Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 415,087 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.

openbb-data-fetcher

4441

monarchjuno/vibe-investing

Skill Claude CodeCodex

Fetch financial, market, economic, fundamental, news, options, crypto, ETF, index, and macro data through the OpenBB Python interface instead of the OpenBB MCP server. Use when an agent needs current or historical data from OpenBB-supported providers, needs to replace OpenBB MCP calls with direct Python/OpenBB usage…

not rated 299 +2 4mo ago A SkillSpector: warn 94 tokens original MIT

forgetful-remember

4442

ScottRBK/forgetful

Skill Claude Code

Remember knowledge worth keeping — a decision made, a solution found, a preference stated, a pattern confirmed. Use when work surfaces something future sessions will need, or the user asks to remember something. Routes content to the right store (memory, document, code artifact, entity, procedure, file) and enforces…

not rated 299 13d ago A SkillSpector: pass 71 tokens original MIT

TIMAN-group/PlugMem

Plugin Claude Code

Bundles 6 hooks

PlugMem cross-session memory for Claude Code — a self-writing CLAUDE.md that learns project conventions and debugging recipes from your sessions.

not rated 299 +2 2mo ago A tokens not measured original Apache-2.0

context7

4444

PageAI-Pro/ralph-loop

MCP server Claude CodeCodexCursor +2

One of 3 in .mcp.json

Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.

not rated 299 +4 15d ago A tokens not measured copy · 75% MIT

ielts-writing

4445

YANZHANLIN/ielts-claude-skills

Skill Claude CodeCodex

A Chinese-language IELTS writing coach covering task analysis, scoring, sentence-level feedback, and rewritten examples.

not rated 299 +3 1mo ago A SkillSpector: pass 62 tokens original MIT

honey

4446

Green-PT/honey-for-devs

Cursor rule Cursor

Honey — write less code and say less about it. A reflexive minimal-code (YAGNI/stdlib-first) and terse-prose discipline that cuts token cost while keeping code, commands, and safety-critical paths exact.

not rated 299 +6 8d ago A 3,222 tokens original MIT

qgis

4447

nkarasiak/qgis-mcp

MCP server Claude CodeCodexCursor +2

MCP server "qgis" as configured in nkarasiak/qgis-mcp. Runs locally from the src/qgis_mcp/server.py Python package.

not rated 299 +12 3d ago A tokens not measured GPL-2.0

spec-governance

4448

devcodex-labs/devcodex

Skill Claude CodeCodex

A governance skill for managing the lifecycle of specifications: recording intent, routing records, and checking specification changes.

not rated 299 +46 changed 6d ago A 42 tokens AGPL-3.0

qiaomu-blog-publish

4449

joeseesun/qiaomu-blog-opensource

Skill Claude Code

A publishing workflow for sending Markdown, text, or a web page to a Qiaomu Blog, with category and draft or published status controls.

not rated 299 4mo ago A 37 tokens original MIT

obsidian-md2wechat

4450

geekjourneyx/obsidian-md2wechat

Skill Claude CodeCodex

Format the current Obsidian article with the existing md2wechat CLI and return its preview to the Obsidian publishing plugin. Use when the user asks to typeset an Obsidian note for WeChat.

not rated 299 +13 2d ago A 49 tokens original AGPL-3.0

prompt-architect

4451

ckelsoe/prompt-architect

Plugin Claude Code

Bundles 1 skill · 111 tokens together

31-framework prompt engineering skill for analyzing and improving prompts across 7 intent categories.

not rated 298 +3 1mo ago A tokens not measured original MIT

ubs

4452

Dicklesworthstone/ultimate_bug_scanner

Skill Claude CodeCodex

Ultimate Bug Scanner - Pre-commit static analysis for AI coding workflows. 14-24 detection categories per language, 12 languages, regex + ast-grep + AST-helper analysis. The AI agent's quality gate.

