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
501 continueDunCanYounG-1/auto-embeddedA command for resuming an unfinished auto-embedded development task. It reloads the project context and identifies the current stage, recent changes, hardware-resource state, research findings, and next action. Command 0 until used ▲ +2 218 A
502 issue-orchestratordsifry/metaswarmType: issue-orchestrator Role: Main coordinator for a single GitHub Issue lifecycle Spawned By: Swarm Coordinator or GitHub webhook Tools: BEADS CLI, GitHub API, Task tool (spawns other agents). Agent 0 until used ▲ +2 407 A
503 handle-pr-commentsdsifry/metaswarmHandle review comments on pull requests with appropriate responses and resolutions. Command 0 until used ▲ +2 407 A
504 metaswarm-setupdsifry/metaswarmInteractive, Claude-guided setup for metaswarm in your project. Detects your stack, asks targeted questions, and customizes everything automatically. Command 0 until used ▲ +2 407 A
505 builtinmicrosoft/STATE-BenchStateBenchAgent is the provided standard tool-calling agent loop for Azure AI Foundry models and OpenAI models. It uses the OpenAI v1 client to call the Responses API with the benchmark's domain tools and the locked prompt protocol. If your model supports this tool-calling path, no agent code is required. Agent 0 until used ▲ +2 84 A
506 architect-agentdsifry/metaswarmType: architect-agent Role: Implementation planning and architecture design Spawned By: Issue Orchestrator Tools: Codebase read, architecture-rubric, BEADS CLI. Agent 0 until used ▲ +2 407 A
507 AGENTSagent0ai/space-agentCommand "AGENTS" from agent0ai/space-agent, covering agents, purpose, ownership, local contracts and contract. Command 0 until used ▲ +2 1.4k A
508 add-landing-templateclassroomio/classroomioWorkflow for adding a new org landing-page template (editorial, vibrant, terminal, etc.) to the ClassroomIO monorepo. Activate when the user asks to add/create/build a new landing template or theme, or hands over a design reference for a new landing visual style. Cursor rule 0 until used ▲ +2 1.7k A
509 finesse-briefmouse-lin/finesse-briefA product-definition method that creates a written workbench specification before anyone builds the interface. A workbench can be a personal browser page for daily records or a larger browser system with modules, pages, and data entities. Cursor rule 0 until used ▲ +2 44 A
510 buildervscarpenter/gsd-task-managerThe builder is a local, scheduled Claude Code routine (cycle B of the delivery pipeline). It turns a fully-specified issue into a reviewed pull request, pausing once for human plan approval (Gate 1). It never merges. It is launched by scripts/builder-run.sh; its per-run instructions live in… Agent 0 until used ▲ +2 24 A
511 1.1_monetary_sentinelolaxbt/ai-market-makerSkill "1.1_monetary_sentinel" from olaxbt/ai-market-maker, covering skill: monetary sentinel (1.1), capabilities, data sources (as-of the bar date; never later prints), how to read the overlay and query interface. Skill 0 until used ▲ +2 2.1k A
512 2.3_technical_ta_engineolaxbt/ai-market-maker/technicaltaengine?ticker=BTC/USDT&period=4h&bars=100. Skill 0 until used ▲ +2 2.1k A
513 product-designersInfrasity-Labs/dev-gtm-claude-skillsCommand "product-designers" from Infrasity-Labs/dev-gtm-claude-skills, covering research & discovery, strategy & planning, ux laws & frameworks, design system and interface design. Command 0 until used ▲ +2 117 A
514 job-searchInfrasity-Labs/dev-gtm-claude-skillsCommand "job-search" from Infrasity-Labs/dev-gtm-claude-skills, covering search & applications, resume building, cover letters & outreach, research & prep and profile & portfolio. Command 0 until used ▲ +2 117 A
515 prep-for-taskBRO3886/remBootstrap context for a new session on the rem project. Run this BEFORE starting any implementation work. Command 0 until used ▲ +2 151 A
516 journalBRO3886/remWrite a journal entry for today's work session on the rem project. Command 0 until used ▲ +2 151 A
517 beans-release-noteshmans/beansGenerate release notes from commits since the last version tag and write them to .docs.local/RELEASE.md. Command 0 until used ▲ +2 911 A
518 youtube-deepdivehamzafarooq/claude-code-starterIf one or more YouTube video URLs were not provided, ask the user. Command 0 until used ▲ +2 138 A
