Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 570,849 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.

f/prompts.chat

Instructions file CodexOpenCode

AGENTS.md instructions for f/prompts.chat, covering agents.md, project overview, tech stack, project structure and commands.

not rated 169k +233 yesterday A 2,226 tokens

f/prompts.chat

Instructions file

Claude Code instructions for f/prompts.chat, covering claude.md, project overview, quick commands, development and database.

not rated 169k +233 yesterday A 571 tokens

huggingface/transformers

Skill Claude CodeCodex ✓ vendor

Fixes broken typing checks detected by ty, make typing, or make check-repo. Use when typing errors appear in local runs, CI, or PR logs.

not rated 165k 5d ago A 41 tokens original Apache-2.0

huggingface/transformers

Instructions file GitHub Copilot ✓ vendor

Instructions for huggingface/transformers, covering copilot-instructions.md guide for hugging face transformers, core project structure, coding conventions for hugging face transformers, copying and inheritance and testing.

not rated 165k 5d ago A 773 tokens original Apache-2.0

huggingface/transformers

Instructions file CodexOpenCode ✓ vendor

Instructions for huggingface/transformers, a project described as: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

not rated 165k 5d ago A 5 tokens original Apache-2.0

huggingface/transformers

Instructions file ✓ vendor

Instructions for huggingface/transformers, a project described as: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

not rated 165k 5d ago A 5 tokens copy · 100% Apache-2.0

backend-code-review

103

langgenius/dify

Skill Claude CodeCodex

Use only when the user explicitly requests a review or audit of backend code under api/. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests, diagnosis without review intent, frontend code, or backend code outside api/.

not rated 154k +220 today A 60 tokens

frontend-code-review

104

langgenius/dify

Skill Claude CodeCodex

Use only when the user explicitly requests a review or audit of frontend code under web/ or packages/dify-ui/. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests, diagnosis without review intent, or backend-only code.

not rated 154k +220 today A 62 tokens

langgenius/dify

Skill Claude CodeCodex

Use when implementing or refactoring React/TypeScript components and the task requires decisions about component ownership, feature boundaries, state, data flow, effects, or interaction ownership. Do not use for review-only requests, test-only work, copy-only edits, or styling-only changes.

not rated 154k +220 changed today A 60 tokens

PreToolUse

106

langgenius/dify

Hook Claude Code

One of 2 in settings.json

Runs before the agent uses a tool for Bash tool calls, running npx -y [email protected]. From langgenius/dify.

not rated 154k +220 today A tokens not measured

dify

107

langgenius/dify

Settings file Claude Code

One of 2 in settings.json

Agent settings declaring 1 hook event (PreToolUse).

not rated 154k +220 today A tokens not measured

dify AGENTS.md

108

langgenius/dify

Instructions file CodexOpenCode

AGENTS.md instructions for langgenius/dify, covering agents.md, repository gotchas and frontend workflow.

not rated 154k +220 changed 2d ago A 222 tokens

dify CLAUDE.md

109

langgenius/dify

Instructions file

Claude Code instructions for langgenius/dify, a project described as: Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

not rated 154k +220 today A 3 tokens

AGENTS

110

langgenius/dify

Command

Per-command agent-optimized usage and structure guide.

not rated 154k +220 today C 0 tokens

docs-langchain

111

langchain-ai/langchain

MCP server Claude CodeCodexCursor +2 ✓ vendor

One of 2 in .mcp.json

MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.

5 · 1 146k +166 today A tokens not measured original MIT

reference-langchain

112

langchain-ai/langchain

MCP server Claude CodeCodexCursor +2 ✓ vendor

One of 2 in .mcp.json

MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/langchain.

not rated 146k +166 today A tokens not measured original MIT

langchain AGENTS.md

113

langchain-ai/langchain

Instructions file CodexOpenCode ✓ vendor

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

not rated 146k +166 today A 4,345 tokens original MIT

langchain CLAUDE.md

114

langchain-ai/langchain

Instructions file ✓ vendor

Claude Code instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

not rated 146k +166 today A 4,345 tokens copy · 100% MIT

dedupe

115

anthropics/claude-code

Command Claude Code ✓ vendor

Find duplicate GitHub issues.

not rated 144k +180 today A 5 tokens

triage-issue

116

anthropics/claude-code

Command Claude Code ✓ vendor

Triage GitHub issues by analyzing and applying labels.

not rated 144k +180 today A 10 tokens

insight-error-page

117

vercel/next.js

Skill Claude CodeCodex ✓ vendor

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

not rated 142k 4d ago A 83 tokens original MIT

sandbox-bench

118

vercel/next.js

Skill Claude CodeCodex ✓ vendor

Benchmark React or Next.js changes on Vercel Sandbox VMs with paired A/B statistics: react PR/commit vs base, or Next.js PR/commit vs base, measured end-to-end through the bench/render-pipeline app (rps, latency, p95; TTFB, RSS and document/Flight bytes when the Next side captures them) and, for React changes, through…

not rated 142k 4d ago A 212 tokens original MIT

v8-jit

119

vercel/next.js

Skill Claude CodeCodex ✓ vendor

V8 JIT optimization patterns for writing high-performance JavaScript in Next.js server internals. Use when writing or reviewing hot-path code in app-render, stream-utils, routing, caching, or any per-request code path. Covers hidden classes / shapes, monomorphic call sites, inline caches, megamorphic deopt, closure…

not rated 142k 4d ago A 88 tokens original MIT

gt-workflow

120

vercel/next.js

Command Cursor ✓ vendor

Use Graphite (gt) instead of git for ALL branch and commit operations in this repository.

not rated 142k 4d ago A 0 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: