.0Multi-agent coordination with agent-swarm MCPdesplega-ai1 skills1 mcpMulti-agent coordination with agent-swarm MCPdesplega-ai1137
39. ▸codestory0.17.7CodeStory grounding for coding agents over a local managed runtime.TheGreenCedar1 skills1 mcpCodeStory grounding for coding agents over a local managed runtime.TheGreenCedar1137
40. ▸retro3.1.0LLM-driven session retrospection. Detects friction in agent sessions and materializes learnings into correct destinations (personal rules, project rules, skill PRs, checkpoints, harness artefacts).netresearch1 skillsLLM-driven session retrospection. Detects friction in agent sessions and materializes learnings into correct destinations (personal rules, project rules, skill PRs, checkpoints, harness artefacts).netresearch1026
41. ▸mcode-island0.3.0Windows 桌面灵动岛 (Dynamic Island) 状态窗口：让 mcode agent 把工作状态（idle/thinking/working/waiting/done/error）实时推送到屏幕顶部悬浮 pill，agent 自己忙的时候用户不用切回 mcode 也能看到进度。v0.3.0 增加 io.minimax.mcode 客户端扩展（Hooks 草案），与 MiniMax-Code-Plugins PR #20 的 portable Hooks 提案对齐；mcode 0.2.4+ Runtime 触发，registry 接受后零改动生效。MiniMax-AI1 skillsWindows 桌面灵动岛 (Dynamic Island) 状态窗口：让 mcode agent 把工作状态（idle/thinking/working/waiting/done/error）实时推送到屏幕顶部悬浮 pill，agent 自己忙的时候用户不用切回 mcode 也能看到进度。v0.3.0 增加 io.minimax.mcode 客户端扩展（Hooks 草案），与 MiniMax-Code-Plugins PR #20 的 portable Hooks 提案对齐；mcode 0.2.4+ Runtime 触发，registry 接受后零改动生效。MiniMax-AI1023
42. ▸mempalace-code1.16.3Local-first semantic memory for coding agents, packaged with a minimal-profile MCP server and LLM skill.rergards1 skills1 mcpLocal-first semantic memory for coding agents, packaged with a minimal-profile MCP server and LLM skill.rergards1123
43. ▸skill-repo3.2.2Guide for structuring Netresearch skill repositoriesnetresearch1 skillsGuide for structuring Netresearch skill repositoriesnetresearch1022
45. ▸valcraft0.13.0Valcraft is a software factory in your repository: it coordinates the work, keeps the requirements and decisions in ordinary files, and checks the code before shipping so you can see what was built and how it was verified. Skills: tune (repository configuration), cast (project framing), roadmap (business-facing progress), spec (feature and quick contracts), draft (task plans with MSW), forge (reviewed-task implementation and authorized task PRs), review (report-only plan, code, and evidence review), land (authorized finalization and tracker closure), foreman (named-state delivery coordination), temper (local retrospective production), hone (prompt refinement), distill (prompt distillation), and msw (MSW Kernel document judgment).valzav13 skillsValcraft is a software factory in your repository: it coordinates the work, keeps the requirements and decisions in ordinary files, and checks the code before shipping so you can see what was built and how it was verified. Skills: tune (repository configuration), cast (project framing), roadmap (business-facing progress), spec (feature and quick contracts), draft (task plans with MSW), forge (reviewed-task implementation and authorized task PRs), review (report-only plan, code, and evidence review), land (authorized finalization and tracker closure), foreman (named-state delivery coordination), temper (local retrospective production), hone (prompt refinement), distill (prompt distillation), and msw (MSW Kernel document judgment).valzav13022
46. ▸agent-toolkit-agents1.48.018 AI agent personas: 11 holistic (planner, architect, designer, implementer, reviewer, qa-engineer, security-engineer, platform-engineer, researcher, data-engineer) + orchestrator (assistant, client-workflow-bootstrap) + 5 specialists (code-reviewer, agentic-security-reviewer, security-reviewer, e2e-runner, tdd-guide, build-error-resolver), 7 specialists archived to references in #865 (typescript/database/performance/refactor → reviewer/references/*; docs/reference-lookup → researcher/references/LOOKUP_GUIDE.md; tech-assistant → platform-engineer/references/WORKSTATION_OPS.md): see docs/AGENT_TAXONOMY.md §8.ulises-jeremias18 AI agent personas: 11 holistic (planner, architect, designer, implementer, reviewer, qa-engineer, security-engineer, platform-engineer, researcher, data-engineer) + orchestrator (assistant, client-workflow-bootstrap) + 5 specialists (code-reviewer, agentic-security-reviewer, security-reviewer, e2e-runner, tdd-guide, build-error-resolver), 7 specialists archived to references in #865 (typescript/database/performance/refactor → reviewer/references/*; docs/reference-lookup → researcher/references/LOOKUP_GUIDE.md; tech-assistant → platform-engineer/references/WORKSTATION_OPS.md): see docs/AGENT_TAXONOMY.md §8.ulises-jeremias0019
47. ▸copilot-atelier6.0.0Portable GitHub Copilot customization library: role-specific custom agents with handoffs and subagent allow-lists, deterministic lifecycle hooks, and on-demand Agent Skills for PowerShell/DSC engineering (Sampler, Pester, Datum, AutomatedLab, WinRM, MECM), document conversion (PDF, DOCX, XLSX, Marp, pandoc), Outlook and Microsoft To Do automation, research and citation integrity, agentic-security review, and skill/prompt/agent evaluation. Skills are portable; agents, rules, slash commands, and hooks load in GitHub Copilot clients. Keybindings are not a plugin component type; install the CopilotAtelier module from the PowerShell Gallery to get those too.raandree50 skillsPortable GitHub Copilot customization library: role-specific custom agents with handoffs and subagent allow-lists, deterministic lifecycle hooks, and on-demand Agent Skills for PowerShell/DSC engineering (Sampler, Pester, Datum, AutomatedLab, WinRM, MECM), document conversion (PDF, DOCX, XLSX, Marp, pandoc), Outlook and Microsoft To Do automation, research and citation integrity, agentic-security review, and skill/prompt/agent evaluation. Skills are portable; agents, rules, slash commands, and hooks load in GitHub Copilot clients. Keybindings are not a plugin component type; install the CopilotAtelier module from the PowerShell Gallery to get those too.raandree50018
48. ▸astral-orchestrator3.13.0Automatically chooses and coordinates GPT models for project tasks, with the right effort and safeguards for each job.Demonbane181 skillsAutomatically chooses and coordinates GPT models for project tasks, with the right effort and safeguards for each job.Demonbane181017
49. ▸prism0.8.0Route Prism work across full Story and Epic lifecycles directly in the host.baldaworks3 skillsRoute Prism work across full Story and Epic lifecycles directly in the host.baldaworks3017
50. ▸lingshu-condition-units0.1.0灵枢条件单元库（Agent Skills 兼容导出）, 白箱条件化知识，KCCS 四要素不放弃FuRongJun-19994 skills灵枢条件单元库（Agent Skills 兼容导出）, 白箱条件化知识，KCCS 四要素不放弃FuRongJun-19994016
51. ▸meta0.4.0Opinionated guidance for governing marketplaces, organizing plugins, and writing agent skills.BastiDood2 skillsOpinionated guidance for governing marketplaces, organizing plugins, and writing agent skills.BastiDood2016
52. ▸ledger-memory0.1.4Ledger-backed persistent memory for coding agents: append-only facts with retraction vaccines, scars, and a generated MEMORY.md projectionprime-radiant-inc1 skillsLedger-backed persistent memory for coding agents: append-only facts with retraction vaccines, scars, and a generated MEMORY.md projectionprime-radiant-inc1015