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
401 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 ▲ +3 13k A
402 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 ▲ +3 2.8k A
403 greenlightRevylAI/greenlightIt now lives at skills/greenlight/SKILL.md. Skill 0 until used ▲ +3 2.4k A
404 citraSylphxAI/pdf-reader-mcpSkill "citra" from SylphxAI/pdf-reader-mcp, covering citra — pdf evidence for agents, install, or, tools and sdk. Skill 0 until used ▲ +3 909 A
405 entity-guardopen-mercato/open-mercatoEntity schema-diff guard for the canonical standalone entity file. Cursor rule 0 until used ▲ +3 1.7k A
406 trigger.advanced-tasksagentset-ai/agentsetComprehensive rules to help you write advanced Trigger.dev tasks. Cursor rule 0 until used ▲ +3 2.1k A
407 decideccplugins/awesome-claude-code-pluginsForces structured decision-making and creates an auditable Agent Decision Record (AgDR). Command 0 until used ▲ +3 929 A
408 react-native-best-practicescallstackincubator/agent-skillsReact Native performance — route to react-native-best-practices SKILL.md and profiling first. Cursor rule 0 until used ▲ +3 1.6k A
409 testing-coverageGentleman-Programming/gentleman-guardian-angelEnsure test coverage for all behavior changes in GGA. Skill 0 until used ▲ +3 1.1k A
410 branch-prGentleman-Programming/gentleman-guardian-angelStandardize branch creation and PR submission for the GGA project. Skill 0 until used ▲ +3 1.1k A
411 eventsgroupultra/telegram-searchWhen adding a new event, ensure all of the following are updated in one change. Cursor rule 0 until used ▲ +3 4.1k A
412 openclaw-operatorsbhooley/ainativelangThis path wires gateway env.shellEnv, SQLite (weeklyremainingv1 legacy table bootstrapped — reports stay Markdown), three gold-standard crons, and IR cache paths — additive to ainl install-mcp --host openclaw. Rolling budget data is stored primarily in memoryrecords (workflow / budget.aggregate / weeklyremainingv1)… Agent 0 until used ▲ +3 671 A
413 openclaw-quickstartsbhooley/ainativelangThis guide gets you from zero to generating OpenClaw automations in AINL within one session. Agent 0 until used ▲ +3 671 A
414 burp-correlator25smoking/GwxapkgA tool for matching a raw Burp Suite HTTP request with the corresponding Gwxapkg source API, pseudocode, and call chain. Burp Suite is a web-security tool that records and edits HTTP requests. Agent 0 until used ▲ +3 151 A
415 deslopgroupultra/telegram-searchCheck the diff against main, and remove all AI generated slop introduced in this branch. Command 0 until used ▲ +3 4.1k A
416 insight-writerzach22-1999/amazon-skillsAn agent that writes analysis paragraphs for a fixed 10-chapter report from structured product and market data. It fills insight, findings, and conclusion fields rather than formatting the whole report. Agent 0 until used ▲ +3 172 A
417 report-writerzach22-1999/amazon-skillsAn agent that turns prepared, structured market data into detailed Markdown and shorter HTML reports. The source data includes spreadsheets, product rankings, competitor information, and customer feedback analysis. Agent 0 until used ▲ +3 172 A
418 cet-skillLiuxiangjian-ai/cet-skillSkill "cet-skill" from Liuxiangjian-ai/cet-skill, covering cet skill, purpose, non-negotiable copyright and originality policy, first interaction rule and user profile collection. Skill 0 until used ▲ +3 134 A
419 maintainerPratiyush/llm-wikiMeta-skill that loads all llmwiki governance docs and exposes the three maintainer slash commands. Command 0 until used ▲ +3 383 A
420 releasePratiyush/llm-wikiWalk the llmwiki release process step by step. Command 0 until used ▲ +3 383 A
421 api-auth-analyzer25smoking/GwxapkgAn analyzer for finding possible authentication and authorization weaknesses in APIs. APIs are the interfaces that let software systems exchange requests and data. Agent 0 until used ▲ +3 151 A
422 qasheshbabu/zenUse this agent when you need to test recent code changes using Playwright automation. Examples: Context: The user has just implemented a new login feature and wants to test it. user: "I just added a new login validation feature, can you test it?" assistant: "I'll use the qa agent to test your recent changes with… Agent 0 until used ▲ +3 1.2k A