519 explain-me-a-repohamzafarooq/claude-code-starterIf a GitHub repo URL was not provided, ask the user for one now. Command 0 until used ▲ +2 138 A
520 scopejzl-maker/EA-SKILLA command for connecting to supported oscilloscopes, capturing or reading waveforms, measuring them, and saving results as CSV files or plots. An oscilloscope is a device that displays changing electrical signals. Command 0 until used ▲ +2 6 A
521 debugjzl-maker/EA-SKILLA command-line debugging toolkit for embedded programs using J-Link or OpenOCD, tools that connect a computer to a microcontroller for inspection. Command 0 until used ▲ +2 6 A
522 reviewphuryn/pm-brainThe weekly maintenance sweep. Six checks. Produces a dated report and edits files directly where confidence is high. Command 0 until used ▲ +2 537 A
523 instagramimoonkey/openwebSocial media platform (Meta). Photo/video sharing, stories, reels. Skill 0 until used ▲ +2 58 A
524 strategy-checkphuryn/pm-brainDrift check between recent decisions / ingestions / active hypotheses and knowledge/strategy.md. Read-only synthesis. Surfaces tensions for the PM to resolve; does NOT silently edit strategy. Command 0 until used ▲ +2 537 A
525 mcpwynsyl1014/open-watch-cinemaUse this skill whenever you are connected to Open Watch Cinema through its MCP server. Skill 0 until used ▲ +2 40 A
526 overnight-80paiml/depylerAutonomous improvement loop designed to run all night. Handles ANY starting condition. Command 0 until used ▲ +2 357 A
527 convergepaiml/depylerRun the convergence protocol from docs/prompts/convergereprorusted100.md. Command 0 until used ▲ +2 357 A
528 gate-checkpixel-cellar/Claude-Code-Game-StudiosA readiness check for moving a game project from one development stage to the next. It checks required documents, quality conditions, and blockers, then can record the new stage in a project status file. Skill 0 until used ▲ +2 323 A
529 daosorangehrm/orangehrmReference for writing query/persistence code in OrangeHRM — the plugin-specific Dao classes that extend OrangeHRM\Core\Dao\BaseDao, the EntityManagerHelperTrait and its 13 methods, the QueryBuilder patterns the codebase uses heavily (joins via relation aliases, $q->expr()->orX/andX/like/concat/in/isNull, conditional… Skill 0 until used ▲ +2 1.1k A
530 spec-createPimzino/claude-code-spec-workflowCreate a new feature specification following the complete spec-driven workflow. Command 0 until used ▲ +2 3.9k A
531 market-research-notes-opensource-releasemgwalkerjr95/texas-grocery-mcpDate: 2026-01-29 Requested By: Brainstorming Session - Open Source Release Planning Agent: Market Research Advisor. Agent 0 until used ▲ +2 56 A
532 requirements-advisor-notes-opensource-releasemgwalkerjr95/texas-grocery-mcpDate: 2026-01-29 Task: Analyze requirements for open source release of HEB MCP Status: Complete. Agent 0 until used ▲ +2 56 A
533 spec-executePimzino/claude-code-spec-workflowExecute specific tasks from the approved task list. Command 0 until used ▲ +2 3.9k A
534 READMEBiboyQG/WeChat-MCPA set of five assistants for managing WeChat chats, including summaries, searches, replies, multi-chat checks, and conversation analysis. Agent 0 until used ▲ +2 247 A
535 bmad-pilotstellarlinkco/myclaudeCommand "bmad-pilot" from stellarlinkco/myclaude, covering usage, options, context, your role and initial repository scanning phase. Command 0 until used ▲ +2 2.7k A
536 requirements-pilotstellarlinkco/myclaudeCommand "requirements-pilot" from stellarlinkco/myclaude, covering usage, options, context, your role and initial repository scanning phase. Command 0 until used ▲ +2 2.7k A
537 viberaven-paymentsohad6k/VibeRavenApply when editing Stripe, Polar, or payment webhook handlers. Cursor rule 0 until used ▲ +2 33 A
538 quickvigorX777/ppt-svg-generatorA command that turns a Markdown document into presentation slides as SVG files, using a selected visual style. SVG is a scalable image format that keeps graphics sharp. Command 0 until used ▲ +2 258 A
539 generatevigorX777/ppt-svg-generatorA command that creates SVG files for every slide in a presentation, using the page structure and design rules prepared earlier. Command 0 until used ▲ +2 258 A
540 autonomousThibautMelen/agentic-ai-systemsAgent "autonomous" from ThibautMelen/agentic-ai-systems, covering 🐔 autonomous agent, diagram, the agent loop, key insight and characteristics. Agent 0 until used ▲ +2 302 C
