All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 417,811 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.
asmyshlyaev177/test-proxy-recorder
Skill Claude CodeCodex
Tag server-side fetches with the x-test-rcrd-id session header so SSR is recorded under the correct Playwright test session. Lead with registerProxyFetch (patch global fetch in the root layout, any runtime) and registerProxyAxios (per-axios-instance interceptor); createHeadersWithRecordingId is the patch-free per-call…
Skill Claude CodeCodex
Troubleshoot and configure the Anthropic Subscription Proxy for OpenClaw. Use when the user has "The AI service returned an error", 401 auth failures through the proxy, key routing issues, pi-ai baseUrl overwrites, or needs help setting up the Claude Code proxy with OpenClaw. Also use when the proxy is not receiving…
Agent Claude Code
Manage the full implementation cycle for a single task: dispatch engineer, run two-stage review, iterate until approved.
Skill Claude CodeCodex
Patsnap Patent Research MCP for AI agents. Performs novelty searches, invention freedom-to-operate reviews, and design-patent FTO reviews from technical text, claims, disclosures, or product images. Use for defined novelty and infringement-risk research workflows, including asynchronous task retrieval; do not use it…
terrense/ros2-multimodal-robot-collab
Skill Claude CodeCodex
Use this skill when an Agent needs tool detection, operator identity verification, gesture interpretation, or perception confidence checks in the ROS2 robot collaboration system.
Command Claude Code needs its repo
Run the right verification gates for what changed.
Agent Claude Code
Combined analysis and planning agent for SIMPLE tasks. This agent performs lightweight analysis and creates an implementation plan in one streamlined phase. Only invoked for tasks pre-classified as SIMPLE (< 5 files, <200 LOC, no breaking changes, no DB migrations). Use this agent when you have a simple issue that…
Skill Claude CodeCodex
Solve day-ahead energy market what-if studies on MATPOWER-style network JSON using DC-OPF with spinning reserve co-optimization, compare base vs counterfactual transmission scenarios, and write a validator-friendly report.json.
Plugin Claude Code
Bundles 2 commands, 28 agents · 1,131 tokens together
Universal AI agents collection for Claude Code - 28+ specialized agents with strict boundary enforcement, project-specific agent creation, and intelligent task routing.
Skill Claude CodeCodex
A tool for DingTalk AI Tables, DingTalk's database-like spreadsheets for storing structured records.
Skill Claude CodeCodex
Guide for using KimiX API utilities covering kimix, kimix.utils, kimix.base, kimix.dag, kimix.network, kimix.server, kimix.parser, kimix.tools, kimix.cot, kimix.retrieval, kimix.summarize, and kimiagentsdk.
emanueleielo/deepagents-open-lovable
Skill Claude CodeCodex
Data fetching with TanStack Query, loading states, and error handling.
Skill Claude CodeCodex
Apply the bryl-minimal design language — a monochrome, typography-driven minimal aesthetic with halftone dot textures, pixel-font display headings, tiny uppercase monospace labels, soft large-radius cards, and full light/dark theming. Use this whenever building or restyling any web UI (portfolio, landing page, blog…
Cursor rule Cursor
You are working on a webjs app, an AI-first, no-build, web-components-first framework. Read AGENTS.md for the full API reference and CONVENTIONS.md for project-specific conventions before writing any code. When AGENTS.md doesn't cover what you need, the full hosted docs are at https://webjs.dev/docs.
MCP server Claude CodeCodexCursor +2
Query your MCPSpend usage: cost today, top tools, recent sessions, budget projections. Runs locally from the @mcpspend/mcp-server npm package. Needs 2 environment variables to run.
Skill Claude CodeCodex
Instructions for using QKA, a Chinese-stock quantitative trading backtesting framework. Backtesting means testing a trading strategy against historical market data without placing real trades.
Skill Claude CodeCodex
Complete product development system with 80 agents and 36 frameworks. Use when the user wants to build a product, write a PRD, plan an MVP or roadmap, design an app, research a market or check whether a feature already exists or is novel, do competitive analysis, run a security audit, build a financial model, plan…
Skill Claude Code
Fetch a YouTube transcript and generate an executive summary, key points, and timestamped topic list as a polished HTML report. Activate on YouTube URLs or requests like "summarize this video", "what's this about", "give me the highlights", "TL;DR this", "digest this video", "watch this for me", "I watched this and…
zifengyuan6-star/xuexi-learning-skill
Skill Codex
Always communicate with the user in Chinese.
Skill Claude Code
Background knowledge for droid-control workflows -- not invoked directly. Video assembly via Remotion — title cards, layout, transitions, effects, and showcase polish.
Skill Claude CodeCodex
A command that implements code from a SPEC, a document describing the required behavior and work.
HoraceLuBFA/en-zh-translation-polish
Skill Claude Code
Translate English passages into natural Chinese or polish Chinese translations against the source; supports bilingual output.
Plugin Claude Code
Bundles 11 skills, 2 agents · 1,468 tokens together
ax - the agent experience layer. Local graph of every Claude Code + Codex session, skill invocation, edit, and commit. Surfaces what to use, what to ground on, and which experiments to package next.
egorfedorov/claude-context-optimizer
Plugin Claude Code
Bundles 22 skills, 1 agent, 6 hooks · 613 tokens together
Claude 5-aware context optimization (Fable 5.1 / Opus 5 / Sonnet 5 pricing, 1h-cache-aware real costs & cache-break detection), SKILL.state-style task state that survives /compact, session baseline audit (/cco-overhead), auto .contextignore, self-calibrating estimates, delegation advisor, ru/en prompt coach…
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: