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
301 issue-logger-conventionssuperplanehq/superplaneWhen creating or editing general SuperPlane issue drafts in tmp/pmlogger, or when working in the issue-logger workflow. Cursor rule 0 until used 5.6k A
302 THEME_SETUPAnil-matcha/awesome-generative-ai-appsThis library uses next-themes to manage light and dark modes. For the theme switching buttons to work correctly, you must wrap your application with the provided AgentThemeProvider. Agent 0 until used 3.1k A
303 triagedoobidoo/mcp-memory-serviceScan, classify, and fix security alerts for mcp-memory-service. Command 0 until used 1.9k A
304 sonicjs-release-announcementSonicJs-Org/sonicjsYou are a specialized agent that creates compelling release announcements for SonicJS across multiple platforms. Your primary responsibilities are. Command 0 until used 1.7k A
305 pdf-viewer-and-annotator-architectureOpen-Source-Legal/OpenContractsWhen working on pdf annotations or pdf rendering, consult this high level overview. Cursor rule 0 until used 1.5k A
306 Addaxwgzhao/AddaxA reference guide to Addax, an open-source tool for copying data between different databases, files, and other data systems. It explains Addax's jobs, readers, writers, transformations, channels, and task groups. Skill 0 until used 1.4k A
307 agentServerConversationsmicrosoft/TypeAgentThe agentServer manages explicit, named conversations with full CRUD semantics. Each conversation has its own isolated dispatcher instance, chat history, conversation memory, and persist directory. Multiple clients can connect to the same conversation simultaneously and share state; clients connected to different… Agent 0 until used 738 A
308 AUDIT_MANIFESTlangwatch/langwatchTotal unimplemented-tagged scenarios: 76 Classified: 76. Agent 0 until used 3.5k A
309 dediboxscaleway/scaleway-cliCommand "dedibox" from scaleway/scaleway-cli, covering documentation for scw dedibox, billing commands, download-invoice dedibox resources, download-refund dedibox resources and get-invoice dedibox resources. Command 0 until used 996 A
310 domainAmanVarshney01/create-better-t-stackHow the engineering skills should consume this repo's domain documentation when exploring the codebase. Agent 0 until used 5.7k A
311 speakpchalasani/claude-code-toolsEnable, disable, or configure voice feedback. Command 0 until used 2.0k A
312 cursoragentrhq/webcmdFetch and follow https://raw.githubusercontent.com/agentrhq/webcmd/main/start.md to set up Webcmd end to end. Agent 0 until used 1.6k A
313 hermesagentrhq/webcmdFetch and follow https://raw.githubusercontent.com/agentrhq/webcmd/main/start.md to set up Webcmd end to end. Agent 0 until used 1.6k A
314 baremetalscaleway/scaleway-cliCommand "baremetal" from scaleway/scaleway-cli, covering documentation for scw baremetal, baseboard management controller (bmc) management commands, get bmc access, start bmc access and stop bmc access. Command 0 until used 996 A
315 defaultSWE-agent/mini-swe-agent!!! note "DefaultAgent class". Agent 0 until used 6.9k A
316 test-document-knowledge-baseOpen-Source-Legal/OpenContractsWhen testing or our pdf.js annotations. Cursor rule 0 until used 1.5k A
317 location_taggerOpen-Source-Legal/OpenContractsThe Location Tagger is a built-in, global default agent that automatically finds place names in a document and turns them into geocoded annotations: OCCOUNTRY, OCSTATE, and OCCITY. Each annotation it creates carries the resolved coordinates and administrative codes in its data payload, so the places show up as pins on… Agent 0 until used 1.5k A
318 LOCAL_CLI_WRAPPERTeam-Commonly/commonlyWrap any locally-installed AI agent CLI (claude, codex, cursor, gemini, …) as a Commonly pod participant. Your laptop becomes the runtime; Commonly provides identity, memory, and the social surface. Agent 0 until used 1.3k A
319 agent-patternsmicrosoft/TypeAgentEvery TypeAgent agent exports an instantiate(): AppAgent function and implements the AppAgent interface from @typeagent/agent-sdk. Beyond that common contract, agents fall into nine patterns based on how they communicate with external systems, whether they manage persistent state, and what kind of output they produce. Agent 0 until used 738 A
320 geminiamantus-ai/vibetunnelExecute Gemini CLI with the context from docs/gemini.md for large codebase analysis. Command 0 until used 4.6k A
321 analyzerwarpdotdev/warpAnalyze blind comparison results to understand WHY the winner won and generate improvement suggestions. Agent 0 until used 65k A
322 verifyEmanuele-web04/synaraHow to launch an isolated Synara instance (server + web) to observe UI changes, without touching /.synara or the default dev ports. Skill 0 until used 1.6k A
323 comparatorwarpdotdev/warpCompare two outputs WITHOUT knowing which skill produced them. Agent 0 until used 65k A
324 code-architect-reviewerlingodotdev/lingo.devUse this agent when you need expert code review focusing on architectural quality, clean code principles, and best practices. Examples: Context: User has just written a new service class and wants architectural feedback. user: 'I just implemented a user authentication service. Can you review it?' assistant: 'I'll use… Agent 0 until used 5.4k A
325 reviewer-writingWUBING2023/PaperSpineRead references/audit.md for the full audit stage playbook. Agent 0 until used 5.0k A
326 datasetsFinMind/FinMindComplete dataset list with column details, tier requirements, and parameter specifications. Command 0 until used 2.8k A
327 weaveAtaraxy-Labs/weaveEntity-level semantic merge driver for Git. Resolves conflicts at the function/class level instead of the line level, so two changes to different functions in the same file never conflict. Skill 0 until used 1.3k A
328 multi-server-state-isolationuzairansaruzi/hermexWhich app state is per-server versus intentionally global, where each lives, and which tests guard the isolation. Almost all isolation holds by construction through the server-keyed view tree and cache keys described below; "Clear Offline Cache" is explicitly scoped to the active server. Agent 0 until used 1.2k A
329 bugstw93/PakeProactively sweep a Pake area for latent UX and runtime defects before users report them, using this repo's own fix history and boundary archetypes, and confirm every finding with a probe run this turn. Use for 找找有没有bug, 主动找bug, 有没有隐患, 排查隐患, 举一反三, 上线前扫一遍, 这块可靠吗, latent bug scan, sibling sweep after a fix. Not for an… Skill 0 until used 61k A
330 reviewer-evidenceWUBING2023/PaperSpineRead references/audit.md for the full audit stage playbook. Agent 0 until used 5.0k A
331 HAPPY_STACKS_EDISON_WRAPPERhappier-dev/happierThis repo (happier-dev) is a hstack project. Edison must be invoked via the hstack wrapper so stack/worktree context is enforced. Agent 0 until used 1.6k A
332 port-sacred-terminal-ui-to-pythoninternet-development/www-sacredTake a React Window.tsx (or any sacred component) and produce a terminal CLI screen written in Python that uses Simulacrum's Python mirror in scripts/python/sacredcli/. Simulacrum is the sacred CLI framework — the JavaScript half lives in scripts/cli/lib/, the Python half is a one-to-one snakecase mirror. Skill 0 until used 1.6k A
333 REGISTRYsceneview/sceneviewThis directory ships the SceneView SDK as agent skills for AI coding assistants. Each skill is a self-contained SKILL.md (with references/) that an agent loads to get the API contract, recipes, and migration guide for one SceneView platform. Agent 0 until used 1.3k A
334 varlock-agent-readinessdmno-dev/varlockUse this skill to discover machine-readable metadata published by varlock.dev. Skill 0 until used 4.2k A
335 package-docs-generatorformkit/formkitUse this agent when the user wants to generate, update, or create CLAUDE.md documentation for a FormKit package. This includes when the user asks to document a specific package's architecture, wants to understand how a package works, or needs to create onboarding documentation for future LLMs working with the… Agent 0 until used 4.8k A
336 CONTRACTchdb-io/chdbOne behavior, many bindings. This document is the single source of truth for the chDB agent-tool surface. chdb.agents.ChDBTool (Python) is the reference implementation; the TypeScript binding (chdb-node) and any future language binding under chdb-io implement the same methods with the same semantics and are verified… Agent 0 until used 2.9k A
337 ideationOpenRaiser/NanoResearchYou are the Ideation Agent for NanoResearch. Your job is to search academic literature and generate novel research hypotheses. Command 0 until used 1.4k A
338 planningOpenRaiser/NanoResearchYou are the Planning Agent for NanoResearch. Your job is to design a detailed experiment blueprint from the ideation output. Command 0 until used 1.4k A
339 i18nuzairansaruzi/hermexHermex ships one String Catalog, HermesMobile/Resources/Localizable.xcstrings, included in the app, widget, and share-extension targets. Every user-facing literal is already externalized (String(localized:) / LocalizedStringKey), so adding a language is normally translation-only — no Swift edits. Agent 0 until used 1.2k A
340 convert-to-todowrite-tasklist-promptcentminmod/my-claude-code-setupPurpose: Transform verbose, context-heavy slash commands into efficient TodoWrite tasklist-based methods with parallel subagent execution for 60-70% speed improvements. Command 0 until used 2.6k A
341 analyzerCherryHQ/cherry-studioAnalyze blind comparison results to understand WHY the winner won and generate improvement suggestions. Agent 0 until used 51k A
342 graderCherryHQ/cherry-studioEvaluate expectations against an execution transcript and outputs. Agent 0 until used 51k A
343 create-release-notecentminmod/my-claude-code-setupGenerate comprehensive release documentation from recent commits, producing two distinct outputs: a customer-facing release note and a technical engineering note. Command 0 until used 2.6k A
344 evaluate-diagramllmsresearch/paperbananaEvaluate a generated diagram against a human reference using PaperBanana's VLM-as-Judge scoring. Skill 0 until used 2.3k A
345 generate-plotllmsresearch/paperbananaGenerate a publication-quality statistical plot from a data file using PaperBanana. Skill 0 until used 2.3k A
346 implementsouthleft/figma-console-mcpImplement a feature or fix using best practices for this MCP server project. Command 0 until used 2.2k A
347 commitelirantutia/vibeyardCreate a git commit for the current staged (or unstaged) changes using a structured commit message convention. Command 0 until used 1.4k A
348 synthesis-reviewerHuman-Agent-Society/CORALVerify that every claim in a research note is grounded in its linked raw sources. Agent 0 until used 935 A
349 dedup-judgeHuman-Agent-Society/CORALDecide what to do with two notes flagged as near-duplicates — without knowing which is which. Agent 0 until used 935 A
350 add-new-servicekossakovsky/selfhost-aiAdd a new optional service called $ARGUMENTS to the Selfhost AI project. Command 0 until used 921 A
351 swc-pluginvercel/workflowThe specification for how to plugin is meant to work can be found in spec.md. Cursor rule 0 until used 2.4k A
352 release-noteselirantutia/vibeyardGenerate release notes for this project and save them to CHANGELOG.md. Command 0 until used 1.4k A
353 THREE.TerrainIceCreamYou/THREE.TerrainUse this guide when an agent must build, modify, inspect, or document a terrain scene with THREE.Terrain. The library creates heightmapped Three.js terrain and provides procedural generators, filters, material blending, decoration tools, grass, image conversion, analysis, and seeded randomness. Skill 0 until used 891 A
354 safaristeipete/macos-automator-mcpThis file, safari.mdc, serves as a repository for detailed working notes, observations, and learnings acquired during the process of automating Safari interactions, particularly for the MCP Inspector UI. It's intended to capture the nuances of trial-and-error, debugging steps, and insights into what worked, what… Cursor rule 0 until used 875 A
355 skillAnionex/dsh-vision-toolkitTen native DSH tools give a text-only agent eyes. Use these structured tools directly; do not shell out to the bundled Python scripts or reproduce their implementation. Vision API credentials and model settings are managed by the plugin, so tool calls do not receive credentials. Skill 0 until used 842 A
356 adding-an-agent-providermattpocock/sandcastleThis document is for contributors adding support for a new agent (e.g. Claude Code, Codex, gemini-cli) as a built-in agent provider. It covers. Agent 0 until used 7.7k A
357 graderaipoch/open-scienceEvaluate expectations against an execution transcript and output files. Grade evidence, not the executor's claims, and also identify weak expectations that could create false confidence. Agent 0 until used 3.3k A
358 reversi-masteredison7009/EchoBirdOne-click install + model switch:Claude Code,Codex CLI (OpenAI), Grok Build (xAI), DeepSeek Harness, Kimi Code (Moonshot) ,Qwen Code,Aider,OpenCode,MiMo Code (Xiaomi),ZCode (Z.AI),OpenClaw,Pi,OpenScience,Vibe-Trading,Claude Desktop (3P profile),ChatGPT desktop,OpenCode Desktop. Skill 0 until used 3.1k A
359 create-releasejoshuayoes/ios-simulator-mcpCreate a GitHub release based on commits since the previous tag. Generate release notes, create the release using the GitHub CLI, and verify the post-release workflow status. Command 0 until used 2.2k A
360 _indextontinton/maki+++ title = "Commands" weight = 8 [extra] group = "Reference" +++. Command 0 until used 977 A
361 debugging-hanging-pytest-runsPipelex/pipelexAudience. Future-me (or any agent) the next time a make agent-test / pytest -n auto run in this repo hangs without finishing. The common causes here are xdist worker crash-and-replace cycles and fixture-teardown hangs; the iteration loop below generalizes to any hanging suite. Agent 0 until used 852 A
362 design-system-checkerJimLiu/baoyu-designYou are a read-only validator for a portable design system. Your only job is to run the checker script, relay what it found, and add a one-line health summary. You must not modify, create, or delete any file, run the compiler, serve anything, or take any other action. You read and report — nothing else. Agent 0 until used 3.6k A
363 analyzeraipoch/open-scienceAfter a valid blind comparison, unblind the result and explain why the winner performed better. Turn the evidence into generalizable Skill improvements rather than copying one output. Agent 0 until used 3.3k A
364 add-mcpVRSEN/OpenSwarmYour task is to add Model Context Protocol (MCP) server to an Agency Swarm agent. MCP servers expose external tools and data sources to agents through a standardized protocol. Command 0 until used 2.9k A
365 testsouthleft/figma-console-mcpRun tests and ensure code quality for the Figma Console MCP server. Command 0 until used 2.2k A
366 bestmoderaphaelmansuy/edgequakeYou are an agent - please keep going until the user’s query is completely resolved, before ending your turn and yielding back to the user. Agent 0 until used 2.1k A
367 publicalsk1992/CloddsBotFor agents: This document explains how to integrate with Clodds APIs. Skill 0 until used 821 A
368 mcp-code-execVRSEN/OpenSwarmYour task is to convert an MCP server into the Code Execution Pattern described in Anthropic's blog post. This pattern enables progressive disclosure of tools, reducing token usage by up to 98% compared to loading all tools upfront. Command 0 until used 2.9k A
369 svelterilldata/rillSvelte best practices and patterns for modern web applications. Cursor rule 0 until used 2.9k A
370 binance-netJKorf/Binance.NetConventions for using Binance.Net library when working with Binance cryptocurrency exchange in C#/.NET. Apply when generating code that interacts with Binance API. Cursor rule 0 until used 1.2k A
371 tanstack-react-router_apiopenstory-so/openstoryThe ActiveLinkOptions type extends the LinkOptions type and contains additional options that can be used to describe how a link should be styled when it is active. Cursor rule 0 until used 519 A
372 aggregatingupstash/redis-jsRun analytics over indexed data using metric and bucket aggregations. Compute statistics, group documents, build histograms, and perform faceted navigation. Aggregations can be nested for multi-level analysis. Command 0 until used 967 A
373 queryingupstash/redis-jsQuery documents from a search index using type-safe filters with support for pagination, sorting, field selection, scoring, and highlighting. Count matching documents efficiently without returning results. Command 0 until used 967 A
374 cursorrulesThe-Pocket/PocketFlow-Tutorial-Codebase-KnowledgeCursor rule "cursorrules" from The-Pocket/PocketFlow-Tutorial-Codebase-Knowledge, covering agentic coding: humans design, agents code!, agentic coding steps, example llm project file structure, pocket flow and core abstraction. Cursor rule 0 until used 13k A
375 frontend-developmentrilldata/rillCursor rule "frontend-development" from rilldata/rill, covering frontend development guidelines, technology stack, web applications, component architecture and shared components (web-common). Cursor rule 0 until used 2.9k A
376 generateactionbook/actionbookGenerate web scraper scripts using Actionbook's verified selectors. Command 0 until used 1.6k A
377 criticaddsumtech/slides_makerYou are an independent, demanding presentation critic — think of yourself as the presenter's sharpest senior colleague doing a dry-run review the day before the talk. You did NOT build this deck, and that is the point: judge what is actually on the slides, not what the author intended. Your job is to catch every… Agent 0 until used 490 A
378 indexdatachain-ai/datachainDataChain is a command-line tool for wrangling unstructured AI data at scale. Use datachain -h to list all available commands. Command 0 until used 2.8k A
379 ERROR-FIXteaql/teaql-agent-kitA model-mediated harness for reliable agentic software development. Agent 0 until used 2.8k A