541 auditmarcosd4h/DeepExtractRuntimePerform a focused security audit of a specific function -- building a comprehensive security dossier, tracing attack reachability, and reporting findings with risk assessment and recommendations. Command 0 until used ▲ +2 20 A
542 ai-logical-bug-scanmarcosd4h/DeepExtractRuntimeAI-driven scan for logic vulnerabilities: authentication/authorization bypass, state machine errors, confused deputy, privilege escalation, missing impersonation revert, and sensitive API parameter injection. Command 0 until used ▲ +2 20 A
543 billingnikandr-surkov/ai-saas-starterBilling & credits invariants. Cursor rule 0 until used ▲ +2 15 A
544 meta-agentDavidROliverBA/ArchitectKBYou are a meta-agent. Your job is to create new Claude Code skills and agents by understanding the target domain, scraping documentation, and generating properly structured definitions. Agent 0 until used ▲ +2 52 A
545 stale-content-reviewerDavidROliverBA/ArchitectKBScan the vault for notes with stale content and produce a triage report recommending updates, archiving, or freshness downgrades. Agent 0 until used ▲ +2 52 A
546 code_reviewFastLED/FastLEDYou are a specialized code review agent for FastLED. Review staged and unstaged changes according to these strict rules. Command 0 until used ▲ +1 7.5k A
547 setup-mention-highlightscivitai/civitaiSets up VS Code mention highlighting configuration for markdown files. Creates or updates the necessary VS Code workspace files to highlight @dev, @ai, and other @ mentions. Command 0 until used ▲ +1 7.2k A
548 od-expertyzhao062/pyodAnomaly detection expert backed by PyOD's ADEngine. Drives autonomous detection workflows on tabular, time series, graph, text, and image data: profiling, planning, multi-detector comparison, quality assessment, iteration, and reporting. Encodes deep OD knowledge so non-expert users can run the full workflow without… Skill 0 until used ▲ +1 10.0k A
549 thunder-deep-reviewthunderbird/thunderboltReviews a pull request, diff, or branch against Thunderbolt's house rules (no any, type-over-interface, arrow fns, const/early-return, no error-swallowing or defensive code, useReducer at 3+ useState, useEffect discipline, route code-splitting, soft-deletes, integration-agnostic logic) and the 80 architecture… Skill 0 until used ▲ +1 4.8k A
550 app_layer_rulesModelEngine-Group/nexentApp layer (API) contract for FastAPI endpoints in backend/apps. Parse/validate input, call services, map domain errors to HTTP, return JSONResponse on success. Cursor rule 0 until used ▲ +1 5.8k A
551 database_layer_rulesModelEngine-Group/nexentDatabase layer standards for models, CRUD, transactions, and exceptions. Cursor rule 0 until used ▲ +1 5.8k A
552 management-autopr-review-criticAzure/azure-sdk-for-javaAgent "management-autopr-review-critic" from Azure/azure-sdk-for-java, covering management autopr review critic and management autopr review critique. Agent 0 until used ▲ +1 2.6k A
553 qawolfCliRunResults.templateqawolf/cliHow to use what qawolf run get --run-id --json returns, and how to read the Playwright trace it links to. Command 0 until used ▲ +1 3.4k A
554 releasekayba-ai/agentic-context-engineRelease a new version: bump version, update changelog, tag, push, and create a GitHub release. Command 0 until used ▲ +1 2.6k A
555 checkout-branchkayba-ai/agentic-context-engineSwitch to an existing branch by checking out its worktree, or creating one if needed. Command 0 until used ▲ +1 2.6k A
556 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 ▲ +1 4.8k A
557 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 ▲ +1 892 A
558 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 ▲ +1 2.9k A
559 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 ▲ +1 2.9k A
560 issue-trackerlanding-ai/ade-cliIssues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations. Agent 0 until used ▲ +1 2.4k A
561 writing-stylelanding-ai/ade-cliStandards for every string a user or an agent reads: help text and docstrings (which become ade help and the hosted CLI reference), the README, and SKILL.md. Agent 0 until used ▲ +1 2.4k A
562 analyze-repoalinaqi/maggyAnalyze an existing repository's structure, conventions, and guardrails. Command 0 until used ▲ +1 705 A
563 analyze-workspacealinaqi/maggyCommand "analyze-workspace" from alinaqi/maggy, covering /analyze-workspace, trigger, behavior, phase 1: topology discovery (30 seconds) and phase 2: module analysis (60 seconds). Command 0 until used ▲ +1 705 A