not rated 298 +4 changed 6d ago C 46 tokens

directory

4453

FifthWye/submitmap-mcp

MCP server Claude CodeCodexCursor +2

A directory of product launch platforms: where your product qualifies and how each form is filled. Remote server at submitmap.com.

not rated 298 +2 27d ago A tokens not measured original MIT

medsci-modeling

4454

Aperivue/medsci-skills

Plugin Claude Code

Bundles 12 skills · 2,082 tokens together

Clinical AI model research engineering: choose a paper-grounded architecture, scaffold a reproducible PyTorch training repo, validate the model's split and validation design, document it (Model Card / Datasheet), and evaluate models or LLMs/MLLMs on clinical tasks. Integrates MONAI / nnU-Net, never replaces them.

not rated 298 +7 yesterday A tokens not measured original MIT

metric-spec

4455

ai-analyst-lab/ai-analyst

Skill Claude Code

Define any metric completely with a standardized template: calculation, denominator, time window, filters, interpretation. Trigger on "define this metric", "how should we measure X?", "what's the right way to calculate Y?", "document our metrics", "create a metric definition", "different teams are measuring this…

not rated 298 +1 yesterday A 79 tokens original MIT

kui-framework

4456

abersheeran/kui

Skill Claude Code

Guide for building web applications with the Kui framework. Use when writing Kui ASGI/WSGI handlers, defining routes, binding parameters, configuring OpenAPI docs, or working with middleware/dependency injection.

not rated 297 5mo ago A 44 tokens original Apache-2.0

servicenow

4457

echelon-ai-labs/servicenow-mcp

MCP server Claude CodeCodexCursor +2

MCP server "servicenow" as configured in echelon-ai-labs/servicenow-mcp. Runs servicenow_mcp.cli with python. Needs 4 environment variables to run.

not rated 297 4mo ago A tokens not measured original MIT

mcp

4458

Snowflake-Labs/mcp

MCP server Claude CodeCodexCursor +2

MCP server for Snowflake. Runs locally from the snowflake-labs-mcp Python package. Needs 13 environment variables to run.

not rated 297 4mo ago A tokens not measured original Apache-2.0

watchmen

4459

firstbatchxyz/watchmen

Plugin Claude Code

Bundles 1 hook

Surface skill suggestions + workspace context from watchmen sessions intelligence into your Claude Code sessions.

not rated 297 +1 21d ago A tokens not measured original MIT

JSONbored/awesome-claude

Skill Claude Code

Use when writing, testing, or preparing ANY contribution or pull request to the JSONbored/awesome-claude (HeyClaude) repo — adding a community content entry (agent/MCP server/skill/hook/command/rule/guide/collection/statusline), or making a platform/code change (website, registry package, MCP package, scripts). The…

not rated 297 29d ago A SkillSpector: pass 209 tokens original MIT

habitat-gs-train

4462

zju3dv/habitat-gs

Skill Claude CodeCodex needs its repo

Train and evaluate a navigation policy in the habitat-gs simulator. Covers the full generate-episodes → train → evaluate flow for PointNav / ImageNav / ObjectNav (Habitat-Lab + DDPPO reinforcement learning) and for Vision-and-Language Navigation (StreamVLN, Uni-NaVid). Use when the user wants to train, fine-tune…

not rated 297 +5 1mo ago A SkillSpector: pass 114 tokens original MIT

ieee-figure-table

4463

CloudWave818/ieee-skills

Skill Codex

Audit, redesign, generate, and improve IEEE manuscript figures, tables, captions, result presentation, plotting scripts, visual polish, hybrid Python/R plus vector-editor workflows, publication-ready matplotlib house style, and layout using routed visual-evidence checks. Use when checking or creating plot readability…

not rated 297 +19 1mo ago A SkillSpector: pass 142 tokens original MIT

auto-research-loop

4464

Dominic789654/awesome-deepseek-harness

Skill Claude CodeCodex

A bounded research workflow that repeats four steps: planning, searching, reading, and combining findings. It records each step and its sources so the work can resume after an interruption.

not rated 297 +62 today A 79 tokens

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: