Every mod, cheapest first

Ranked by what a mod adds to every session before you have asked anything; equal costs break by stars gained this week, so the near-free mods people are picking up right now lead. A zero is real — a rule with globs costs nothing until a file matches — and everything else is a number you can check against the source.

#ModTypeTokens / sessionThis weekStarsScanRating
201 flow-developnyldn/claude-octopusMulti-AI implementation using available external providers (Double Diamond Develop phase). Skill 0 until used 4.0k A
202 create-planspree/spreeCreate a new architecture/feature plan document. Command 0 until used 16k A
203 piopenagents-org/openagentsOpenAgents supports Pi, Earendil's coding agent for the terminal — executable pi, distributed as the npm package @earendil-works/pi-coding-agent. Agent 0 until used 4.0k A
204 CHANGELOGbytedance/UI-TARS-desktopCommand "CHANGELOG" from bytedance/UI-TARS-desktop, covering 0.4.0 2024-12-10 - add logging, 1.2.29, 1.2.28, 1.2.26 and 1.2.25. Command 0 until used 39k A
205 docs-guideHelicone/heliconeA streamlined guide for creating consistent, high-quality feature documentation. Cursor rule 0 until used 6.1k A
206 CLAUDEUfoMiao/zcfLast Updated: Mon Oct 27 19:39:26 CST 2025. Command 0 until used 6.1k A
207 evaluatorQ00/ouroborosYou perform 3-stage evaluation to verify workflow outputs meet requirements. Agent 0 until used 5.7k A
208 analyze-resultsGalaxy-Dawn/claude-scholarRun a blocker-first post-experiment workflow: validate evidence, produce strict statistical analysis when possible, and generate a decision-oriented results report only when the analysis bundle is sufficient. Uses results-analysis + results-report as a gated two-stage workflow. Command 0 until used 5.3k A
209 nanoclawopenagents-org/openagentsNanoClaw lets a NanoClaw Agent Group act as an OpenAgents Workspace agent. Unlike most OpenAgents agents, NanoClaw is not a stdin/stdout CLI and not a direct LLM API — it is an independent containerized agent runtime. Each Agent Group runs in its own Docker container (Apple Container on macOS; WSL2 on Windows), with… Agent 0 until used 4.0k A
210 offensive-vuln-classesSnailSploit/Claude-RedExploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit… Skill 0 until used 3.0k A
211 offensive-edr-evasionSnailSploit/Claude-RedEDR evasion offensive checklist: hook unhooking (user/kernel), direct syscalls, PPID spoofing, process injection variants, AMSI bypass, ETW patching, memory encryption, and behavior-based evasion. Use when planning EDR bypass during red team engagements or researching AV/EDR evasion techniques. Skill 0 until used 3.0k A
212 TODObytedance/UI-TARS-desktopThe Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra. Command 0 until used 39k A
213 init-architectUfoMiao/zcfAdaptive initialization: concise at root + detailed at module level; staged traversal with coverage reporting. Agent 0 until used 6.1k A
214 ui-ux-designerUfoMiao/zcfUse this agent when you need UI/UX design guidance, Current Project UI Framework implementation advice, or visual design improvements for the desktop application interface. Examples: Context: User wants to improve the layout of a chat interface component. user: "I want to improve the chat interface layout to make it… Agent 0 until used 6.1k A
215 beeaiIBM/mcp-context-forgeBeeAI Framework is a dual-language framework for building agentic applications in Python and TypeScript. It can use tools exposed by any MCP server through BeeAI's MCPTool, which discovers remote tools from an MCP client and makes them available to BeeAI agents. Agent 0 until used 4.4k A
216 auth-and-securitykiali/kialiKiali's authentication system lives in handlers/authentication/. At startup a single AuthController is instantiated based on the auth.strategy configuration field. The controller drives the full session lifecycle: login, per-request validation, and logout. Agent 0 until used 3.6k A
217 frontend-architecturekiali/kialiThe frontend lives entirely under frontend/. The production artifact is built with react-scripts and served from the Go backend as static files. In development, MSW (Mock Service Worker) can be enabled to run the frontend without a live backend (REACTAPPMOCKAPI=true). Agent 0 until used 3.6k A
218 management-autopr-review-criticAzure/azure-sdk-for-javaAgent "management-autopr-review-critic" from Azure/azure-sdk-for-java, covering management autopr review critic and management autopr review critique. Agent 0 until used 2.6k A
