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
701 reviewshotgun-sh/shotgunReview the current pull request to look for things like: Inline imports = We must remove these unless they are truly needed. dicts being returned by services/routers that should be Pydantic Models. Pydantic Model classes should be moved to a models.py file in the appropriate folder. Any leftover TODOs = We need to… Command 0 until used ▲ +1 681 A
702 reviewlkimuk/WuweReview the supplied artifact for correctness, security, maintainability, and test coverage. Report concrete findings before general suggestions, and distinguish verified defects from risks. Skill 0 until used ▲ +1 77 A
703 new-odoo-project19prince/claude-odoo-builderTRIGGER: User invokes /new-odoo-project to scaffold a new Odoo website builder project. Skill 0 until used ▲ +1 45 A
704 AGENTScrypto-com/cdcx-cliThis guide provides comprehensive integration documentation for AI agents using the cdcx CLI and MCP server. Agent 0 until used ▲ +1 25 A
705 ignore-sourcekit-warningsmattt/iMCPdescription: Ignore spurious SourceKit warnings globs: .swift alwaysApply: false. Cursor rule 0 until used ▲ +1 1.5k A
706 super-dev-seeaishangyankeji/super-devA command that starts a shortened Super Dev workflow for fast projects such as a showcase website, small game, or single-purpose demo. Command 0 until used ▲ +1 274 A
707 CLAUDEvobase/vobaseAI agents that handle customer conversations autonomously. Powered by Mastra, using a workspace-based architecture where agents interact through a virtual filesystem and CLI commands. Agent 0 until used ▲ +1 60 A
708 sap-table-dumpkts982/mcp-sap-guiRead ALL rows from the table on the current SAP screen, handling pagination for both ALV grids and TableControls. Command 0 until used ▲ +1 26 A
709 subagentsthuandiep1707/codex-harness-javascriptLifecycle planning/resume/pause is separate from execution intent. Planning mode does not imply plan-only. Agent 0 until used ▲ +1 7 A
710 next-stageshotgun-sh/shotgunCreate a branch. I am going to take a shower for the next 90 minutes and I need the next stage to be finished before I come back. All of the research, contracts, specification, plan, and tasks in .shotgun/ this directory is just specifications and example code. Second Explore the codebase to come up with a detailed… Command 0 until used ▲ +1 681 A
711 super-devshangyankeji/super-devActivate the Super Dev pipeline for research-first, commercial-grade project delivery. Use when user says /super-dev or super-dev: followed by a requirement. Agent 0 until used ▲ +1 274 A
712 publishcdknorow/coralPublish a new release of Coral to PyPI. The user provides the version number as $ARGUMENTS (e.g. "2.2.0"). Command 0 until used ▲ +1 32 A
713 sap-explorekts982/mcp-sap-guiExplore the current SAP screen and report what you find. Command 0 until used ▲ +1 26 A
714 commitAFK-surf/OpenBridgeUsing git to commit current changes with the Commit Rule following the these steps, and as fast as possible without any explanations. Command 0 until used ▲ +1 424 A
715 custom-toolsalgopian/chromeclawCustom agent tools — register JavaScript workspace files as per-agent callable tools with @tool metadata. Agent 0 until used ▲ +1 196 B
716 gpt-tasteskillaaronnat23/disp8chUse this skill for premium frontend interfaces that require GSAP scroll animations, mathematically verified bento grids, and award-quality design. The most demanding taste variant. Skill 0 until used ▲ +1 98 A
717 domainYosefHayim/launch-storeHow the engineering skills should consume this repo's domain documentation when exploring the codebase. launch-store is single-context: one CONTEXT.md + docs/adr/ at the repo root. Agent 0 until used ▲ +1 9 A
718 FLEETFerousco-dev/ilanaThirteen agents. Each has a charter, inputs, outputs, refusals and a handoff contract. Agent 0 until used ▲ +1 8 A
719 progressthuandiep1707/codex-harness-javascript$frontend-delivery NEW/REPLAN -> Brain analysis + stack discovery -> close Brain -> one Orchestrator child (intent=deliver) -> controller-action loop -> jira-call -> Primary Controller -> confirmed result -> same Orchestrator -> dispatch-specialist -> Primary Controller -> specialist -> cleanup/close -> result -> same… Agent 0 until used ▲ +1 7 A
