Other Agent Plugins · Page 30
Listings 1393–1440 of 4252 plugins in this editorial category. All current listings were verified against Agent Plugins 1.0.0 on 2026-11-13.
Plugin directory
48 of 48 plugins on this page · click a row to expand · 4,252 total
PluginDescriptionPublisherSkillsMCPStars
cortex-system0.7.1Cortex system skill bundle: approval / browser / client-manage / project-init / schedule / user-learn.fangxm2336 skillsCortex system skill bundle: approval / browser / client-manage / project-init / schedule / user-learn.fangxm2336014
design-constraints0.1.0Design UI with explicit spatial and typographic constraints instead of letting the model guess.adamperlis1 skillsDesign UI with explicit spatial and typographic constraints instead of letting the model guess.adamperlis1013
pepper-prompt-engineer2.5.1CRAFT+ workflow for turning task descriptions into verified production-ready prompts.ITSalt1 skillsCRAFT+ workflow for turning task descriptions into verified production-ready prompts.ITSalt1011
block-no-verify0.3.0Best-effort guard against bypassing git hooks via git commit/push --no-verify, commit's short -n form, or any way of pointing core.hooksPath elsewhere: -c, --config-env, `git config core.hooksPath <path>` and the GIT_CONFIG_* environment. Read as a parsed command, so `cd repo && git commit --no-verify`, `bash -c '...'` and sudo/env/xargs wrappers are caught and a message that merely says --no-verify is not. On git push, -n means --dry-run and stays allowed. Known bypass classes include aliases, wrapper scripts, and non-standard clients. Also refuses an agent command that sets a person-only override (CHOCK_ALLOW*, CHOCK_AGENT_COMMIT, CHOCK_DIFF_LIMIT) by env prefix, env, export, declare, set/setx or $env:, and refuses hiding the agent markers (CLAUDECODE, AI_AGENT, CHOCK_AGENT_COMMIT) by unset, env -u/-i, export -n or Remove-Item Env:; it tells the agent to ask the person. Fix the underlying hook failure instead of skipping validation.open-coder-ai1 skillsBest-effort guard against bypassing git hooks via git commit/push --no-verify, commit's short -n form, or any way of pointing core.hooksPath elsewhere: -c, --config-env, `git config core.hooksPath <path>` and the GIT_CONFIG_* environment. Read as a parsed command, so `cd repo && git commit --no-verify`, `bash -c '...'` and sudo/env/xargs wrappers are caught and a message that merely says --no-verify is not. On git push, -n means --dry-run and stays allowed. Known bypass classes include aliases, wrapper scripts, and non-standard clients. Also refuses an agent command that sets a person-only override (CHOCK_ALLOW*, CHOCK_AGENT_COMMIT, CHOCK_DIFF_LIMIT) by env prefix, env, export, declare, set/setx or $env:, and refuses hiding the agent markers (CLAUDECODE, AI_AGENT, CHOCK_AGENT_COMMIT) by unset, env -u/-i, export -n or Remove-Item Env:; it tells the agent to ask the person. Fix the underlying hook failure instead of skipping validation.open-coder-ai1010
ast-grep0.3.3Structural code search with ast-grep rules: finds code by shape when grep on text is too noisy, and never rewrites it. Not for plain string or filename lookups; use grep or find.iowarpStructural code search with ast-grep rules: finds code by shape when grep on text is too noisy, and never rewrites it. Not for plain string or filename lookups; use grep or find.iowarp0010
azure-functions-hosted-skills0.5.6Azure Functions Hosted Skills canvas builds Hosted Skills with Timer, HTTP, Queue, and Microsoft 365 Inbox triggers locally or works with an existing Azure Function App.microsoft2 skillsAzure Functions Hosted Skills canvas builds Hosted Skills with Timer, HTTP, Queue, and Microsoft 365 Inbox triggers locally or works with an existing Azure Function App.microsoft2010