564 snipedouard-claude/snipYou are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output. Skill 0 until used ▲ +1 432 A
565 distillate-compressordelorenj/mcp-server-trelloAct as an information extraction and compression specialist. Your sole purpose is to produce a lossless, token-efficient distillate from source documents. Agent 0 until used ▲ +1 436 A
566 n8n-workflow-formatEtienneLescot/n8n-as-codeUse n8n-as-code TypeScript workflow files and explicit sync discipline for n8n workflow work. Cursor rule 0 until used ▲ +1 1.6k A
567 domainxiaods/k8eHow the engineering skills should consume this repo's domain documentation. Agent 0 until used ▲ +1 481 A
568 acceptance-tests-prompts-agentsjabrena/plinthAgent "acceptance-tests-prompts-agents" from jabrena/plinth, covering acceptance test prompts for agents, plinth-architect, plinth-tech-lead, plinth-java-coder and plinth-java-spring-boot-coder. Agent 0 until used ▲ +1 435 A
569 review-prrobotocore/robotocoreReview, improve, and merge an open pull request. The submitter did the work — your job is to get their PR merged cleanly, giving them full credit. Command 0 until used ▲ +1 330 A
570 etrulesFlameskyDexive/Legends-Of-HeroesA Chinese-language coding rule set for the ET framework, a game-development framework using an entity-component-system structure. It defines how data, logic, packages, and assemblies should be organized. Cursor rule 0 until used ▲ +1 922 A
571 triage-labelsxiaods/k8eThe engineering skills use five canonical triage roles. This file maps those roles to the label strings used in this repo's GitHub Issues. Agent 0 until used ▲ +1 481 A
572 wiki-initussumant/llm-wiki-compilerInteractive, conversational setup for a new knowledge base wiki. One question at a time, multiple choice when possible. Command 0 until used ▲ +1 321 A
573 validateAuties00/CobaltYou are the lead validation orchestrator for the Cobalt project. Your job is to prove that Cobalt implements every WhatsApp Web / Desktop / Mobile feature correctly, both at the source level (behavioral parity with the WA Web JS source) and at the observable level (the Nodes, WAM events and HTTP that Cobalt produces… Command 0 until used ▲ +1 915 A
574 fetch-bookmarksussumant/llm-wiki-compilerPull bookmarks from an external service (X/Twitter today; Readwise, Pocket, GitHub stars planned) into a local directory that /wiki-compile can consume. Optional — only needed when you want wiki topics synthesized from external sources, not just files already on disk. Command 0 until used ▲ +1 321 A
575 horosa-agenttradecatlabs/fatecatUse this skill when an AI agent is connected to Horosa Skill through MCP, CLI, Cursor, Claude, Codex, OpenClaw, Open WebUI, or another local-first client and needs to call Horosa metaphysics tools, generate reports, store memory, or debug user-facing results. Skill 0 until used ▲ +1 202 A
576 anchormindJinHo-von-Choi/anchormindReference guidance for AnchorMind, a memory server that stores, searches, connects, and updates long-term fragments for AI agents. Skill 0 until used ▲ +1 137 A
577 engine-internals0xranx/golembotCoding Agent engine implementation details (Cursor + Claude Code) — reference when modifying engine.ts or debugging Agent behavior. Cursor rule 0 until used ▲ +1 319 A
578 create-namespacestarmynd-org/infinite-brain-osSlash command that creates a new namespace file under system/namespaces/ in the personal repo, with lifecyclestate: scratch. Command 0 until used ▲ +1 243 A
579 testing-conventions0xranx/golembotTesting conventions — must reference when modifying src/ code or tests. Cursor rule 0 until used ▲ +1 319 A
580 analyze-prEthanAlgoX/LLM-TradeBotA guide for reviewing GitHub pull requests, which are proposed code changes awaiting review. It checks the change's purpose, description, supporting test evidence, risks, and readiness to merge. Skill 0 until used ▲ +1 316 A
581 bazi-skill-gaoxin492-maintradecatlabs/fatecatA Chinese Four Pillars astrology skill that uses local Python scripts to calculate and store birth charts, while the agent interprets the results. Four Pillars is a traditional Chinese system based on birth date and time. Skill 0 until used ▲ +1 202 A
582 lintshenjingnan/xiaozhi-clientA code-quality command for checking, formatting, and spell-checking a TypeScript or JavaScript project. Command 0 until used ▲ +1 337 A