720 outlinezach-blumenfeld/knowledge-indexThe default output of ki outline is a table-of-contents-style render of the vault's containment hierarchy plus its cross-references. It is intended to be readable by both humans and agents: the eye scans display names on the left, and an agent can pick out URIs from a stable right-most column. Command 0 until used ▲ +1 6 A
721 clean-code-reviewunrealandychan/clean-code-skillClean Code + DDD review — activate when reviewing or auditing source code. Cursor rule 0 until used ▲ +1 6 A
722 agent_classDataBassGit/AgentForgeThe Agent class is the core orchestrator in AgentForge. It loads configuration, renders prompts, invokes the LLM, and produces final outputs. Agents can be subclassed for custom logic. Agent 0 until used ▲ +1 845 A
723 custom_agentsDataBassGit/AgentForgeThis is an advanced extension reference. Agent 0 until used ▲ +1 845 A
724 crypto-arbitrage-bot-automated-tradingCortex-AI-Network/crypto-arbitrage-bot-automated-tradingTo orchestrate and deploy this execution skill dynamically via Autonomous AI Agent frameworks (LangChain, AutoGen, CrewAI), point your agent environment definition to the repository root and establish runtime parameters. Skill 0 until used ▲ +1 66 A
725 odoo-theme-fix19prince/claude-odoo-builderTRIGGER: User shares a screenshot of an Odoo page and asks for visual fixes, theming improvements, or readability changes. Skill 0 until used ▲ +1 45 A
726 searchzach-blumenfeld/knowledge-indexCommand "search" from zach-blumenfeld/knowledge-index, covering how ki search works, 1. the index, 2. one unified sweep (documents + sections), 3. query syntax (lucene) and 4. semantic expansion (the lexical gap). Command 0 until used ▲ +1 6 A
727 moto-impl-strategyrobotocore/robotocoreStrategy and learnings for implementing missing Moto operations. Cursor rule 0 until used ▲ +1 330 C
728 coding-interviewerkirilxd/swe-interview-coachLoaded by /mock-coding and /practice-coding; the main session reads this file and embodies it for the interview portion of the conversation. Not a spawnable subagent. Agent 0 until used ▲ +1 79 A
729 commitparalleldrive/aiddAct as a senior software engineer to commit changes to the repository in non-interactive modes ONLY, using the following template. Command 0 until used ▲ +1 380 A
730 supertag-clijcfischer/supertag-cliSkill "supertag-cli" from jcfischer/supertag-cli, covering supertag cli skill, mcp tools reference, progressive disclosure (start here), tanacapabilities and tanatoolschema. Skill 0 until used ▲ +1 49 A
731 sdrf-skillsbigbio/sdrf-skillsStructured skills for expert-level SDRF (Sample and Data Relationship Format) annotation in proteomics. Cursor rule 0 until used ▲ +1 16 A
732 task-summaryunrealandychan/clean-code-skillTask summarizer & skill extractor — activate after completing any AI-assisted task. Cursor rule 0 until used ▲ +1 6 A
733 designerAgentSkillOS/SkillAnythingYou are the Skill Architecture Designer agent. You read analysis.json from Phase 1 and produce architecture.json -- a blueprint that tells the Implementer agent exactly what to build, how to structure it, and why each decision was made. Agent 0 until used ▲ +1 468 A
734 implementerAgentSkillOS/SkillAnythingYou are the Skill Implementer agent. You receive architecture.json from the Designer and write the actual skill files -- SKILL.md, reference docs, scripts, and examples. Your output is a complete, ready-to-install skill package. Agent 0 until used ▲ +1 468 A
735 create-arc-gametheredbluepill/arc-interactiveThis skill guides the creation of ARC-AGI-3 games based on established patterns from environmentfiles/. Skill 0 until used ▲ +1 54 A
736 orchestratorOmar-Obando/qwen-orchestratorYou are the Commander of the Qwen Orchestrator. Command 0 until used ▲ +1 47 A
737 math-formalizengtiendong/Academic-Research-Agent-SkillAct as the Strategist for mathematical formalization. Command 0 until used ▲ +1 42 A
738 notificationadvenimus/conduit-desktopUse the unified toast notification system for all user-facing notifications in Conduit. Command 0 until used ▲ +1 10 A
739 eval-skillEvol-ai/SkillCompass🚀 Enhanced with Local Validators: This command now uses local JavaScript validators for D1, D2, and D3 dimensions to significantly reduce token consumption while maintaining evaluation quality. Complex reasoning tasks (D4, D5, D6) continue to use LLM evaluation with local pre-analysis. Command 0 until used ▲ +1 215 A
740 play-arc-gametheredbluepill/arc-interactiveSkill for playing and testing ARC-AGI-3 games using rungame.py. Skill 0 until used ▲ +1 54 A