219 create-pull-requestliam-hq/liamThis guide explains how to create pull requests using GitHub CLI in our project. Command 0 until used 5.1k A
220 architectspree/spreeYou are the architecture planning agent for Spree Commerce. Agent 0 until used 16k A
221 potpie-featurepotpie-ai/potpieUse Potpie context before feature work. Load potpie-project-preferences first, and load potpie-infra-architecture when the change touches services, deployment, adapters, or runtime behavior. Command 0 until used 5.7k A
222 potpie-recordpotpie-ai/potpieRecord durable Potpie learnings after useful work. Command 0 until used 5.7k A
223 quickstartgeneralaction/emdashAgent "quickstart" from generalaction/emdash, covering quickstart, toolchain, core commands, validation commands and important notes. Agent 0 until used 5.5k A
224 commit-push-prpollinations/pollinationsCommit and push changes safely. Follows branch rules to avoid mistakes. Command 0 until used 5.0k A
225 pluginsevalstate/fast-agentPlugins package reusable slash commands such as /find, /peek, or /edit-last, post-user-turn displays, or both. They install into the active project or global fast-agent home under plugins/ and are enabled by name from that scope's configuration file. Agent 0 until used 3.9k A
226 server-types-runtime-onlytruefoundry/trueforgeAgentUIServer / server-port types are defined only in assistant-ui-runtime; UI re-exports. Cursor rule 0 until used 4.9k A
227 varlockdmno-dev/varlockRules for working with varlock env-spec files, providing syntax highlighting, autocompletion, and validation for environment variable specifications. Cursor rule 0 until used 4.2k A
228 custom-agentsgoogle/adk-docsSupported in ADK Python v0.1.0 TypeScript v0.2.0 Go v0.1.0 Java v0.1.0 Kotlin v0.1.0. Agent 0 until used 1.5k A
229 interactiveSWE-agent/mini-swe-agent!!! note "InteractiveAgent class". Agent 0 until used 6.9k A
230 release-swiftrobinebers/openusageCut a release of OpenUsage (Swift menu-bar app): pick a version, generate a categorized changelog, tag from main, and publish the GitHub Release with notes. Use to ship an Early Access beta or a stable release. Skill 0 until used 4.0k A
231 docssamuelgursky/davinci-resolve-mcpThis document gives AI assistants the context needed to use the DaVinci Resolve MCP server effectively. It covers the tool landscape, page prerequisites, common workflow patterns, error recovery, and known gotchas. Skill 0 until used 2.3k A
232 openclawsimular-ai/Agent-SAgent-S is a powerful autonomous agent that can control your computer's graphical interface to complete complex tasks. It combines vision and action understanding to interact with any GUI element. Skill 0 until used 12k A
233 solid-jschakra-ui/arkWhen writing code for Solid.js, follow these rules. Cursor rule 0 until used 5.4k A
234 test-enterpollinations/pollinationsRun tests for enter.pollinations.ai service. Command 0 until used 5.0k A
235 openagentdarrenhinde/OpenAgentsControlYour intelligent assistant for questions, tasks, and workflows. Agent 0 until used 4.8k A
236 llm-agentsgoogle/adk-docsSupported in ADK Python v0.1.0 TypeScript v0.2.0 Go v0.1.0 Java v0.1.0 Kotlin v0.1.0. Agent 0 until used 1.5k A
237 editorTheCraigHewitt/seomachineYou are a professional content editor specializing in making technical content sound human, engaging, and authentic while maintaining accuracy and SEO value. Agent 0 until used 7.4k A
238 articleTheCraigHewitt/seomachineA unified content creation pipeline that produces comprehensive, SEO-optimized articles through mandatory research, strategic planning, and section-by-section writing. Command 0 until used 7.4k A
239 writeTheCraigHewitt/seomachineUse this command to create comprehensive, SEO-optimized long-form blog content. Command 0 until used 7.4k A
240 planning-agents-guidedarrenhinde/OpenAgentsControlThe planning agent ecosystem consists of five specialized agents that work together to transform feature requirements into actionable implementation plans. Agent 0 until used 4.8k A
241 langchainIBM/mcp-context-forgeLangChain is a framework for developing applications powered by language models. Integrating LangChain with the Model Context Protocol (MCP) allows agents to utilize tools defined across one or more MCP servers, enabling seamless interaction with external data sources and services. Agent 0 until used 4.4k A
242 visual-testskyhook-io/radarVisually test Radar changes against a real cluster using Playwright MCP. Takes screenshots, organizes them, and reports what looks right or wrong. Command 0 until used 3.2k A
243 semioticnteract/semioticSemiotic React data visualization — 30+ chart types (line, bar, network, geo, streaming), push API, MCP server, TypeScript strict mode. Cursor rule 0 until used 2.7k A
244 plugin-developmenthigress-group/higressPlugin Development Standards - Applies to all new wasm and golang-filter plugins. Cursor rule 0 until used 9.3k A
245 keyword-mapperTheCraigHewitt/seomachineYou are a keyword optimization specialist focused on analyzing keyword usage patterns and ensuring natural, effective keyword integration throughout long-form content. Agent 0 until used 7.4k A
246 generated-and-runtime-notesilysenko/codex-desktop-linuxDo not edit or commit generated application/package state. Agent 0 until used 3.7k A
247 validation-playbookilysenko/codex-desktop-linuxAgent "validation-playbook" from ilysenko/codex-desktop-linux, covering validation playbook, fast source checks, source-security matrix, baseline build and features. Agent 0 until used 3.7k A
248 qawolfCliRunResults.templateqawolf/cliHow to use what qawolf run get --run-id --json returns, and how to read the Playwright trace it links to. Command 0 until used 3.4k A
249 snippet_testsdagster-io/dagsterWhen updating tests in this directory, always run them to validate that they succeed. To do so, run. Cursor rule 0 until used 16k A
250 test-reviewdatahub-project/datahubReview DataHub smoke and integration tests for standards compliance and quality. Command 0 until used 13k A
251 CLAUDEPrefectHQ/marvinAI agents with tool access, memory, and autonomous decision-making capabilities. Agent 0 until used 6.2k A
252 installrunkids/skillshareAdd skills from GitHub repos, git URLs, or local paths. Command 0 until used 2.6k A
253 awesome-chatgpttaishi-i/awesome-ChatGPT-repositoriesSearch awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs. Command 0 until used 3.2k A
254 researchdgunning/edgartoolsYou are tasked with conducting comprehensive research to answer user questions by spawning parallel sub-agents and synthesizing their findings. This is Phase 1 of the Frequent Intentional Compaction (FIC) workflow. Command 0 until used 2.6k A
255 challengerbradygaster/squadI handle: Fact-checking, counter-hypothesis testing, verification, constructive challenge I do not handle: Implementation, code writing, architecture design — I review, not build On rejection: Specific items needing correction + verification methods provided. Agent 0 until used 3.1k A
256 audit-rulesrunkids/skillshareBrowse, enable, disable, and customize audit rules. Command 0 until used 2.6k A
257 pycrazyguitar/pysheeetComprehensive Python programming reference covering syntax, concurrency, networking, databases, ML/LLM development, and HPC. Use for: Python questions, Python interview preparation, debugging, performance optimization, async patterns, library examples, code review, best practices, MLOps workflows, distributed… Skill 0 until used 8.2k A
258 interceptorsBitterbot-AI/bitterbot-desktopExecutable skill interceptors turn passive markdown skills into deterministic behavioral guardrails. When the agent proposes a tool call, registered interceptors inspect the action, read the agent's current state (hormonal, GCCRF, channel, recent turns), and may modify, inject context into, require a prerequisite for… Agent 0 until used 2.5k A
259 repo-workflow-guideGetStream/Vision-AgentsUse this agent when you need to understand or follow project-specific development guidelines, coding standards, or workflow instructions that are documented in the docs/ai directory. This agent should be consulted before starting any development work, when uncertain about project conventions, or when you need… Agent 0 until used 8.1k A
260 Devinopenclaw/acpxDevin requires Windsurf-compatible client metadata during ACP initialization. acpx satisfies this by detecting Devin ACP launches and advertising a narrow Windsurf identity shim. Agent 0 until used 3.2k A
261 ZeroClawopenclaw/acpxAgent "ZeroClaw" from openclaw/acpx, covering zeroclaw, agent selection, notes and connecting to a running gateway. Agent 0 until used 3.2k A
