agentpluginsdirectory

Agent Tooling Agent Plugins

Agent Tooling is the 1st-largest category in agentpluginsdirectory.com's verified index: 103 of the 524 distinct Agent Plugins verified on 2026-08-09, or 20% of the directory. It covers plugins that build, inspect, or extend AI agents themselves: MCP server builders, skill and plugin authoring kits, memory and context management, prompt engineering, agent evaluation and observability. Of these 103, 92 ship at least one Agent Skill and 32 declare MCP servers.

The plugin's subject is the agent or its tooling. A plugin that merely runs as an agent plugin does not belong here — every plugin does that. Agent Plugins 1.0.0 defines no category field, so this grouping is editorial, not read from the manifest — the verification claim covers the plugin, not the category.

103 plugins · sorted by stars
  1. agentic-bundle-aas-agent-mcp-builderPortable skills-only "AAS Agent & MCP Builder" plugin from Agentic Awesome Skills.sickn33★ 44,677
  2. agentic-bundle-aas-ai-product-evaluation-opsPortable skills-only "AAS AI Product & Evaluation Ops" plugin from Agentic Awesome Skills.sickn33★ 44,677
  3. agentic-bundle-agent-architectPortable skills-only "Agent Architect" plugin from Agentic Awesome Skills.sickn33★ 44,677
  4. agentic-bundle-llm-application-developerPortable skills-only "LLM Application Developer" plugin from Agentic Awesome Skills.sickn33★ 44,677
  5. agentic-bundle-skill-authorPortable skills-only "Skill Author" plugin from Agentic Awesome Skills.sickn33★ 44,677
  6. google-agents-cliScaffold, develop, evaluate, and deploy AI agents with Google ADK. Bundles skills for the agent development lifecycle.google★ 5,521
  7. agent-native-turn-into-appTurn visible project context, a proven thread, skill, or workflow into a runnable Agent-Native app. On Claude or ChatGPT Web, it hands a bounded source brief to Builder through Dispatch; local code agents can build and verify in a workspace.BuilderIO★ 4,451
  8. langwatchRecords which repository and branch each coding-agent session worked in, and teaches the agent to read its own traces back from LangWatch.langwatch★ 3,480
  9. aws-agentsBuild, 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.aws★ 2,277
  10. sol-advisorConfigurable cross-client architect orchestration with lazy setup, exact user-selected native roles, safe adapter installation, and a separate explicit Codex Luna app-task lane.DannyMac180★ 1,842
  11. compartmentHigh-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.MaxFreedomPollard★ 685
  12. maintainer-suitelevnikolaevich★ 534
  13. power-builderCreate new Kiro Powers using the Agent Plugins specification, or migrate existing POWER.md-based powers to the agent-plugins standard.kirodotdev★ 353
  14. create-agent-pluginCreate portable Agent Plugins from existing Skills, MCP configurations, and client-specific plugins.SudoJacky★ 188
  15. nowledge-memCross-tool memory for AI agents through Nowledge Mem skills and MCP.nowledge-co★ 154
  16. role-modelConnect Codex (and other clients) to a local role-model runtime via the codex-role-model adapter CLI.try-works★ 95
  17. pi-skill-paletteCommand palette for selecting and applying skills in pinicobailon★ 91
  18. githitsThe code context layer for AI coding agentsgithits-com★ 76
  19. agent-rulesGenerate and maintain AGENTS.md, copilot-instructions.md, and other agent rule filesnetresearch★ 70
  20. skillsawA configurable linter for agent skills, plugins, and AI coding assistant contextstbenjam★ 47
  21. everrunsInteract with the Everruns managed harnesses platform. Manage harnesses, agents, capabilities, sessions, and applications.everruns★ 42
  22. everruns-devInteract with the Everruns(Dev) managed harnesses platform. Manage harnesses, agents, capabilities, sessions, and applications.everruns★ 42
  23. nikaNika — intent-as-code for AI workflows: author a reviewable DAG in YAML, audit cost and permits before running, keep tamper-evident traces after. 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-st★ 41
  24. agent-plugins-exampleA copyable reference package and migration guide for Agent Plugins v1.0.0.agentplugins★ 34
  25. skill-repoGuide for structuring Netresearch skill repositoriesnetresearch★ 15
  26. vigilesVerify CLAUDE.md/AGENTS.md references, compile typed specs, and test the agent harnesszernie★ 14
  27. moraLocal-first memory skills and MCP tools for grounded recall, briefs, and governed capture.pyranthus-hq★ 8
  28. kibiRepo-local, per-branch, queryable knowledge base. Portable Agent Plugin packaging Kibi's Agent Skills and MCP server.Looted★ 7
  29. correctionguyAgents often drift and waste time on the wrong work. Correction Guy watches from the sidelines and steers them back on track.correctionguy★ 5
  30. toughtongueBuild, refine, and analyze Tough Tongue AI voice agents for tough conversations — agents that automate them (sales calls, lead qualification, demos, screening, booking) and agents that train you for the ones you handle yourself (negotiations, interviews, coaching). Create scenarios, place phone calls, schedule meeting bots, and analyze sessions.tough-tongue★ 5
  31. a2acliCLI and agent skills for the A2A protocol: drive a2acli to discover/invoke/monitor A2A agents, and build/audit A2A-compliant services.ghchinoy★ 4
  32. agent-harnessUse when making a repo agent-ready, verifying harness consistency, checking for documentation drift, bootstrapping harness infrastructure (AGENTS.md as index, docs/ structure, CI verification, enforcement mechanisms), or auditing repo agent-readiness maturity level.netresearch★ 4
  33. dotagentsSkills and agent roles synced by dotagents across coding-agent harnesses.yourconscience★ 3
  34. retroLLM-driven session retrospection. Detects friction in agent sessions and materializes learnings into correct destinations (user memory, project rules, skill PRs, checkpoints, harness artefacts).netresearch★ 3
  35. summonCross-vendor sub-agent broker with structured envelopes, optional MCP facade, and provider drivers (CLI + openai-compat + arkcli).Nafjan★ 3
  36. automated-assessmentSystematic project assessment against checkpoint-enabled skills with scripted verification + LLM reviewnetresearch★ 2
  37. nikaNika — intent-as-code for AI workflows: author a reviewable DAG in YAML, audit cost and permits before running, keep tamper-evident traces after. 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-st★ 2
  38. steeringCompact conversation-steering skills for changing direction, explaining decisions, asking for clarity, tightening prose, executing decisively, and raising frontend quality.stbenjam★ 2
  39. ai-employee-builderConnect AI Employee Builder to Codex, Claude Code, Cowork, and other Agent Plugins-compatible hosts.the2hourclo★ 1
  40. auriga-notifyOpt-in macOS native notification hook for Claude Code Notification events.Ben2pc★ 1
  41. gepa-omniOptimize scorable prompts, code, configs, schemas, SQL, regexes, and agent instructions with GEPA's Omni portfolio and fresh continuation workflow.Qredence★ 1
  42. ink-and-agencySkills for writing, sprint work, and neurodivergent-friendly workflows (ink), plus a library of specialist skills and a persona council for multi-perspective decisions (agency).risadams★ 1
  43. kyberion-agent-pluginPortable Agent Plugins package for Kyberion governed operations, knowledge access, mission control, approvals, and audit workflows.famaoai-creator★ 1
  44. precise-termsTransform verbose instructions into concise prompts and canonical technical terms while preserving every stated requirement.andydrewie★ 1
  45. quantitative-groundingAdd decision-useful quantitative structure for scale, comparison, likelihood, economics, uncertainty, and consequential empirical claims without numerical theater or false precision.andydrewie★ 1
  46. reelierShips two Agent Skills and nothing else: reelier-replay freezes a repeatable tool-call job into a deterministic replay with a receipt per run, and reelier-write-safety covers bounding an agent's writes before you grant them. Skill-only package — it includes no MCP servers.seldonframe★ 1
  47. sergeantAn AI agent orchestration system for working across multi-repo projects, with specialized capabilities for cross-repo dispatch, wiki management, code review, and project-aware context loading.callmeradical★ 1
  48. session-instructions-loaderCodex-only SessionStart hook that injects ancestor AGENTS.md files and repo-configured instruction files.Ben2pc★ 1
  49. agency-agents數位行銷代理商專用 Agent 集合，涵蓋工程、設計、行銷、銷售、測試等 14 個專業類別，共超過 140 個專業 Agent。RDCrystalLab
  50. agent-aware-cliBest practices and architectural guidelines for CLI tools optimized for both human users and AI coding agents.ghchinoy
  51. agent-builder[tien-os] Creates, evaluates, and packages confirmed capabilities as one-agent-with-licensed-skills plugins.tiennguyentt
  52. agent-craftBuild the agents themselves: writing system prompts and skills, delegating across subagents, holding output to a schema, and recalling what earlier sessions decided.opspresso
  53. agent-docsHält die Agent-Doku (CLAUDE.md/AGENTS.md + Rules) am Code: Sync als Standard, --audit für den vollen Report, --fix schreibt. Asymmetrisches Add-Gate, löschen-bevorzugt.Xuoon
  54. agent-looperPortable Agent Plugins skills for designing and running Agent Looper fix-until-green cycles.dancingteeth
  55. agent-plugin-authoringAuthoring, migration, and linting tools for packaging Agent Skills into Agent Plugins v1.0.0 spec packages.ghchinoy
  56. agent-plugins-builderCreate, migrate, package, and inspect Agent PluginsHiAi-gg
  57. agent-plugins-builderCreate, migrate, package, and inspect Agent PluginsHiAi-gg
  58. agent-plugins-doctorDiagnose and fix Agent PluginsHiAi-gg
  59. agentpluginsPortable Agent Plugin and skill for converting components (hooks, commands, tools) between coding-agent vendors.shuvrobhai
  60. analyze-screen-feedbackGround narrated macOS screen-recording feedback in local word timestamps, visible interface evidence, cursor motion, and explicit uncertainty.andydrewie
  61. autoresearchAutonomous improvement engine for Claude Code. Runs an unbounded modify-verify-keep/discard loop against any mechanical metric. Includes planning wizard, security audit, shipping workflow, autonomous debugger, and autonomous fixer.RDCrystalLab
  62. building-with-zepBuild and configure applications that use Zep — agent memory built on temporal Context Graphs. Bundles the building-with-zep skill and the Zep documentation MCP server.getzep
  63. cavemanUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.RDCrystalLab
  64. claude-remote-controlConfigure Claude Code Remote Control server mode and choose between the current computer, Claude web, an existing host, and new paid hosting.Anchras
  65. claude-skills-exporterExtrae las skills de un repositorio con un plugin de Claude, audita su portabilidad y las empaqueta para ChatGPT, Perplexity Computer y Mistral Vibe Work. Conforme a Agent Plugins 1.0.0.novanoticia
  66. claudexRichtet CLIProxyAPI und eine claudex-Funktion für Claude Code mit GPT auf macOS ein — installieren, aktualisieren, reparieren, entfernen.Xuoon
  67. cli-creator從 API 文件、OpenAPI spec、curl 範例或現有腳本建立可組合的 CLI 工具。支援 Python (uv single-file)、Rust、TypeScript，含 companion skill 自動生成。RDCrystalLab
  68. codex-maestroExperimental Codex workflow for planning, bounded delegation, review, and verification.akoita
  69. context7Portable Agent Plugins package for Context7. Pull up-to-date, version-specific documentation and code examples directly from source repositories into agent context.777genius
  70. copilot-plugin-smoke-testA minimal Agent Plugins v1 package for testing GitHub Copilot plugin loading.Lavelee954
  71. delx-recoveryFree recovery, continuity, and witness protocol for AI agents: resume sessions, capture state, process failures, close with feedback. Optional opt-in Agents Hive guardian hooks seal a Continuity Capsule on compact/session end. No API key, no payment.davidmosiah
  72. dreamerosDreamerOS governed AI memory and verification. Cross-session memory, verified answers, and multi-engine routing through one governed gateway.gbude-sudo
  73. eval-writer[tien-os] Defines measurable success criteria and designs evaluations for any LLM-based task, product, feature, or piece of logic.tiennguyentt
  74. example-pluginReference Agent Plugins package: one skill plus a minimal stdio MCP server.nbpm128
  75. firmamentYour team's shared, verified knowledge for AI agents: ask what's true about your org and how work gets done, then record what you learn. One install wires the ask & submit tools and a standing session reminder to use them.spkenny455
  76. foundations.authoringGuidance for creating portable, maintainable Agent Plugins.mylokaye
  77. foundations.authoringGuidance for creating portable, maintainable Agent Plugins.mylokaye
  78. handsHands — extra hands for your repo: an expo/station agent fleet for Claude Code on a per-repo coordination bus. Strict pass discipline (hub-and-spoke), wake-cost accounting, station provisioning with focus labels and self-managed prep books, a live SSE dashboard, and the books — an opt-in durable journal with browsable daily digests.hands-dev
  79. ievoiEvo — self-evolving plugin for AI coding agents (Claude Code, Codex). Universal via the agentskills.io standard. Capture lessons, patch local agents and skills, replay logs on upstream updates. Antivirus-style security audit before install.ievo-ai
  80. knowledgebaseCurated memory for coding agents: schema-enforced findings, learnings, and decisions in .knowledgebase/, with guard enforcement, lookup, and note skills.simonpokorny
  81. langwatchRecords which repository and branch each coding-agent session worked in, and teaches the agent to read its own traces back from LangWatch.langwatch
  82. linear-spec-pluginSpec-driven project execution pipeline backed by Linear. Same skills and agents as spec-plugin, but writes specs, stories and validation to Linear via GraphQL while keeping reasoning artifacts on disk.nexaedge
  83. mcp-builderPortable Agent Plugin packaging of the mcp-builder Agent Skill.chenmiaohero
  84. mehmoryMemory abstraction layer for Claude Code and Codex CLI: deterministic capture hooks plus model-driven skills over a markdown wiki in ~/.mehmory.elderfo
  85. necktieThe angel of late-stage capitalism for your AI agent, with Mammon as its internal adversary.gillcash
  86. nexaedgeFront end for the nexaedge marketplace that works the same on Claude Code, Codex and Antigravity. Detects which agent is running, translates to that agent's native install path, and keeps everything at user scope so a plugin is installed once per machine rather than copied into each repository.nexaedge
  87. oqoqoOperate and analyze Oqoqo projects and eval experiments, and search Oqoqo product documentation from your agent.Oqoqo-Inc
  88. palimCross-tool AI memory over MCP. Checkpoint chats in Cursor, resume them in Claude or ChatGPT. EU-hosted full-text search — not another local SQLite sidecar.joleschmidt
  89. peter537-agent-pluginPortable agent skills and MCP integrations for research, planning, code and dependency audits, supply-chain security, documentation, UI design, and development workflows.Peter537
  90. qiWork on qi — a local-first text river running Granite 4.1, with research that verifies its own citations and a standalone Mac app. Covers setup, editing the codebase, the model cards, adapter conversion, the research process, and shipping.qubie-org
  91. ryu.teamsTeams: named groups of agents you can address as one. Governance shell over the in-crate teams store (agent-id membership only); no documents, no external dependencies. Runs the out-of-process ryu-teams sidecar; Core proxies /api/teams/* to it.amajorai
  92. scriptoriumPersistent Markdown memory. Searches memory before answering and writes the conversation back in the background, as files you can read and diff.Fzkuji
  93. shared-mcpCursor/Codex で共通利用する MCP サーバ定義（chrome-devtools / bigquery / huggingface）ababa831
  94. skill-creatorPortable Agent Plugin packaging of the skill-creator Agent Skill.chenmiaohero
  95. skill-scout從外部 repo 發現、評估、移植 skills 到插件市集。支援瀏覽、討論篩選、合併相關 skills、雙格式 plugin.json 產出。觸發詞：讀這個 repo、看一下 ~/workspaces、瀏覽 skills、移植這個 skill、把這個 porting 過來、評估這個 repo、從 GitHub 匯入 skill；read this repo, browse skills, port this skill, add this skill.RDCrystalLab
  96. skills-sh-growth-loopMeasure skills.sh discoverability, track verified organic users, and run ethical community growth experiments.L4A-ai
  97. spec-pluginSpec-driven project execution pipeline, from ideation to verified deliverables, orchestrated by AI agents. Works with any project type. Built on a team of subagents plus a tool-use hook, so it needs an agent that can run plugin-provided subagents and hooks.nexaedge
  98. tmux-forkFork new tmux windows to spawn parallel AI agents or run CLI commandsRDCrystalLab
  99. token-calculatorAnalyze token usage, estimate API costs, compare AI models, and assess file sizes for context window optimization. A toolkit for understanding and managing AI resource consumption.novanoticia
  100. unknown-remover[tien-os] Classifies the unknown, picks the artifact form, and writes one planning document at a time from the five-document chain.tiennguyentt
  101. uruBuild, organize, and publish durable work through Uru.Ignition-Forward
  102. usableKnowledge-first workflow for agents backed by Usable. Search team knowledge before implementing, retrieve complete sources, separate evidence from assumptions, and verify before claiming success.flowcore-io
  103. vendored-skillsVendored skills from external repositories, copied into this marketplace and pinned to the upstream commit they came from, so they keep working when upstream moves.nexaedge

Verified on 2026-08-09