Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 414,922 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.

smell

3529

smallnest/pigo

Skill Claude Code

Detect software architecture bad smells, algorithmic complexity hotspots, and anti-patterns in a codebase. Produces a detailed markdown report identifying violations of architectural principles, design patterns, code quality, and performance complexity. Triggers on: smell, code smell, architecture smell, find…

not rated 435 +7 yesterday A SkillSpector: pass 97 tokens original MIT

plain-writing

3530

docwriter-org/plain-writing-skill

Skill Claude CodeCodex

Writes and edits prose in a plain and boring style: simple everyday words, complete sentences, no dashes, no jargon, and no analogies. Use when drafting or revising documents, Notion pages, reports, summaries, READMEs, emails, slides, commit messages, or PR descriptions, or when the user asks to simplify, clean up…

not rated 435 +58 22d ago A SkillSpector: pass 119 tokens original MIT

fire-your-seo-agency

3531

leopard627/fire-your-seo-agency

Plugin Claude Code

Bundles 1 skill · 162 tokens together

Fire your SEO agency — a Claude Code skill that audits and implements SEO·AEO·GEO·LLMO·NEO(Naver) itself: crawler-eye audit, intent landing pages, llms.txt, structured data, Naver AI Briefing, and a measurement loop.

not rated 435 +23 18d ago A tokens not measured original MIT

marionette

3532

leancodepl/marionette_mcp

MCP server Cursor

MCP server "marionette" as configured in leancodepl/marionettemcp. Launched with fvm dart run ${workspaceFolder}/packages/marionette_mcp/bin/marionette_mcp.dart .

not rated 435 +26 4d ago A tokens not measured original Apache-2.0

markrai/scrumboy

Plugin Claude Code

Bundles 1 skill · 51 tokens together

Agent plugin with Skills for operating Scrumboy boards through its MCP and Agoragentic APIs.

not rated 434 +1 yesterday A tokens not measured AGPL-3.0

pavedpath-code

3534

Jia-Ethan/pavedpath-code

Skill Claude CodeCodex

PavedPath Code is the code-focused edition of PavedPath. It helps agents solve software engineering problems by finding proven implementation paths from GitHub repositories, issues, pull requests, discussions, code examples, release notes, and open-source evidence.

not rated 434 +18 2mo ago A 54 tokens original MIT

spine-animation

3535

GenielabsOpenSource/spine-animation-ai

Skill Claude CodeCodex

Create Spine 2D skeletal animations from pre-existing character assets (separated body-part PNGs, atlas spritesheet, or a full character image). Use this skill whenever the user wants to animate a 2D character, create Spine JSON from existing art assets, rig a character with bones, build walk/idle/run/attack…

not rated 434 +19 19d ago A 181 tokens

Autoloops/greplica

Skill Claude Code

Update Greplica working memory from the current coding-agent session, recent code changes, and durable decisions. Use only when the user explicitly invokes greplica-update-working-memory or asks to update working memory.

not rated 433 1mo ago A SkillSpector: warn 46 tokens original MIT

conductor

3539

microsoft/conductor

Plugin Claude Code ✓ vendor

Bundles 1 skill · 64 tokens together

Multi-agent workflow orchestration via YAML. Ships the conductor skill so the assistant can validate, run, debug, and author workflow files for the conductor CLI.

not rated 433 +9 3d ago A tokens not measured original MIT

pr-review

3540

microsoft/win-dev-skills

Skill Claude CodeCodex ✓ vendor

Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness…

not rated 433 +8 5d ago A SkillSpector: warn 98 tokens original MIT

agent-manager

3541

YoanWai/agent-manager

Skill Claude CodeCodex

Run a fleet of AI coding agents as live tmux sessions with agent-manager. Use when a developer is running more than one coding agent, needs to see which one is working or blocked, wants to spawn another on an independent task, or wants to review an agent's diff without leaving the terminal.

not rated 433 +22 changed 3d ago A SkillSpector: warn 63 tokens original Apache-2.0

job-description-skill

3542

yanliudesign/offer-toolkit-skill

Skill Claude CodeCodex

A job-description analysis skill that turns a vacancy listing and a candidate’s background into an HTML report about fit, gaps, interview topics, and application strategy.

not rated 433 +19 3d ago A SkillSpector: pass 150 tokens original MIT

001_workspace

3543

hyperb1iss/droidmind

Cursor rule Cursor

DroidMind :: Control your Android devices with AI via Model Context Protocol.

not rated 432 +2 8mo ago A 679 tokens original Apache-2.0

enrich

3544

mimurchison/claude-chief-of-staff

Command Claude Code

Build and maintain your personal CRM. Scan communications for contact mentions, update interaction history, and surface relationships that need attention.

not rated 432 +2 7mo ago A 0 tokens original MIT

app-store-optimization

3545

alirezarezvani/claude-code-aso-skill

Skill Claude CodeCodex

Complete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store.

not rated 432 +1 3mo ago A 32 tokens

search-math-results

3546

frenzymath/Danus

Skill Codex

Find program-conditioned math results, constructions, examples, counterexamples, analogies, and background references. Use when the current active program needs repair, mutation, analogy, a program shift, or carefully gated obstruction search.

not rated 432 +20 18d ago A SkillSpector: pass 48 tokens original Apache-2.0

puppetmaster

3547

professorpalmer/Puppetmaster

Skill Claude CodeCodex

Operate and supervise Puppetmaster through MCP or CLI. Use for non-trivial edits, implementations, audits, reviews, broad investigations, CodeGraph lookups, routing decisions, long-running start jobs, MCP disconnects, stuck/empty/degraded jobs, and any request to monitor or recover Puppetmaster work.

not rated 432 +29 today A SkillSpector: pass 66 tokens original MIT

exchange-recovery

3548

openbkn-ai/bkn-foundry

Skill Claude CodeCodex

A recovery workflow for Exchange servers, which are systems used for organisational email and calendars. It covers planning a restoration from backups, creating a recovery job, and checking whether the service works afterward.

not rated 432 +32 yesterday A 0 tokens

Prysai/Prysai-LLM-Playbook

Skill Codex

Audit, draft, and revise public-facing prose for open-source software so it is specific, credible, and natural without flattening the project's voice. Use for README files, documentation, landing pages, release notes, changelogs, contribution guides, PR or issue text, UI copy, error messages, prompts, Traditional…

not rated 432 3d ago A 123 tokens

claude-plan

3550

Ancienttwo/repo-harness

Skill Codex

Get an independent architecture/implementation plan from Anthropic Claude (Fable, a different vendor's model) running Claude Code's native plan mode, from inside a non-Claude host such as Codex. Use mid-execution when work hits a genuine design fork or high-stakes decision that should not be settled unilaterally. Not…

not rated 431 yesterday A SkillSpector: pass 128 tokens original MIT

mu

3551

micro/mu

MCP server Claude CodeCodexCursor +2

News, web search, mail, markets, weather, places, files, calendar, contacts. 67 tools, one endpoint. Remote server at micro.mu.

not rated 431 +1 yesterday A tokens not measured AGPL-3.0

research-writing

3552

alfonso0512/research-writing-skill

Skill Claude CodeCodex

A collection of 30 prompt templates for writing and reviewing scientific papers. It covers tasks such as translating, editing, summarizing research, writing sections, creating figure captions, and preparing reviewer replies.

not rated 431 +9 2mo ago A 136 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: