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
801 startLonelyHerbivore/Trellis-HerbivoreInitialize a Trellis-managed development session. If startup context was not injected automatically, manually load the equivalent compact context by following these steps. Command 0 until used ▲ +1 95 A
802 position-optimizerDaviddTech/ai-trading-agentYou are a top 0.1% quantitative position-sizing and risk-optimization agent. Skill 0 until used ▲ +1 53 A
803 business-flow-reviewercis2042/product-design-harnessProtect sustainable value: value exchange, ownership cost, priority, distribution, retention, defensibility, and trust. Agent 0 until used ▲ +1 16 A
804 council-facilitatorcis2042/product-design-harnessTurn verified disagreement into one product decision. Do not vote and do not average. Agent 0 until used ▲ +1 16 A
805 alt-pathJHostalek/dotclaudeOne lens: what fundamentally different approaches did we never consider? The biggest wins come from switching approach, not optimizing the chosen one — so you check whether the choice itself was well-informed, not whether the implementation is good. Agent 0 until used ▲ +1 11 A
806 pragmatistJHostalek/dotclaudeOne lens: is this the most direct path from problem to solution? Agent 0 until used ▲ +1 11 A
807 avvarrePralhadYadawad/avvarreWhen working on any source file, follow Google Style Guide conventions for that language. Cursor rule 0 until used ▲ +1 4 A
808 3-prdvercel-labs/design-systems-to-agent-skillsRun Stage 3 of the design system skill generation pipeline: closed PRD generation. Command 0 until used ▲ +1 36 A
809 4-generatevercel-labs/design-systems-to-agent-skillsRun Stage 4 of the design system skill generation pipeline: parallel skill file generation. Command 0 until used ▲ +1 36 A
810 multica-mcpKorkyzer/multica-mcpThis guide documents patterns and best practices for orchestrating Multica through the MCP server, from an LLM chat (Claude Desktop, Codex Desktop, Claude Code, or any MCP-capable client). Skill 0 until used ▲ +1 24 B
811 READMEEnovatr-Labs/SpecRouteThis directory contains the 12 Claude Code agents that implement the SpecRoute skeleton. They are project-internal - they build SpecRoute itself, not consumer-facing templates that ship as artifacts. Agent 0 until used ▲ +1 3 A
812 warpbobvibes/ClavixClavix helps Warp developers turn rough ideas into quality, AI-ready prompts and Product Requirements Documents without leaving the terminal. Agent 0 until used ▲ +1 673 A
813 prd-writeraakashg/pm-claude-code-setupActivate on "write a PRD", "create a PRD", "draft a PRD", "PRD for [feature]", "spec out [feature]", or "one pager for [feature]". Skill 0 until used ▲ +1 152 A
814 architectured3mocide/Sovereign_WatchSkill "architecture" from d3mocide/Sovereign_Watch, covering architecture - sovereign watch and core architectural rules. Skill 0 until used ▲ +1 92 A
815 codex-execalirezarezvani/claude-code-skill-factoryEasy wrapper for running Codex CLI commands from Claude Code with proper syntax. Command 0 until used ▲ +1 855 A
816 data-security-and-compliance-auditorvaquarkhan/data-engineering-agent-skillsUse this persona when reviewing regulated-data handling, compliance controls, governance evidence, and release readiness for PII, PCI, HIPAA, PHI, or similarly sensitive data paths. Agent 0 until used ▲ +1 40 A
817 READMEalirezarezvani/claude-code-skill-factoryInteractive guide system for building custom Skills, Prompts, and Agents using the Claude Code Skills Factory. Agent 0 until used ▲ +1 855 A
818 devlensdevlensio/devlensOSSUnderstand a codebase with the DevLens MCP — TypeScript, JavaScript, Python, Go, Rust, or Java (incl. React/Next.js/Node, FastAPI/Flask/Django, Spring Boot, Gin/Echo/chi/net-http, axum/actix/rocket). Query a precomputed graph of nodes (components, hooks, functions, classes, methods, structs, traits, routes) and typed… Skill 0 until used ▲ +1 55 A
819 architecturedevlensio/devlensOSSProduce a thorough architecture document grounded in the graph — the kind of brief a raw LLM can't write because it's built from the codebase's real clusters, real edges, and precomputed business summaries. Arguments: none (cwd graph; pass a graphId to target another). Needs summaries for the richest output — follow… Command 0 until used ▲ +1 55 A
820 analytics-engineer-reviewervaquarkhan/data-engineering-agent-skillsUse this persona when reviewing marts, metrics, semantic definitions, and dbt model quality. Agent 0 until used ▲ +1 40 A
821 hegelionHmbown/HegelionCommand "hegelion" from Hmbown/Hegelion, covering /hegelion, routing and autocoding loop. Command 0 until used ▲ +1 172 A
822 repository-mapdistsystem/codex-desktop-linuxThis map keeps the detailed file ownership notes out of AGENTS.md while preserving the source-of-truth routing agents need before editing. Agent 0 until used ▲ +1 12 A
823 diagramdevlensio/devlensOSSRender the graph visually. Argument: [architecture|cluster|flow|deps] (default architecture). For cluster/flow, an optional second arg is a seed node id/name. Command 0 until used ▲ +1 55 A
824 acme-uivercel-labs/design-systems-to-agent-skillsPackage: @acme/ui v1.0.0 Framework: React 18 + Next.js 14 (App Router). Skill 0 until used ▲ +1 36 A
825 user-researchaakashg/pm-claude-code-setupActivate on "synthesize research", "analyze interviews", "research findings", "interview synthesis". Skill 0 until used ▲ +1 152 A
826 claim-evidence-auditorHaohaha-11/Paper-WritingCheck whether the paper's claims are backed by evidence. This skill protects the manuscript from overclaiming, hallucinated citations, unsupported novelty, and reviewer objections that the paper does not prove what it promises. Skill 0 until used ▲ +1 3 A
827 paper-strategistHaohaha-11/Paper-WritingTurn a research idea, draft, or result bundle into a defensible paper plan before drafting begins. This skill is the first gate for paper quality: it decides what the paper is really claiming, what evidence is needed, and what reviewers are likely to attack. Skill 0 until used ▲ +1 3 A
828 art-directiontimkoda/koda-stackYou are an art director for visual content. Your job is to define the complete visual language of a piece — palette, mood, lighting, composition, and references. Skill 0 until used ▲ +1 110 A
829 generatetimkoda/koda-stackYou are a visual producer. Your job is to generate AI images and videos from a shot deck, using the right models, prompts, and settings for each shot. Skill 0 until used ▲ +1 110 A
830 backfillvaquarkhan/data-engineering-agent-skillsUse replay-safe workflows before rerunning, replaying, or cutting over data. Command 0 until used ▲ +1 40 A
831 source-analysis-agentCDSecurity/cdsecurity-skillsYou have: projectdir, in-scope file list, and Grep + Read tools. Agent 0 until used ▲ +1 51 A
832 reviewvaquarkhan/data-engineering-agent-skillsReview the change using the relevant checklist references and one or more personas from agents/. Command 0 until used ▲ +1 40 A
833 code-deduplicatorKochava-Studios/witsyUse this agent when you need to identify and eliminate code duplication through systematic refactoring. Examples: Context: User has written several similar functions with repeated logic patterns. user: 'I've been copying and pasting this validation logic across multiple files. Can you help clean this up?' assistant… Agent 0 until used ▲ +1 2.0k A
834 infrastructure-agentCDSecurity/cdsecurity-skillsYou have: framework, projectdir, and Bash/Read/Glob/Grep tools. Do NOT read source .sol files. Check project infrastructure only. Agent 0 until used ▲ +1 51 A
835 migration-behaviorCodeForUsers/odoo-dev-superskillDefine how the agent should behave when migrating an Odoo module between versions, especially across 16.0, 17.0, 18.0 and 19.0. Agent 0 until used ▲ +1 12 A
836 review-behaviorCodeForUsers/odoo-dev-superskillDefine how the agent should behave when reviewing an existing Odoo module for quality, maintainability, structure, OCA alignment, and production readiness. Agent 0 until used ▲ +1 12 A
837 plugin-submission-reviewerJ-Pster/Psters_AI_WorkflowRun a final submission-quality review before commit/release for psters-ai-workflow. Agent 0 until used ▲ +1 290 A
838 plugin-release-managerJ-Pster/Psters_AI_WorkflowOrchestrate release flow for this repository with strict quality gates. Agent 0 until used ▲ +1 290 A
839 testKochava-Studios/witsyMake sure you have added or updated tests for any new functionality or bug fixes in the codebase. Command 0 until used ▲ +1 2.0k A
840 CONVENTIONSlegioncodeinc/honeycombThe unified honeycomb command surface lives under src/commands/. src/cli/index.ts is the ENTRY POINT (global-flag parse → route); src/commands/ are the HANDLERS. Wave 1 (this scaffold) ships contracts + seams + honest stubs; Wave 2 fills the handler bodies and rewires src/cli/index.ts onto createDispatcher(). Command 0 until used ▲ +1 110 A
841 example_yao_mathAdeleZhu/teacher-skillA generated AI teacher profile for teaching middle-school mathematics, especially algebra and geometry. It describes the teacher’s teaching routines, explanations, exercises, grading style, and personality rules. Skill 0 until used ▲ +1 105 A
842 example_zhou_englishAdeleZhu/teacher-skillA teaching guide for an AI English teacher working mainly with middle-school reading, grammar, and writing. Skill 0 until used ▲ +1 105 A
843 md-to-wiki-docs-skillsabertanha/md-to-wiki-docs-skillsTurn markdown specification files into documentation sites. Skill 0 until used ▲ +1 4 A
844 dodKochava-Studios/witsyBefore considering a task complete, verify ALL items below pass. This is a quality gate - do not skip any step. Command 0 until used ▲ +1 2.0k A
845 create-releaseyuya373/claude-code-emacsThis package provides seamless integration with Claude Code, allowing you to run AI-powered coding sessions directly in your Emacs environment. Command 0 until used ▲ +1 67 A
846 setupfredrikaverpil/claudelineInstall and configure the claudeline plugin as your Claude Code statusline. Command 0 until used ▲ +1 55 B
847 format-pdfabertanha/md-to-wiki-docs-skillsYou are a specialized subagent for generating PDF documents from markdown spec files using Pandoc. Agent 0 until used ▲ +1 4 A
848 tto-autokittimasak/thai-token-optimizer============================================================================ Thai Token Optimizer v2.0 ============================================================================ Description : A Thai token optimization tool for AI coding agents that keeps commands, code, and technical details accurate. Command 0 until used ▲ +1 47 C
849 tto-benchmarkkittimasak/thai-token-optimizer============================================================================ Thai Token Optimizer v2.0 ============================================================================ Description : A Thai token optimization tool for AI coding agents that keeps commands, code, and technical details accurate. Command 0 until used ▲ +1 47 C
850 format-github-wikiabertanha/md-to-wiki-docs-skillsYou are a specialized subagent for publishing markdown spec files as a GitHub Wiki. Agent 0 until used ▲ +1 4 A
851 typescript-stylebobbylkchao/ai-phone-agentTypeScript style — prefer arrow functions and consistent callbacks. Cursor rule 0 until used ▲ +1 110 A
852 teamktnyt/cclspI am Nano, the product owner. Command 0 until used ▲ +1 673 A
853 architectureJTCHE/houdini-mcpThree layers. Each runs in a different process. Agent 0 until used ▲ +1 2 A
854 codeJTCHE/houdini-mcpEach value, shape, and rule lives in one place. Ports, paths, defaults, and patterns get one definition that every caller imports. A value written twice will drift. Agent 0 until used ▲ +1 2 A
855 create-versionqiniu/skillsA command for creating a new version of a Qiniu AppMarket application. It collects version details and deployment settings, including a Terraform module, which is reusable infrastructure configuration. Command 0 until used ▲ +1 10 A
856 create-appqiniu/skillsA guided command for creating an AppMarket cloud application. It first helps choose how the application runs, how its software image is prepared, how it is accessed, and what deployment settings it needs. Command 0 until used ▲ +1 10 A
857 tailtest-huntavansaber/tailtestRun an adversarial pass on $ARGUMENTS -- explicitly try to break the source code. Command 0 until used ▲ +1 11 A
858 sync-tutorialsgvkhosla/compound-engineering-piCommit and push your tutorials to the GitHub repository for backup and mobile reading. Command 0 until used ▲ +1 51 A
859 plans0oooooooo0/skilllessAnalyze project context, recommend relevant tools, then enter planning mode. Command 0 until used ▲ +1 38 A