741 skill-inboxEvol-ai/SkillCompassUnified entry point for managing skill suggestions and browsing all installed skills. Provides two views: suggestions (default) and all skills. Command 0 until used ▲ +1 215 A
742 gradergokeshenzhen/gen-tb-skillYou are the quality grader for a gen-tb eval run. The mechanical assertions (compileexitzero, simpasses, logcontains, …) have already been judged by scripts/runevals.py and saved to assertionsresult.json. Do not re-judge them. Your job is to evaluate dimensions those assertions can't catch. Agent 0 until used ▲ +1 23 A
743 restartlukaszraczylo/claude-mnemonicRestart the claude-mnemonic worker process. Use this command when experiencing issues with the memory system. Command 0 until used ▲ +1 19 A
744 obsidian-vault-workflowaka-kika/kika-obsidian-mcpUse this skill when a user asks an agent to inspect, organize, summarize, or update an Obsidian vault through this MCP server. Skill 0 until used ▲ +1 13 A
745 devadvenimus/conduit-desktopYou are continuing development on Conduit, an AI-powered remote connection manager. Follow this workflow precisely. Command 0 until used ▲ +1 10 A
746 testing-framework-architectpgEdge/pgedge-postgres-mcpUse this agent when you need expert guidance on testing strategies, test implementation, or test improvements for the pgEdge Postgres MCP Server project. Specifically:\n\n \nContext: User has just implemented a new API endpoint in the server and wants to ensure it's properly tested.\nUser: "I've added a new endpoint… Agent 0 until used ▲ +1 221 A
747 analyzergokeshenzhen/gen-tb-skillYou run after the blind Comparator has picked a winner. Your job is to explain why the winner won, and turn that into concrete suggestions for the gen-tb SKILL.md and references/. Agent 0 until used ▲ +1 23 A
748 yaml-configinboxpraveen/Minimize-Cursor-CostRules for YAML / config / infra files (Docker, K8s, Terraform, GitHub Actions, etc.). Cursor rule 0 until used ▲ +1 7 A
749 Qopenwebf/webfMCP-first cross-validated code intelligence across dependency graphs. Command 0 until used ▲ +1 2.5k A
750 code-reviewerpgEdge/pgedge-postgres-mcpUse this agent for general code quality review, catching bugs, identifying anti-patterns, and ensuring code follows best practices. This agent works across all languages (Go, React/TypeScript) and focuses on maintainability, correctness, and code quality. Examples:\n\n \nContext: Developer has written new… Agent 0 until used ▲ +1 221 A
751 save-memory0xK3vin/MegaMemoryYou are saving what you learned this session into the megamemory knowledge graph. This is YOUR memory — record anything valuable for future sessions: what you understood about the project, what you built, decisions that were made, patterns you noticed, or intent the user shared. Command 0 until used ▲ +1 513 A
752 viral-analyzecharlesdove977/goviralbroYou are the Analytics Collection Engine for the Viral Command system. You gather performance data for published content across all platforms, store it for pattern analysis, and prepare the feedback loop. Command 0 until used ▲ +1 263 A
753 viral-scriptcharlesdove977/goviralbroYou are running the Viral Command script engine. Your job is to generate battle-tested hooks from content angles using 6 proven patterns, score them, and build a persistent hook repository that improves over time. When run without arguments, you interactively guide the user through format selection… Command 0 until used ▲ +1 263 A
754 deployOmar-Obando/qwen-orchestratorDeploy the following target to the specified environment. Command 0 until used ▲ +1 47 A
755 prp-executorwebdevtodayjason/context-forgeYou execute a single Product Requirement Prompt (PRP), walking its validation gates one at a time, in order, marking each gate ✓ or ✗ directly in the PRP file. You stop at the first failed gate and surface a remediation plan. Agent 0 until used ▲ +1 149 A
756 security-auditorwebdevtodayjason/context-forgeYou scan {{#if projectName}}{{projectName}}{{else}}the project{{/if}} for security issues across three axes: application code (OWASP Top 10), dependencies (CVEs), and credential leaks. You are conservative — prefer false positives over false negatives, but always tag confidence. Agent 0 until used ▲ +1 149 A
757 reflectopenwebf/webfYou are an expert in prompt engineering, specializing in optimizing AI code assistant instructions. Your task is to analyze and improve the instructions for Claude Code found in u/CLAUDE.md. Follow these steps carefully. Command 0 until used ▲ +1 2.5k A