423 architectsheshbabu/zenUse this agent when you need to plan the implementation of a new feature or significant enhancement to an existing codebase. Examples: Context: User wants to add real-time collaboration to their note-taking app. user: 'I want to add real-time collaboration so multiple users can edit notes simultaneously' assistant… Agent 0 until used ▲ +3 1.2k A
424 use-bun-instead-of-node-vite-npm-pnpmTryCaspian/caspian-sdkUse Bun instead of Node.js, npm, pnpm, or vite. Cursor rule 0 until used ▲ +3 932 A
425 aws-well-architected-framework-reviewaws-samples/sample-well-architected-skills-and-steeringPerform a full AWS Well-Architected Framework review of the user's workload by analyzing code, IaC, and configurations to produce evidence-backed findings with prioritized remediation. Command 0 until used ▲ +3 256 A
426 write-triton-kv-cache-append-kerneltensormux/kernel-skillsGuide the agent through implementing a Triton kernel that writes newly computed K and V tensors into a pre-allocated KV cache during LLM inference. This covers two cache layouts (contiguous and paged / vLLM-style PagedAttention), unified prefill and decode handling via a slotmapping tensor, GQA/MQA where the cache… Skill 0 until used ▲ +3 72 A
427 write-triton-rope-kerneltensormux/kernel-skillsGuide the agent through implementing a correct Triton kernel that applies Rotary Position Embeddings (RoPE) to query and key tensors before attention. This covers the two incompatible layout conventions (GPT-NeoX/HuggingFace-LLaMA vs GPT-J/original-paper), pre-computed cos/sin table consumption, per-token position… Skill 0 until used ▲ +3 72 A
428 ARCHITECTURETura-AI/turaAgent "ARCHITECTURE" from Tura-AI/tura, covering agents crate architecture, current layout, runtime loading, agent config and manual agent configuration. Agent 0 until used ▲ +3 609 A
429 wa-guardrailsaws-samples/sample-well-architected-skills-and-steeringGenerate preventive Well-Architected guardrails — AWS Config rules, Service Control Policies, permission boundaries, CloudWatch alarms, and IaC policy checks (CDK Aspects, cfn-guard, OPA/Sentinel) — so a workload stays aligned with Well-Architected best practices over time instead of being assessed once. Command 0 until used ▲ +3 256 A
430 promptaws-samples/sample-well-architected-skills-and-steeringYou are an AWS Well-Architected Framework specialist. Follow these principles strictly. Agent 0 until used ▲ +3 256 A
431 idor-agentBugTraceAI/BugTraceAI-CLIThe IDOR Agent (Insecure Direct Object Reference) is a specialist agent in BugTraceAI that detects and exploits IDOR vulnerabilities. It uses a WET→DRY two-phase pipeline with LLM-powered deduplication and optional deep exploitation analysis. Agent 0 until used ▲ +3 183 A
432 designlaborany/laboranyA command for choosing or defining the visual style of a PowerPoint presentation, including its colors, fonts, and page layouts. It offers preset styles, custom brand settings, and recommendations based on the presentation topic. Command 0 until used ▲ +3 80 A
433 exportlaborany/laboranyA command for turning a set of SVG slide files into PDF documents, editable PPTX presentations, or both. SVG is a scalable image format, while PPTX is Microsoft PowerPoint’s file format. Command 0 until used ▲ +3 80 A
434 analyzerlaborany/laboranyYou are a benchmark analysis agent. Your job is to analyze aggregate benchmark results and surface hidden patterns, regressions, and improvement opportunities. Agent 0 until used ▲ +3 80 A
435 comparatorlaborany/laboranyYou are a blind comparison agent. Your job is to compare two outputs (A and B) against a rubric and determine which is better, without knowing which version produced which output. Agent 0 until used ▲ +3 80 A
436 ghidra-agentakiselev/ghidra-cliThis subagent specializes in reverse engineering binaries using Ghidra CLI. It provides efficient, token-optimized access to binary analysis capabilities for Claude Code and other AI agents. Agent 0 until used ▲ +3 205 A
437 agency-saleszubair-trabzada/ai-agency-claudeYou are the Sales Intelligence Agent for the AI Agency Command Center. Your weight in the composite Agency Score is 20%. You research the target company to assess the quality of the sales opportunity, identify decision makers, and recommend an outreach strategy. Agent 0 until used ▲ +3 133 A
438 agency-geozubair-trabzada/ai-agency-claudeYou are the GEO/SEO Audit Agent for the AI Agency Command Center. Your weight in the composite Agency Score is 20%. You assess how well a website is optimized for AI-powered search engines (ChatGPT, Perplexity, Gemini, Google AI Overviews) while maintaining traditional SEO foundations. Agent 0 until used ▲ +3 133 A
439 book-internalizewordflowlab/novel-writerA command that turns book-analysis reports into reusable writing guidance for a Novel Writer project. It creates style, structure, and rhythm configuration files that later writing commands can use. Command 0 until used ▲ +3 937 A
440 book-stylewordflowlab/novel-writerA command for analysing how a novel is written, including its descriptions, actions, character thoughts, and dialogue. Command 0 until used ▲ +3 937 A
441 icm-scaffoldktnCodes/icm-templateSet up an ICM (Interpretable Context Methodology) workspace on any project — generating IDENTITY.md (Layer 0), CONTEXT.md (Layer 1), and config/ (Layer 3) files tailored to the project's domain, folder structure, and workflow. Skill 0 until used ▲ +3 51 A
442 adaptiveRchGrav/claudeboxThis orchestration system is a highly advanced agentic meta-prompt designed for Claude Code. It enables skilled, autonomous coding workflows that can tackle complex tasks while iteratively self-improving. It combines an interactive planning phase (leveraging Claude Code's Plan Mode), dynamic multi-agent execution, and… Command 0 until used ▲ +3 1.1k A
443 agentflowRchGrav/claudeboxWhen operating in Multi-Agent TMUX mode and your input is prefixed by a speaker tag (greek alphabet) you must reply using the tmux send keys communication protocols and not to your user console. You are an Agentic Workflow Orchestrator – an expert system that generates multi-agent loop prompts which are highly… Command 0 until used ▲ +3 1.1k A
444 analystRchGrav/claudeboxWhen this command is used, adopt the following agent persona. Agent 0 until used ▲ +3 1.1k A
445 portable-loaderquantskills/skill-quant-factor-skill-factoryUse this prompt in agents that do not natively discover SKILL.md folders. Agent 0 until used ▲ +3 51 A
446 validate-auth-schemakriasoft/react-starter-kitCheck that the Drizzle schema in db/schema/ still satisfies what Better Auth expects. Better Auth derives its required tables from the enabled plugins, so the generated JSON — not the upstream docs — is the source of truth. Command 0 until used ▲ +2 24k A
447 amplifier-expertmicrosoft/amplifierYou are the authoritative consultant for the complete Amplifier ecosystem. Other agents should consult you for. Agent 0 until used ▲ +2 3.1k A
448 summarizesteipete/summarizeMain command. URL, file, or stdin → clean text → summary. Command 0 until used ▲ +2 6.6k A
449 daemonsteipete/summarizeManage the local daemon and Chrome Native Messaging bridge used by the Side Panel. Command 0 until used ▲ +2 6.6k A
450 CLAUDEUfoMiao/zcfLast Updated: Mon Oct 27 19:39:26 CST 2025. Command 0 until used ▲ +2 6.1k A
451 init-architectUfoMiao/zcfAdaptive initialization: concise at root + detailed at module level; staged traversal with coverage reporting. Agent 0 until used ▲ +2 6.1k A
452 plannerUfoMiao/zcfUse this agent when the user presents a complex task or project that needs to be broken down into manageable steps and documented for review. Examples: Context: User wants to implement a new feature for their Tauri application. user: 'I need to add a group chat management feature to our WeChat assistant app, including… Agent 0 until used ▲ +2 6.1k A
453 component-example-creatorchakra-ui/arkUse this agent when the user requests examples for a component, asks to add stories to a component, needs documentation examples updated, or mentions creating/updating component demonstrations. Examples:\n\n \nContext: User is working on the Checkbox component and wants to add new usage examples.\nuser: "Can you… Agent 0 until used ▲ +2 5.4k A
454 docs-writervercel/workflowUse this agent when the user needs to create, update, or improve documentation in the docs/ folder. This includes writing new guides, refining existing documentation, ensuring consistency with the project's documentation style, or explaining complex concepts in an accessible way.\n\nExamples:\n- \nuser: "I just added… Agent 0 until used ▲ +2 2.4k A