860 auto-discovery0oooooooo0/skilllessAutomatically recommend relevant capabilities when the user works with specific frameworks or tools. Skill 0 until used ▲ +1 38 A
861 skill-installer0oooooooo0/skilllessInstall Claude Code skills from various sources. Skill 0 until used ▲ +1 38 A
862 tailtestavansaber/tailtestGenerate or update tests for $ARGUMENTS. Command 0 until used ▲ +1 11 A
863 portfoliovisusnet/coinbase-mcp-serverDisplay a compact portfolio status report with minimal token overhead. Command 0 until used ▲ +1 6 A
864 secure-dev-c-sharpmatank001/cursor-security-rulesThese rules apply to all C#/.NET code in the repository and aim to prevent common security risks through disciplined use of input validation and deserialization, output encoding, and safe APIs. Cursor rule 0 until used ▲ +1 378 A
865 review-economics-paperviplee110/economics-paper-reviewerReview the current English economics paper using the economics-paper-reviewer protocol. Command 0 until used ▲ +1 6 A
866 gitczhimaAi/ChatClawA command that stages safe Git changes, writes a commit message matching the repository’s conventions, and creates a commit. Command 0 until used ▲ +1 307 A
867 lhvstefanoamorelli/estonia-ai-kitInteract with LHV Bank through the lhv CLI — check balances, view transactions, switch accounts, and make SEPA payments. Skill 0 until used ▲ +1 79 A
868 CONTEXTmoabualruz/fulcrumMaskedProfileRow: A UI-safe projection of an AgentProfileRow where each authEnv value is replaced with a fixed-width mask, plus derived capabilities and sessionscount. Avoid: Sanitized profile, redacted profile, view-model. Agent 0 until used ▲ +1 3 A
869 ai-content-analyticsomer-metin/skills-for-antigravityWorld-class expertise in measuring, attributing, and optimizing AI-generated content performance. Combining data science rigor with content strategy intelligence to answer the questions traditional content analytics can't: Is AI content performing? Which AI variations convert? What's the true ROI of AI vs traditional… Skill 0 until used ▲ +1 140 A
870 market_analystpamirtuna/gamestudio-subagentsYou are the Market Analyst Agent for game development projects. You provide critical market insights, competitor analysis, and data-driven recommendations to ensure project viability and success. Agent 0 until used ▲ +1 247 A
871 producer_agentpamirtuna/gamestudio-subagentsYou are the Producer Agent for game development projects. You work under the Master Orchestrator to manage project execution, validate deliverables, and ensure successful game development. Agent 0 until used ▲ +1 247 A
872 emtastefanoamorelli/estonia-ai-kitInteract with the Estonian Tax and Customs Board (EMTA) through the emta tool. Authenticate via Smart-ID QR code, list and view TSD (Income and Social Tax Return) declarations. Skill 0 until used ▲ +1 79 A
873 worktree-policymoabualruz/fulcrumEvery PRD-driven adoption slice runs in its own git worktree. The policy keeps generated work isolated, makes failed verification inspectable, and keeps dev/v1.0 as the only merge target. Agent 0 until used ▲ +1 3 A
874 self-testzhimaAi/ChatClawA command that compares the current branch with the main branch and reports which functionality should be tested before merging. Command 0 until used ▲ +1 307 A
875 tradevisusnet/coinbase-mcp-serverStart the autonomous trading agent with the coinbase-trading skill. Command 0 until used ▲ +1 6 A
876 gedd-chataws-samples/sample-GEDDYou are a GEDD coaching assistant. You guide the user through building a golden evaluation dataset for their AI agent using Open Coding methodology, then help them evaluate and annotate responses — all without leaving Claude Code. Command 0 until used ▲ +1 12 A
877 geddaws-samples/sample-GEDDYou are a GEDD coaching agent. You guide a Domain Expert through building a golden evaluation dataset, deploy the agent, then hand off to an ML Engineer who wires it into a SageMaker MLflow production pipeline. Command 0 until used ▲ +1 12 A
878 pr-assessivangrynenko/cursorrulesCommand "pr-assess" from ivangrynenko/cursorrules, covering custom command: pr assess, command usage, code review agent instructions, primary objectives and input data analysis. Command 0 until used ▲ +1 88 A
879 setup-cascading-contexteficode/modern-ai-developer-stackThis skill audits a project's existing context files, validates consistency across cascading context layers, and generates missing context files based on the cascading context methodology. Skill 0 until used ▲ +1 12 A
880 behat-drevopsivangrynenko/cursorrulesCommand "behat-drevops" from ivangrynenko/cursorrules, covering custom command: behat drevops, command usage, role definition, drevops behat steps integration and available behat traits from drevops. Command 0 until used ▲ +1 88 A
881 example-update-readme-taxonomyeficode/modern-ai-developer-stackHelp an AI agent safely update the taxonomy and tool listings in README.md while preserving structure, style, and consistency with this repository's goals. Skill 0 until used ▲ +1 12 A
882 mcpkernel-securitypiyushptiwari1/mcpkernelMCPKernel security rules for AI agent tool calls. Use when working with MCP tool servers, AI agents, or any code that makes autonomous tool calls. Cursor rule 0 until used ▲ +1 2 A
883 portable-loaderquantskills/skill-futures-deepview-analystUse this prompt in agents that do not natively discover SKILL.md folders. Agent 0 until used ▲ +1 21 A
884 new-sessionJustinPerea/midjourney-cc-skillStart a new prompt engineering session with full knowledge application. Command 0 until used ▲ +1 11 A
885 agency-welcomethe-agency-ai/the-agency-starterYou are the captain, and you're running the welcome/onboarding flow. Command 0 until used ▲ +1 20 A
886 reflectJustinPerea/midjourney-cc-skillAnalyze iteration logs and extract/update patterns in the knowledge base. Command 0 until used ▲ +1 11 A
887 agency-requestthe-agency-ai/the-agency-starterThe user typed: /agency-request $ARGUMENTS. Command 0 until used ▲ +1 20 A
888 thai-token-optimizerkittimasak/thai-token-optimizer============================================================================ Thai Token Optimizer v2.0 ============================================================================ Description : Claude Code skill guidance for Thai Token Optimizer v2.0. Skill 0 until used ▲ +1 47 D
889 reviewdelphicleancode/delphi-spec-kitproject:review. Command 0 until used ▲ +1 50 A
890 edit_draftMigueDuque/capcut-mcp-server-extendedEdita un proyecto CapCut existente agregando subtítulos al PROYECTO ORIGINAL. Command 0 until used ▲ +1 5 A
891 ros-roboticswzyn20051216/ros-robotics-skillA command for handling requests as a senior ROS robotics engineer. ROS is a software framework used to connect robot sensors, controllers, processes, and tools. Command 0 until used ▲ +1 58 A
892 create_fontsMigueDuque/capcut-mcp-server-extendedAgrega texto animado al draft de CapCut activo usando los presets de tipografía y animación definidos en el proyecto. Command 0 until used ▲ +1 5 A
893 competitive-analysis.testMrJoeSack/pm-prompts/competitive-analysis Context: Well-funded startup launched competing product Competitor: $20M Series A, strong team, similar target market Timeline: Need threat assessment and response plan within 2 weeks Goal: Determine strategic response and resource allocation. Command 0 until used ▲ +1 6 A
894 context-primecacr92/WeReplyA command that loads project context, including the project structure, technology stack, modules, and development rules. It is described for a specific feed-formula optimization desktop application. Command 0 until used ▲ +1 6 A
895 optimizecacr92/WeReplyA command for reviewing application performance across a Rust backend, React frontend, and SQLite database. It uses profiling, benchmarking, query-plan checks, and a list of common bottlenecks. Command 0 until used ▲ +1 6 A
896 discover0oooooooo0/skilllessSearch for and install specialized tools and capabilities from all available sources. Command 0 until used ▲ +1 38 B
897 directorLinHao-city/StoryMindTurn 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 ▲ +1 6 A
898 builderLinHao-city/StoryMindTurn 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 ▲ +1 6 A
899 commitcharliezstong/nutri-mcpCuando el usuario pida hacer commit, sigue estas reglas. Command 0 until used ▲ +1 6 A
900 create-api-clientFarzannajipour/cursor-react-rulesSet up a centralized API client with error handling, interceptors, and TypeScript types. Command 0 until used ▲ +1 3 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.