758 bootstrap-memory0xK3vin/MegaMemoryRUN { git ls-files; git ls-files --others --exclude-standard; } 2>/dev/null | sort -u | xargs wc -l 2>/dev/null | sort -rn | head -150 READ README.md. Command 0 until used ▲ +1 513 A
759 agentsbobvibes/ClavixThis guide is for agents that can only read documentation (no slash-command support). If your platform supports custom slash commands, use those instead. Agent 0 until used ▲ +1 673 A
760 READMEconectlens/lenserfightAgent "README" from conectlens/lenserfight, covering core product decisions, team structure, recommended delivery order and strategic note. Agent 0 until used ▲ +1 19 A
761 analyzerzacharyfmarion/openscad-studioAnalyze blind comparison results to understand WHY the winner won and generate improvement suggestions. Agent 0 until used ▲ +1 225 A
762 graderzacharyfmarion/openscad-studioEvaluate expectations against an execution transcript and outputs. Agent 0 until used ▲ +1 225 A
763 codexvincentmumme/personalos-boilerplateCodex ist Vincents bevorzugte interaktive Arbeitsoberfläche im Demo. Es besitzt keine eigene konkurrierende Wahrheit, sondern liest und verändert das PersonalOS innerhalb seiner Regeln. Agent 0 until used ▲ +1 12 A
764 hermesvincentmumme/personalos-boilerplateHermes steht im Demo für einen dauerhaft verfügbaren Agenten. Auch Hermes nutzt das PersonalOS als zentrale Kontext- und Wahrheitsschicht. Agent 0 until used ▲ +1 12 A
765 use-bun-instead-of-node-vite-npm-pnpmktnyt/cclspUse Bun instead of Node.js, npm, pnpm, or vite. Cursor rule 0 until used ▲ +1 673 A
766 install-spinnerAlexPl292/awesome-claude-spinnersAsk the user which spinner pack they want to install. List all available .json files from the spinners/ directory in this repository (without the .json extension). Command 0 until used ▲ +1 75 B
767 issue-trackerYosefHayim/launch-storeIssues and PRDs for launch-store live as GitHub issues on YosefHayim/launch-store. Use the gh CLI for all operations - it infers the repo from git remote -v automatically inside a clone. Agent 0 until used ▲ +1 9 A
768 expecttestezyang/codemcpWe use expecttest for testing. If you need to match against a multiline string or some output that is likely to change in the future (e.g., the kind of thing you would have ordinarily done an assertIn with), use an expect test. If a test is assertExpectedInline and it fails, use 'accept' command to update the output… Cursor rule 0 until used ▲ +1 1.6k A
769 core-typesYosefHayim/launch-storeEditing the domain shapes or provider interfaces. Cursor rule 0 until used ▲ +1 9 A
770 report_writer_cnpppop00/Equity-Research-CompanyA Chinese interactive research-report generator that fills a fixed HTML template with company research data. An HTML file is a webpage that can include text, styles, scripts, and charts. Agent 0 until used ▲ +1 8 A
771 sprintkesteva/soloflowRun an execution sprint over ready tasks in the backlog. Command 0 until used ▲ +1 40 A
772 supabase-security-engineerconectlens/lenserfightUse for RLS, grants, exposed schemas, SQL functions, views, auth-sensitive migrations, and production DB hardening. Agent 0 until used ▲ +1 19 A
773 团队基线总结-企微Ai搭子nongjun/feishu-cursor-clawA command that reviews how a problem was solved and turns reusable lessons into rules for a team baseline document. It checks existing rules before adding or updating one. Command 0 until used ▲ +1 14 A
774 assistant-registrationnongjun/feishu-cursor-clawA standard for registering webhook-based notifications, such as alerts, daily reports, and reminders, in a central assistant configuration system. A webhook is a URL that receives automated messages from another program. Cursor rule 0 until used ▲ +1 14 A
775 report_validatorpppop00/Equity-Research-CompanyA validator for generated HTML research reports. It checks the required template, validation results, report structure, charts, and selected data consistency. Agent 0 until used ▲ +1 8 A
776 review-prddgonzal3/rallyYou are a senior engineer orchestrating a thorough, iterative code review. Your goal is to leave the code meaningfully better than you found it. Command 0 until used ▲ +1 6 A
777 web-design-directorguia-matthieu/clawfu-skillsSkill "web-design-director" from guia-matthieu/clawfu-skills, covering web design director, when to use this skill, methodology foundation, what claude does vs what you decide and what this skill does. Skill 0 until used ▲ +1 146 A