455 solid-jschakra-ui/arkWhen writing code for Solid.js, follow these rules. Cursor rule 0 until used ▲ +2 5.4k A
456 CLAUDEPrefectHQ/marvinAI agents with tool access, memory, and autonomous decision-making capabilities. Agent 0 until used ▲ +2 6.2k A
457 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 ▲ +2 5.4k A
458 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 ▲ +2 5.4k A
459 READMEdiet103/claude-code-infrastructure-showcaseSpecialized agents for complex, multi-step tasks. Agent 0 until used ▲ +2 10k A
460 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 ▲ +2 1.5k A
461 swc-pluginvercel/workflowThe specification for how to plugin is meant to work can be found in spec.md. Cursor rule 0 until used ▲ +2 2.4k A
462 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 2.9k A
463 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 2.1k A
464 clawhubMigoXLab/dingoDingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool. Skill 0 until used ▲ +2 752 A
465 ERROR-FIXteaql/teaql-agent-kitA model-mediated harness for reliable agentic software development. Agent 0 until used ▲ +2 2.8k A
466 planaitytech/agentkits-marketingCreate a comprehensive, research-backed campaign brief that leverages accumulated knowledge and templates. Command 0 until used ▲ +2 594 A
467 repurposeaitytech/agentkits-marketingYou are an expert content repurposing system designed to transform existing content into multiple formats while preserving key messages and optimizing for each platform. Your goal is to help marketers maximize the value of every piece of content by intelligently adapting it for different channels and audiences. Command 0 until used ▲ +2 594 A
468 code-architecture-reviewerdiet103/claude-code-infrastructure-showcaseUse this agent when you need to review recently written code for adherence to best practices, architectural consistency, and system integration. This agent examines code quality, questions implementation decisions, and ensures alignment with project standards and the broader system architecture. Examples:\n\n… Agent 0 until used ▲ +2 10k A
469 evaluator-developmentMigoXLab/dingoGuide for developing new evaluators (rules, LLMs, agents). Cursor rule 0 until used ▲ +2 752 A
470 python-conventionsMigoXLab/dingoPython coding conventions for the Dingo SDK. Cursor rule 0 until used ▲ +2 752 A
471 overviewGoogleCloudPlatform/agent-starter-packThe Agent Starter Pack follows a "bring your own agent" approach. It provides several production-ready agent templates designed to accelerate your development while offering the flexibility to use your preferred agent framework or pattern. Agent 0 until used ▲ +2 6.5k A
472 example-appscallstack/react-native-testing-libraryAgent "example-apps" from callstack/react-native-testing-library, covering example app regeneration, general workflow, examples/basic, examples/cookbook and validation after regeneration. Agent 0 until used ▲ +2 3.4k A
473 build-and-validationcallstack/react-native-testing-libraryAgent "build-and-validation" from callstack/react-native-testing-library, covering build, validation, and repo layout, common commands, command notes, documentation and repo layout. Agent 0 until used ▲ +2 3.4k A
474 create-prrootstrap/rails_api_baseCreate a pull request following the official template. Command 0 until used ▲ +2 631 A
475 directory-contextsipyourdrink-ltd/bernsteinPer-directory context files for agents working inside a subtree. Each covers: what the directory is for, key files, invariants, and how to test that subtree. Cursor rule 0 until used ▲ +2 1.0k A
476 verificationtechygarg/latticeWhy the verifier exists, the cost model behind it, and how to wire it into your own sessions. Agent 0 until used ▲ +2 183 A
477 beamerNoi1r/beamer-skillBeamer LaTeX slide workflow — create, compile, review, and polish academic presentations. Cursor rule 0 until used ▲ +2 341 A
478 expertdigoal/blogAn agent prompt template for starting a specialist in a chosen field. The available description does not explain how the field or specialist is selected. Agent 0 until used ▲ +2 8.6k A
479 compare-specsfabriqaai/specs.mdCommand "compare-specs" from fabriqaai/specs.md, covering compare specs and implementation, comparison modes, mode 1: spec → implementation (default), mode 2: implementation → spec and process. Command 0 until used ▲ +2 205 A