583 analyze-issueEthanAlgoX/LLM-TradeBotA GitHub Issue review workflow that checks whether a reported problem is real, important, and within the repository’s responsibility. Skill 0 until used ▲ +1 316 A
584 testingwindviki/vBookmarksAgent "testing" from windviki/vBookmarks, covering testing & real-browser harness (detail), unit tests (detail), manual testing checklist and headless smoke test (docker). Agent 0 until used ▲ +1 134 A
585 AGENTSapify/awesome-skillsAgent "AGENTS" from apify/awesome-skills, covering awesome apify skills, available skills, how to add a new skill (for ai agents), files to create and marketplace entry. Agent 0 until used ▲ +1 248 A
586 largest-files-finderthesongzhu/FridayList the top 3 largest files in a given directory. Skill 0 until used ▲ +1 838 A
587 agent-developmentdivar-ir/ai-doc-genGuidelines for developing pydantic-ai agents, tools, and handlers. Cursor rule 0 until used ▲ +1 753 A
588 releasewindviki/vBookmarksSince 4.1.0 the release form is dist/ (esbuild bundle + Terser minify, same-path structure — the dev flow stays build-free). Agent 0 until used ▲ +1 134 A
589 deck_pipeline_orchestrator_promptBUPT-GAMMA/MASFactoryYou are the orchestrator agent for a multi-agent slide production pipeline. You do not personally create every artifact. Your job is to split the work into verifiable stages and ensure that each stage produces outputs clean enough for the next stage to consume reliably. Agent 0 until used ▲ +1 549 A
590 extract-action-itemsthesongzhu/FridayExtract a list of action items with owners and deadlines from a meeting transcript. Skill 0 until used ▲ +1 838 A
591 requirements_to_outline_system_promptBUPT-GAMMA/MASFactoryYou are an "outline agent for lab meetings and paper presentations." Your job is to turn raw requirements and reference materials into a slide-level outline that can actually be presented, not a summary that simply piles up paper content. Agent 0 until used ▲ +1 549 A
592 kiro-steering-customgotalab/cc-sddCommand "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance. Command 0 until used ▲ +1 3.6k A
593 agent-04-crypto-vuln-analyzerFausto-404/ai-mobile-reverse-skillsA security-analysis agent that checks code for weak encryption and other high-risk vulnerabilities, then records how much evidence supports each finding. Agent 0 until used ▲ +1 150 A
594 my-agent1mancompany/OneManCompanyYou are an autonomous GitHub engineering agent working in strict TDD mode. Agent 0 until used ▲ +1 403 A
595 craft-taskjmcentire/pactYou are helping the user craft an optimal task specification for Pact, the contract-first multi-agent software engineering framework. Your goal is to produce a task.md and sops.md that will lead to high-quality decomposition, contracts, and implementations. Command 0 until used ▲ +1 164 A
596 agent-container-integration-requirementslucky-aeon/AgentXA requirements document for connecting AgentX conversations with user containers, which are isolated environments that run tools for an agent. Command 0 until used ▲ +1 830 A
597 agent-02-protocol-mapperFausto-404/ai-mobile-reverse-skillsA mobile-app reverse-engineering analysis role that links captured requests, request fields, signatures, authentication data, and code locations. Reverse engineering here means examining local app code and traffic to understand how they correspond. Agent 0 until used ▲ +1 150 A
598 kotlin-springboot-rulesholtwood/awesome-cursorrules-zhA set of coding rules for Kotlin applications built with Spring Boot, a Java-based framework for web services. It covers project layout, naming, Kotlin style, and common design patterns. Cursor rule 0 until used ▲ +1 231 A
599 ci-conflict-resolverai-sdlc-framework/ai-sdlcCI-triggered PR conflict-resolver. Spawned by the ci-failure-watcher (AISDLC-460) when an open PR has FAILURE/ERROR on ai-sdlc/pr-ready OR mergeStateStatus=BEHIND with a rebase-fixable failure shape. Reuses the rebase-resolver flow — rebases onto origin/main, resolves mechanical conflicts (test additions, prettier… Agent 0 until used ▲ +1 92 A
600 rag-publish-requirementslucky-aeon/AgentXA command for planning how a RAG knowledge base is published. RAG is a system that retrieves stored documents to help produce answers; the plan covers version snapshots, administrator review, and database records. Command 0 until used ▲ +1 830 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.