computer-use0.1.0桌面观测与操控包: 节点获得在 macOS 本机观测桌面(应用/窗口/屏幕截图/剪贴板)与操控桌面应用(打开激活、按键、点击)的可用路径、权限引导与无害化纪律。适用于桌面自动化、操控鼠标键盘、点击与输入、程序化按键、屏幕截图、窗口与界面元素读取、剪贴板读写、本机 app 自动化、GUI 验收等任务。内含 skill:computer-use(观测, 动作, 复核主循环、观测路径与命令、权限引导卡、分级与 fail-closed 收口)。不适用于浏览器页面操作(由独立的浏览器操控插件面承担);宿主进程与宿主应用窗口永不可入观测面;出图与汇报另配 visual-report。组件面:宿主执行器未就绪(见 references/host-dependencies.md),无 mcp.json、无工具扩展。MashiroKai1 skills桌面观测与操控包: 节点获得在 macOS 本机观测桌面(应用/窗口/屏幕截图/剪贴板)与操控桌面应用(打开激活、按键、点击)的可用路径、权限引导与无害化纪律。适用于桌面自动化、操控鼠标键盘、点击与输入、程序化按键、屏幕截图、窗口与界面元素读取、剪贴板读写、本机 app 自动化、GUI 验收等任务。内含 skill:computer-use(观测, 动作, 复核主循环、观测路径与命令、权限引导卡、分级与 fail-closed 收口)。不适用于浏览器页面操作(由独立的浏览器操控插件面承担);宿主进程与宿主应用窗口永不可入观测面;出图与汇报另配 visual-report。组件面:宿主执行器未就绪(见 references/host-dependencies.md),无 mcp.json、无工具扩展。MashiroKai1010
tidy3d0.4.0Tidy3D simulation, API, and documentation guidance for AI coding agents.flexcompute2 skills1 mcpTidy3D simulation, API, and documentation guidance for AI coding agents.flexcompute2110
canva1.0.0Canva's hosted MCP server: find, create and export designs in your Canva account. Sign in with your Canva account.stigmer1 mcpCanva's hosted MCP server: find, create and export designs in your Canva account. Sign in with your Canva account.stigmer019
assistant-account-research1.0.3针对单一客户汇总近期变化、关系历史及会议准备要点。xpert-ai3 skills针对单一客户汇总近期变化、关系历史及会议准备要点。xpert-ai309
epistemic-self-monitoring0.6.1Observation-vs-conjecture discipline for coding agents. Bundles the epistemic-self-monitoring skill (the 'what': claims carry their evidence and a named falsifier; only verified claims become facts or closures) with per-host hooks (the 'when'). Non-blocking by default; an opt-in strict mode gates closures on a complete [EPISTEMIC CLOSE] block. Portable core: the skill only; hooks are host-specific (hooks/ for Claude Code and Codex, cursor/ for Cursor).3dgiordanoObservation-vs-conjecture discipline for coding agents. Bundles the epistemic-self-monitoring skill (the 'what': claims carry their evidence and a named falsifier; only verified claims become facts or closures) with per-host hooks (the 'when'). Non-blocking by default; an opt-in strict mode gates closures on a complete [EPISTEMIC CLOSE] block. Portable core: the skill only; hooks are host-specific (hooks/ for Claude Code and Codex, cursor/ for Cursor).3dgiordano007
webengine-web1.0.0Observe and interact with live web pages via WebEngine MCP (Selenium): snapshot, click/type/select, then generate UI code in any stack.AxaFrance2 skills1 mcpObserve and interact with live web pages via WebEngine MCP (Selenium): snapshot, click/type/select, then generate UI code in any stack.AxaFrance217
cloudflare0.1.0Cloudflare platform workflows paired with the token-efficient Cloudflare API MCP.travnie1 skills1 mcpCloudflare platform workflows paired with the token-efficient Cloudflare API MCP.travnie116
generate-agents-md0.2.3Generate a lean, high-signal CLAUDE.md from codebase analysis. Grounded in Anthropic best practices and empirical studies; built to pass review-agents-md's critical checks.smykla-skalski1 skillsGenerate a lean, high-signal CLAUDE.md from codebase analysis. Grounded in Anthropic best practices and empirical studies; built to pass review-agents-md's critical checks.smykla-skalski105
project-management0.1.2A plugin to manage project workflows, backlog refinement, and team collaborationpagopa1 skills1 mcpA plugin to manage project workflows, backlog refinement, and team collaborationpagopa115
hello-world1.0.0A simple example power that demonstrates multilingual greetings and basic power structurealexhddev1 skillsA simple example power that demonstrates multilingual greetings and basic power structurealexhddev105
report-authoring1.1.0Workflows for creating, updating, cloning, pinning, and publishing Seizu reports through the built-in reports MCP tools.mappedsky5 skillsWorkflows for creating, updating, cloning, pinning, and publishing Seizu reports through the built-in reports MCP tools.mappedsky505
nerd-consensus1.0.0Find what enthusiast communities agree on, argue about, and warn against for a product, tool, or product categorystaticaland1 skillsFind what enthusiast communities agree on, argue about, and warn against for a product, tool, or product categorystaticaland105
keepgoing0.3.0A Stop hook for Claude Code and Codex that requests one final completion pass, with an opt-in infinite mode.stbenjamA Stop hook for Claude Code and Codex that requests one final completion pass, with an opt-in infinite mode.stbenjam005
fk-toolkit-ops2.1.3Operate the toolkit itself: check for and apply toolkit updates, wire MCP servers into Claude Code, and use Codex-native ImageGen when available with a clear optional API fallback boundary.furkankoykiran3 skills1 mcpOperate the toolkit itself: check for and apply toolkit updates, wire MCP servers into Claude Code, and use Codex-native ImageGen when available with a clear optional API fallback boundary.furkankoykiran315
agentic-bundle-aas-ai-product-evaluation-ops19.11.0Portable skills-only "AAS AI Product & Evaluation Ops" plugin from Agentic Awesome Skills.ibrdot13 skillsPortable skills-only "AAS AI Product & Evaluation Ops" plugin from Agentic Awesome Skills.ibrdot1304
demo-quality1.0.0Quality gate for the demo and lab guides in this masterclass: a readme checker skill, a topic-index MCP server, a review agent, and a hook that catches brand-voice violations as they are written.alexander-kastil1 skills1 mcpQuality gate for the demo and lab guides in this masterclass: a readme checker skill, a topic-index MCP server, a review agent, and a hook that catches brand-voice violations as they are written.alexander-kastil114
ask-gina-spot0.1.0Ask Gina Spot lets an agent quote and, with your approval, execute spot token swaps, transfers, and liquidity-pool operations from your Gina wallet. It also reads swap history, wallet addresses, LP positions, and operation status, and it includes skills for scanning liquidity pools and rebalancing LP positions. Transactions move real funds, so review every quote before you approve it.askgina1 mcpAsk Gina Spot lets an agent quote and, with your approval, execute spot token swaps, transfers, and liquidity-pool operations from your Gina wallet. It also reads swap history, wallet addresses, LP positions, and operation status, and it includes skills for scanning liquidity pools and rebalancing LP positions. Transactions move real funds, so review every quote before you approve it.askgina014
hook-askConformance hook ask effect on the shell alias: the guard asks only for a command carrying `lab-deny`.uze-shConformance hook ask effect on the shell alias: the guard asks only for a command carrying `lab-deny`.uze-sh004
agentic-code-security0.4.1trigger: writing agent code or agent config, Python or TypeScript using AutoGen, CrewAI, LangChain, LangGraph, mem0, the OpenAI Agents or Claude Agent SDK, an MCP server or client (.mcp.json,.cursor/mcp.json,.vscode/mcp.json, claude_desktop_config.json,.codex/config.toml,.gemini/settings.json), docker-compose files for agents. avoid: code execution on the host, unpinned MCP servers and models, shell-reaching tools, approvals switched off, whole-environment and credential-store leaks, TLS verification off, unbounded loops, SQL and eval built from strings, stripped provenance markers. 29 rules in 10 packs, exec, supply, tools, approval, identity, comms, bounds, prompt-memory, code, provenance, each pack or rule allow|deny in.chock/agentic-security.json; bounds, prompt-memory and one supply rule start as allow.open-coder-ai1 skillstrigger: writing agent code or agent config, Python or TypeScript using AutoGen, CrewAI, LangChain, LangGraph, mem0, the OpenAI Agents or Claude Agent SDK, an MCP server or client (.mcp.json,.cursor/mcp.json,.vscode/mcp.json, claude_desktop_config.json,.codex/config.toml,.gemini/settings.json), docker-compose files for agents. avoid: code execution on the host, unpinned MCP servers and models, shell-reaching tools, approvals switched off, whole-environment and credential-store leaks, TLS verification off, unbounded loops, SQL and eval built from strings, stripped provenance markers. 29 rules in 10 packs, exec, supply, tools, approval, identity, comms, bounds, prompt-memory, code, provenance, each pack or rule allow|deny in.chock/agentic-security.json; bounds, prompt-memory and one supply rule start as allow.open-coder-ai103
tinyfish1.2.4Community package for TinyFish MCP. Search the live web, fetch clean page content, and run browser automations through TinyFish's hosted server.777genius1 mcpCommunity package for TinyFish MCP. Search the live web, fetch clean page content, and run browser automations through TinyFish's hosted server.777genius013
opinion-manager0.6.0Manage Agent behavior rules through templates, partial selection, blank iteration, and authorized-memory candidates, with complete previews and exact version locks.lc4t1 skillsManage Agent behavior rules through templates, partial selection, blank iteration, and authorized-memory candidates, with complete previews and exact version locks.lc4t103
electron0.1.0Electron conventions: browser surfaces, Node integration, and IPC.AkaraChen1 skillsElectron conventions: browser surfaces, Node integration, and IPC.AkaraChen103
dataminer-connector0.1.4DataMiner connector orchestration, XML, QAction, validation, testing, documentation, and simulation agents.SkylineCommunications31 skillsDataMiner connector orchestration, XML, QAction, validation, testing, documentation, and simulation agents.SkylineCommunications3103
ultron1.3.0Activate the Ultron lead workflow when the user selects or mentions @Ultron.Simone-AndreottiActivate the Ultron lead workflow when the user selects or mentions @Ultron.Simone-Andreotti003
mizan-mcp0.1.0Expose the Mizan eval engine to agents and MCP clients as callable tools via the `mizan mcp` server. Registers a local stdio MCP server (`mizan mcp stdio`) advertising four tools, mizan_list_metrics, mizan_get_metric (read-only), mizan_eval_run, and mizan_eval_pairwise, plus an agent-in-the-loop eval skill. Use when an agent should discover a judge and run an evaluation over MCP rather than shelling out to the CLI.ghchinoy1 skillsExpose the Mizan eval engine to agents and MCP clients as callable tools via the `mizan mcp` server. Registers a local stdio MCP server (`mizan mcp stdio`) advertising four tools, mizan_list_metrics, mizan_get_metric (read-only), mizan_eval_run, and mizan_eval_pairwise, plus an agent-in-the-loop eval skill. Use when an agent should discover a judge and run an evaluation over MCP rather than shelling out to the CLI.ghchinoy103
ping-identity-pingone-aic1.0.0Agent plugin for PingOne Advanced Identity Cloud (AIC). Journey design and build guidance for AIC journeys and PingAM authentication trees, node selection, composition invariants, risk and MFA branches, plus app-integration guidance for connecting web, mobile, and backend applications to AIC (Journey modules, journey client, OIDC/PKCE, tenant CORS, OAuth clients), with MCP-backed journey creation where connected.pingidentity2 skillsAgent plugin for PingOne Advanced Identity Cloud (AIC). Journey design and build guidance for AIC journeys and PingAM authentication trees, node selection, composition invariants, risk and MFA branches, plus app-integration guidance for connecting web, mobile, and backend applications to AIC (Journey modules, journey client, OIDC/PKCE, tenant CORS, OAuth clients), with MCP-backed journey creation where connected.pingidentity203