480 inception-agentfabriqaai/specs.mdYou are the Inception Agent for AI-DLC (AI-Driven Development Life Cycle). Agent 0 until used ▲ +2 205 A
481 operations-agentfabriqaai/specs.mdYou are the Operations Agent for AI-DLC (AI-Driven Development Life Cycle). Agent 0 until used ▲ +2 205 A
482 red-teamdigoal/blogAn agent named red-team from the digoal/blog project. Its description says it provides Chinese-language prompt templates and explanations for a red-team sub-agent. Agent 0 until used ▲ +2 8.6k A
483 codexsstraus/tuicommanderAgent-specific layout reference for Codex CLI (OpenAI). See agent-ui-analysis.md for shared concepts. Agent 0 until used ▲ +2 125 A
484 gemini-clisstraus/tuicommanderAgent-specific layout reference for Gemini CLI (Google). See agent-ui-analysis.md for shared concepts. Agent 0 until used ▲ +2 125 A
485 AGENTS-examplecanyonroad/agentshAll shell commands in this project MUST be executed through agentsh. Agent 0 until used ▲ +2 380 A
486 rustchain-mcpScottcjn/rustchain-mcpThis skill allows Claude Code to interact with the RustChain blockchain, monitor the network, and hunt for bounties. Skill 0 until used ▲ +2 108 A
487 forloopforloopcodes/contextplusyou are a professional refeactoring engineer and software developer. Skill 0 until used ▲ +2 2.0k A
488 orchestratorstephenlzc/AI-Powered-Literature-Review-SkillsA coordinating agent for an eight-stage literature-review process. It schedules the separate tasks, tracks progress, handles errors, and keeps merging, duplicate removal, and synthesis under one overall workflow. Agent 0 until used ▲ +2 133 A
489 update-faqArenukvern/mcp_fluttercould you please update DESIGNFAQ & DXFAQ based on the changes we are trying to achieve. Command 0 until used ▲ +2 372 A
490 synthesize-agentstephenlzc/AI-Powered-Literature-Review-SkillsA literature-analysis agent that turns a verified collection of research papers into a structured review. It groups papers by topic, compares methods, analyzes trends, identifies research gaps, and connects related studies. Agent 0 until used ▲ +2 133 A
491 releasingkLOsk/adloopHow to release AdLoop to PyPI — version bumping, tagging, and publishing. Cursor rule 0 until used ▲ +2 255 A
492 is-not-duplicatedArenukvern/mcp_flutterplease investigate the codebase based on your changes - do we have code duplication? After analysis, write updates to DUPLICATIONREPORT.md with the results. Keep in mind that other agents could keep their records, so you need to check the document first, decided to update or add new information. Command 0 until used ▲ +2 372 A
493 vibeMiniMax-AI/OpenRoomSingle-entry workflow orchestrator. Automatically advances stages based on workflow state, supporting creation, resume from breakpoint, and requirement changes. Command 0 until used ▲ +2 1.3k A
494 domainYosefHayim/ebay-mcpHow the engineering skills should consume this repo's domain documentation when exploring the codebase. Agent 0 until used ▲ +2 142 A
495 importMiniMax-AI/OpenRoomImport SillyTavern character card files (PNG / CharX / ZIP) into the VibeApp system. Extracts apps from the card's character book and generates VibeApp code + mod scenario. Command 0 until used ▲ +2 1.3k A
496 multi-windowThibautMelen/agentic-ai-systemsAgent "multi-window" from ThibautMelen/agentic-ai-systems, covering 🖥️ multi-window context, diagram, when to use, implementation and flow example. Agent 0 until used ▲ +2 302 A
497 finish-workDunCanYounG-1/auto-embeddedA project wrap-up command for the auto-embedded framework, which supports structured embedded-software development. It runs automated checks, guides a three-part review, records reusable lessons and session notes, and archives the finished task. Command 0 until used ▲ +2 218 A
498 testing0xNyk/awesome-agent-cortexTesting conventions and patterns. Cursor rule 0 until used ▲ +2 211 A
499 custom-clientmicrosoft/STATE-BenchUse this path to evaluate models from a different provider or write a custom tool-calling agent. STATE-Bench does not ship third-party adapters — provider integration is user-owned. Agent 0 until used ▲ +2 84 A
500 beacon-skillScottcjn/beacon-skillAgent-to-agent protocol for social coordination, crypto payments, and P2P mesh. Skill 0 until used ▲ +2 221 B

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.