380 content-planneraddsumtech/slides_makerYou are the deck's lead content strategist — the constructive counterpart to the critic/arbiter judges. You did the reading no one else did, and you turn it into a narrative a real audience will follow and remember. Think like an experienced subject-matter expert who also knows how to tell a story: you grasp the… Agent 0 until used 490 A
381 directorcalesthio/OpenMontageTurn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md. Agent 0 until used 55k A
382 wiki-graphSamurAIGPT/llm-wiki-agentBuild the LLM Wiki knowledge graph. Command 0 until used 3.5k A
383 wiki-ingestSamurAIGPT/llm-wiki-agentIngest a source document into the LLM Wiki. Command 0 until used 3.5k A
384 deploychrisryugj/korean-law-mcpA deployment command guide for this project’s npm release process and its shared production MCP host. MCP is a standard way for software tools to expose capabilities to AI agents. Command 0 until used 2.5k A
385 specigorkasyanchuk/active_storage_validationsShared RSpec conventions for the gem suite. Cursor rule 0 until used 1.2k A
386 building-agentspromptise-com/FoundryCreate intelligent agents that connect to MCP servers, discover tools automatically, and execute tasks with full observability. Agent 0 until used 869 A
387 vertex-deployGoogleCloudPlatform/vertex-ai-samplesSkill "vertex-deploy" from GoogleCloudPlatform/vertex-ai-samples, covering vertex ai model garden deploy skill, 1. prerequisites, 2. discovering deployable models, 3. deploying a model and example: deploying gemma 3. Skill 0 until used 780 A
388 vertex-inferenceGoogleCloudPlatform/vertex-ai-samplesSkill "vertex-inference" from GoogleCloudPlatform/vertex-ai-samples, covering vertex ai genai inference skill, 1. authentication (critical), 2. gemini models, choosing the right sdk and installation. Skill 0 until used 780 A
389 tanstack-react-router_setup-and-architectureopenstory-so/openstoryTanStack Router: Setup and Architecture. Cursor rule 0 until used 519 A
390 js-sdk-genai-framework-instrumentationopenlit/openlitGuide for implementing JS SDK agent and framework instrumentations, such as LangChain, LangGraph, OpenAI Agents, Claude Agent SDK, Google ADK, and Vercel AI. Cursor rule 0 until used 2.7k A
391 reasoning-patternspromptise-com/FoundryEvery Promptise agent is powered by a Reasoning Graph. By default, buildagent() creates a ReAct graph (single node with tools) — and that default is smart by default: it manages context automatically (contextscope="auto"), so simple tasks are unchanged and deep tool loops stay token-efficient without you choosing… Agent 0 until used 869 A
392 excelgetomnico/omniAfter fetching an Excel file with readdocument, run excel inspect first via runbash. This shows: sheet names, dimensions, merged cell regions, detected header row, and a data preview. Review the output carefully before writing any processing code. Skill 0 until used 764 A
393 geo-optimizer-skillAuriti-Labs/geo-optimizer-skillRun geo audit first. It scores the site 0–100 across 8 categories and generates a prioritized action list. Skill 0 until used 744 A
394 planaitytech/agentkits-marketingCreate a comprehensive, research-backed campaign brief that leverages accumulated knowledge and templates. Command 0 until used 592 A
395 release-bundle-testingcallstackincubator/rozeniteRozenite is a development tool. Whatever a project wires into its bundler config, a release build must ship none of our code. @rozenite/test-utils provides the bench that proves it, and every plugin owns a Vitest suite in src/tests/release-bundle.test.ts that uses it. Agent 0 until used 653 A
396 buildercalesthio/OpenMontageTurn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared… Agent 0 until used 55k A
397 finmindFinMind/FinMindYou are a FinMind financial data assistant. Help the user query financial data from the FinMind API based on their natural language request. Command 0 until used 2.8k B
398 coding-agents-hookopenlit/openlitAuthoring and testing coding-agent hook adapters, including payload probing, session state, capture modes, and plugin manifests. Consult the telemetry convention when changing canonical attributes. Cursor rule 0 until used 2.7k A
399 issue-trackersamanhappy/mcphubIssues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations. Agent 0 until used 2.4k A
400 analyzeactionbook/actionbookAnalyze a webpage's structure using Actionbook's verified selectors and show available elements for scraping. Command 0 until used 1.6k 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.