778 issue-trackerdrunkrhin0/antislopSpecs and tickets for this repository live as Markdown files under .scratch/. Agent 0 until used ▲ +1 23 A
779 grow-scannerDefend-AI-Tech-Inc/agent-discover-scannerAutonomous task: increase real-world adoption of the AgentDiscover scanner. Command 0 until used ▲ +1 21 A
780 Git提交和推送nongjun/feishu-cursor-clawA command that saves local Git changes, incorporates updates from a remote repository, and sends the result back to configured remotes. Git is a system for tracking changes to code, while a remote repository is a shared online copy. Command 0 until used ▲ +1 14 A
781 api-designnth5693/gemini-kitRESTful API patterns, GraphQL design, and API best practices. Skill 0 until used ▲ +1 375 A
782 comm-busHermeticOrmus/LibreEmbed-Claude-CodeYou are a bus-driver-engineer agent using deep expertise across I2C, SPI, UART, CAN, and USB. Help the user design a correct driver, debug a misbehaving driver, or migrate a driver between MCU families. Command 0 until used ▲ +1 44 A
783 iotHermeticOrmus/LibreEmbed-Claude-CodeYou are an iot-protocol-engineer agent with deep expertise across MQTT, CoAP, LwM2M, BLE GATT, LoRaWAN, Thread, and Zigbee. Help the user choose the right protocol for their constraints and design the protocol layer correctly. Command 0 until used ▲ +1 44 A
784 rally-parkddgonzal3/rallyYou are parking the current thread so its tree slot frees up. Branch + Claude convo persist on remote + in Rally's DB. Resume later from any tree. Command 0 until used ▲ +1 6 A
785 network-troubleshootCacinieP/network-troubleshoot-skillSystematic, safety-first network troubleshooting for developers. Cursor rule 0 until used ▲ +1 5 A
786 cortex-m-patternsHermeticOrmus/LibreEmbed-Claude-CodeReal ARM Cortex-M patterns used in production firmware. All code targets C11 with arm-none-eabi-gcc unless noted. Skill 0 until used ▲ +1 44 A
787 bare-metal-patternsHermeticOrmus/LibreEmbed-Claude-CodeProduction bare-metal C patterns for ARM Cortex-M. All code uses arm-none-eabi-gcc, C11. Skill 0 until used ▲ +1 44 A
788 validation-playbookdistsystem/codex-desktop-linuxRun the smallest validation set that matches the touched surface, then broaden when the change crosses package formats, launcher/runtime behavior, updater state, or patch drift handling. Agent 0 until used ▲ +1 12 A
789 ATTRIBUTIONTheStreamCode/super-cliThese compact marks identify compatible third-party CLIs. They do not make Super CLI an official client, partner, or endorsed product. Vendor marks remain the property of their respective owners and are excluded from Super CLI's MIT license; see TRADEMARKS.md. Agent 0 until used ▲ +1 6 A
790 academic-paper-reviewerkomunite/kalfaUluslararası bir derginin tam akran denetimi (peer review) sürecini simüle eder: Makalenin alanını otomatik olarak tanımlar, 5 hakemi (Genel Yayın Yönetmeni + 3 Hakem + Şeytanın Avukatı) dinamik olarak yapılandırır. Bu hakemler; metodoloji, alan uzmanlığı, disiplinler arası bakış açıları ve temel argüman meydan… Skill 0 until used ▲ +1 244 A
791 threat-modelingSecurity-Phoenix-demo/security-skills-claude-codePurpose: Automated threat modeling from code analysis using STRIDE/DREAD methodologies. Skill 0 until used ▲ +1 68 A
792 create-manifestLonelyHerbivore/Trellis-HerbivoreCreate a migration manifest for a new patch, beta, rc, or minor release based on commits since the previous release. Command 0 until used ▲ +1 95 A
793 quant-mathematicianDaviddTech/ai-trading-agentYou are a world-class applied mathematician, statistical researcher, and quantitative strategy architect. Skill 0 until used ▲ +1 53 A
794 b2b-lead-hunterxiongQvQ/-b2b-lead-hunter-skillB2B Lead Hunter — evidence-backed foreign-trade lead research, DM discovery, outreach drafting, and controlled SMTP sending. Cursor rule 0 until used ▲ +1 25 A
795 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
796 position-optimizerDaviddTech/ai-trading-agentYou are a top 0.1% quantitative position-sizing and risk-optimization agent. Skill 0 until used ▲ +1 53 A
797 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
798 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
799 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
800 pragmatistJHostalek/dotclaudeOne lens: is this the most direct path from problem to solution? Agent 0 until used ▲ +1 11 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.