amplitudeProduct analytics: events and charts so you see what people doreforma-ai1 mcpProduct analytics: events and charts so you see what people doreforma-ai012
commit0.1.2Create Conventional Commits safely, including logical commit stacks over mixed working trees and plan-traceable commit sequences.ayagmar1 skillsCreate Conventional Commits safely, including logical commit stacks over mixed working trees and plan-traceable commit sequences.ayagmar102
hyper-v-control0.2.1Control Hyper-V VMs, graphical consoles, guest automation and user/kernel debugging through a native C# stdio MCP server.JerryLinLinLin1 skills1 mcpControl Hyper-V VMs, graphical consoles, guest automation and user/kernel debugging through a native C# stdio MCP server.JerryLinLinLin112
claude-code1.0.0Nuvel integration plugin for Anthropic Claude Code CLIFolken23 skills1 mcpNuvel integration plugin for Anthropic Claude Code CLIFolken2312
no-declaration1.0.0Negative control: declares nothing about skills at all.roryeckel1 skillsNegative control: declares nothing about skills at all.roryeckel102
hpc-crux0.1.0Facility-specific HPC workflow skills for Crux (ALCF). Install the hpc base plugin first for MCP tools.william-dawson7 skillsFacility-specific HPC workflow skills for Crux (ALCF). Install the hpc base plugin first for MCP tools.william-dawson702
writing-release2.0.0Runs the release cycle: integration lanes into main, pull requests as merge commits, CI-cut releases, tooling by repo contents, channels, and recovery.CrackingShells1 skillsRuns the release cycle: integration lanes into main, pull requests as merge commits, CI-cut releases, tooling by repo contents, channels, and recovery.CrackingShells102
ai-team-orchestration2.0.0Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.DarthCoder501Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.DarthCoder501001
arcade-canvas1.0.2Play five retro Phaser mini-games in a Copilot canvas while agents work.dkhautomationPlay five retro Phaser mini-games in a Copilot canvas while agents work.dkhautomation001
domain-check1.0.0Find, check and price domain names, and register them.kody-w1 mcpFind, check and price domain names, and register them.kody-w011
artifactory-system-monitor0.1.3A live system monitor your agent can read and show beside your chat, as an example app for Dimension.insodimension1 mcpA live system monitor your agent can read and show beside your chat, as an example app for Dimension.insodimension011
instructions-authoringInstruction-authoring workflow skills for AI agents: creating portable instruction packages, writing and auditing controlled-English agent instructions, assessing agent skills for readiness, and diagnosing instruction defects.sjinks4 skillsInstruction-authoring workflow skills for AI agents: creating portable instruction packages, writing and auditing controlled-English agent instructions, assessing agent skills for readiness, and diagnosing instruction defects.sjinks401
blazium-engine0.8.0Engine skills: languages, scenes, 2D/physics, presentation, resources, localization, and multiplayer core. Blazium 0.8.x (Godot 4.8.x fork, branch `blazium_4.8`).blazium-gamesEngine skills: languages, scenes, 2D/physics, presentation, resources, localization, and multiplayer core. Blazium 0.8.x (Godot 4.8.x fork, branch `blazium_4.8`).blazium-games001
emil-skills0.8.0Emil Kowalski's design engineering skills: web and native animation, motion choreography, UI polish, review and audit, performance, platform design, Swift, and library choices.ShanireZ17 skillsEmil Kowalski's design engineering skills: web and native animation, motion choreography, UI polish, review and audit, performance, platform design, Swift, and library choices.ShanireZ1701