262 semAtaraxy-Labs/semSemantic version control CLI. Entity-level diffs for Git (functions, classes, methods instead of lines). Skill 0 until used 3.3k A
263 meeting-uiVexa-ai/vexaAgent "meeting-ui" from Vexa-ai/vexa, covering data hooks, actions, ui vocabulary, go-live gate and rules. Agent 0 until used 2.7k A
264 agent-browserColeMurray/background-agentsUse agent-browser from bash when you need visual verification in the sandbox. Skill 0 until used 2.7k A
265 interceptors-author-guideBitterbot-AI/bitterbot-desktopHow to author and register a new pre-action interceptor (PLAN-20). Agent 0 until used 2.5k A
266 deep_research_agentGCWing/BitFunYou are a senior research analyst and orchestrator. Your job is to produce a deep-research report that reads like investigative journalism — specific, sourced, opinionated, and grounded in evidence. You run a structured 6-phase quality pipeline where specialists, debaters, and a fact-checker each play a distinct role… Agent 0 until used 1.9k A
267 export-productbuildermethods/design-osYou are helping the user export their complete product design as a handoff package for implementation. This generates all files needed to integrate the UI designs into a real codebase. Command 0 until used 1.8k A
268 verifiercobusgreyling/loop-engineeringYou are the independent verifier for the Changelog Drafter loop. Agent 0 until used 11k A
269 avoid-ai-writingconorbronsdon/avoid-ai-writingAudit and rewrite content to remove AI writing patterns ("AI-isms"). Activate whenever editing prose-heavy files (Markdown, documentation, blog posts, READMEs, release notes, emails). Cursor port of the avoid-ai-writing skill v3.28.0. See https://github.com/conorbronsdon/avoid-ai-writing. Cursor rule 0 until used 3.8k A
270 visual-graderexpo/skillsGrading instructions for an eval run that produced device/web screenshots. You receive the eval prompt, its expectations and visualexpectations, and the run's outputs (screenshots, Metro logs, the static-gate result), and you write grading.json next to the outputs in the shape defined by the eval skill's Grade step. Agent 0 until used 2.5k A
271 team_modeGCWing/BitFunYou are BitFun in Team Mode — a virtual engineering team orchestrator. You coordinate specialized roles through a full sprint workflow to deliver high-quality software. Agent 0 until used 1.9k A
272 releaseyoshiko-pg/difitUpdate CHANGELOG.md with all changes from the latest tag to current commit. Command 0 until used 3.1k A
273 cursorrocketride-org/rocketride-serverUse when working with RocketRide pipelines, SDK, components, or configuration. Cursor rule 0 until used 7.5k A
274 rivetkit-driver-test-writerrivet-dev/actorsUse this agent when the user needs to write, modify, or debug driver tests for RivetKit. This includes creating new test cases in rivetkit-typescript/packages/rivetkit/src/driver-test-suite/tests/.ts, implementing or updating test fixture actors in rivetkit-typescript/packages/rivetkit/fixtures/driver-test-suite/.ts… Agent 0 until used 6.1k A
275 component-review.rulessuperplanehq/superplaneAdd new rules to this list in the same format. Keep each rule focused and testable. Categories define ordering and scope. Command 0 until used 5.6k A
276 gcdatachain-ai/datachainGarbage collect temporary tables, failed dataset versions, and outdated checkpoints. Command 0 until used 2.8k A
277 releasekayba-ai/agentic-context-engineRelease a new version: bump version, update changelog, tag, push, and create a GitHub release. Command 0 until used 2.6k A
278 skillcheckBesty0728/Unity-SkillsA consistency checker for Unity skills, where Unity is a game-development platform and skills are documented or coded actions. It compares C# definitions with SKILL.md files and checks that names, parameters, metadata, and totals agree. Command 0 until used 1.7k A
279 om-auto-update-changelogopen-mercato/open-mercatoOpen Mercato releases must keep CHANGELOG.md, UPGRADENOTES.md, and version-specific downstream migration skills aligned. Apply this contract after the external skill resolves {version}, {date}, and the previous changelog release, but before it edits files or delegates to om-auto-create-pr. Skill 0 until used 1.7k A
280 benchmarkkayba-ai/agentic-context-engineRun a TAU-bench evaluation end-to-end and present results. Command 0 until used 2.6k A
281 releaseGLips/Figma-Context-MCPCommand "release" from GLips/Figma-Context-MCP, covering release and steps. Command 0 until used 16k A
282 project-hierarchy-checkopenlit/openlitUse this command before changing organisation, project, or database config behavior. Command 0 until used 2.7k A
283 agent-provider-architecturenimbalyst/nimbalystThis document is a reference for implementing a new agent provider in Nimbalyst. It is the architectural counterpart to docs/AIPROVIDERTYPES.md (which is end-user / product oriented) and walks through every seam a new agent has to fit through: session start and resume, prompt handling, transcript output, tool calling… Agent 0 until used 1.6k A
284 design-screenbuildermethods/design-osYou are helping the user create a screen design for a section of their product. The screen design will be a props-based React component that can be exported and integrated into any React codebase. Command 0 until used 1.8k A
285 component-example-researcherchakra-ui/arkUse this agent when you need to discover and suggest new examples for Ark UI components. This includes:\n\n \nContext: User is working on enhancing the Checkbox component documentation.\nuser: "I've just finished updating the Checkbox component API. Can you help me find what examples we should add?"\nassistant: "I'll… Agent 0 until used 5.4k A
286 autogendoobidoo/mcp-memory-serviceUse mcp-memory-service as the persistent memory backend for AutoGen 0.4+ multi-agent conversations. Agent 0 until used 1.9k A
287 work-issueyoanbernabeu/grepaiYou are an issue implementation assistant. Follow these steps carefully to implement a GitHub issue from start to finish. Always ask for user confirmation before critical operations. Command 0 until used 1.8k A
288 x64dbg-mcp-serverduty1g/x64dbg-mcp-serverYou are controlling x64dbg through MCP tools. Skill 0 until used 1.8k A
289 researcha5c-ai/babysitterRepository: https://github.com/wshobson/agents Stars: 33,494 ⭐ License: MIT Language: Python Archetype: Claude Code Multi-Agent Orchestration Framework Processing Date: 2026-04-13. Agent 0 until used 1.7k A
290 releaseBesty0728/Unity-SkillsA guided release command for turning a tested beta version into a stable GitHub release. It checks versions, branches, tags, commits, and release notes in a fixed order. Command 0 until used 1.7k A
291 checkpointopenclaw/crabboxSave the state of a lease, then restore it onto another box or fork it into a fresh lease later. A checkpoint turns expensive one-time setup — installed dependencies, warmed caches, generated fixtures, a paused bug — into something you can reproduce on demand without repeating the work. Command 0 until used 1.3k A
292 providersopenclaw/crabboxCommand "providers" from openclaw/crabbox, covering providers, flags, providers sizes, providers describe and json schema v2. Command 0 until used 1.3k A
293 AGENT_RUNTIMETeam-Commonly/commonlyCommonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens. Agent 0 until used 1.3k A
294 workerscloudflare/skillsWhen building applications on Cloudflare Workers or with frameworks that deploy to Cloudflare Workers, strongly prefer retrieval and fetching documentation over training data. Cursor rule 0 until used 2.7k A
295 security-validationopenlit/openlitUse this command before handing off security-sensitive OpenLIT changes. Command 0 until used 2.7k A
296 refactor-functiondoobidoo/mcp-memory-serviceAutomated function complexity reduction using multi-agent workflow. Command 0 until used 1.9k A
297 crewaidoobidoo/mcp-memory-serviceUse mcp-memory-service as the persistent shared memory backend for CrewAI agents and crews. Agent 0 until used 1.9k A
298 sonicjs-pr-makerSonicJs-Org/sonicjsYou are a specialized agent that creates Pull Requests for SonicJS, monitors CI/CD pipelines, analyzes failures, and automatically fixes issues including E2E test failures. Command 0 until used 1.7k A
299 monitor-cinrwl/nx-consoleYou are the orchestrator for monitoring Nx Cloud CI pipeline executions and handling self-healing fixes. You spawn the ci-monitor-subagent subagent to poll CI status and make decisions based on the results. Command 0 until used 1.4k A
300 READMEdiet103/claude-code-infrastructure-showcaseSpecialized agents for complex, multi-step tasks. Agent 0 until used 10k A

Counted with the o200k_base tokenizer at crawl time; mcp, hooks and settings are not measured this way, so they are not ranked here. Two mods per repository at most.