hk-test-writer
8449Agent Claude Code
You are a test-writing specialist for the harness-kit monorepo. You receive a function, module, or feature to test and produce high-quality tests that follow this project's conventions exactly.
All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 436,793 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.
Agent Claude Code
You are a test-writing specialist for the harness-kit monorepo. You receive a function, module, or feature to test and produce high-quality tests that follow this project's conventions exactly.
Cursor rule Cursor
Brand workspace context loading for Adspirer performance marketing. Ensures the agent reads brand context and memory on every session, and bootstraps new workspaces automatically.
Plugin Claude Code
Bundles 10 skills · 174 tokens together
You say it, AutoCode ships it. 11 skills. See a product you like, get a sourced blueprint and an MVP cut, build and deploy it in one session. I-Lang v5.0 judgment: AI decides the small stuff, checks with you on the costly stuff.
Skill Claude CodeCodex
Airbnb's UI design system. Use when building interfaces inspired by Airbnb's aesthetic - light mode, Inter font, 4px grid.
Skill Claude CodeCodex
Use this to access external services/CLIs/APIs: Gmail/gh/Github/Stripe etc. or when running any bash command, script, or curl/wget that makes outbound HTTP calls. Make HTTP requests directly and the gateway injects credentials automatically.
Skill Claude Code
Query spend and token activity on a live LiteLLM proxy. Shows daily usage broken down by user, team, org, tag, job, or model. Use when the user wants to see costs, token counts, request volume, or job-level attribution for a given date range.
Plugin Claude Code
Bundles 17 skills · 575 tokens together
Scientific research brainstorming partner: survey the literature, find good problems, and shape concrete research ideas together.
Skill Codex
A visual guide for creating bitmap images in a consistent oil-painting and manga-ink style. It supports either complete explanatory images with labels or transparent character illustrations for use in another layout.
MCP server Claude CodeCodexCursor +2
MCP server "vs-debug" as configured in firish/claudecodevs. Launched with powershell -NoProfile -ExecutionPolicy Bypass -File .claude/vs-mcp-shim.ps1.
Skill Codex
Converts arbitrary source material into an executable structured Codex skill package. Use when the user provides text, notes, documents, PDFs, transcripts, videos, courses, articles, repositories, workflows, chat logs, or rough ideas and asks to turn them into a Skill, SKILL.md, skill scaffold, reusable agent…
Skill Claude CodeCodex
Reviews code changes for reuse, composition, codebase consistency, and slop. Use when asked to review PRs/diffs, check code reuse, composition, cleanliness, or whether code fits the codebase.
Skill Claude CodeCodex
A multilingual guide to growing a business-to-business software company, from finding product-market fit to reaching $10 million in annual recurring revenue. It covers product-led growth, sales-led growth, partnerships, contracts, sales materials, and measurement.
Skill Claude CodeCodex
A guidance skill that applies Paul Graham’s ideas and writing style to questions about startups, writing, products, and life choices. Paul Graham is a startup investor and essayist.
Plugin Claude Code
Bundles 1 skill · 12 tokens together
Indexed knowledge bases with command-line tools for agents.
Agent Claude Code
Use this agent when you need to test progressive DOM reading implementations by navigating to websites and extracting specific information. This agent works as a driver that receives instructions from a navigator AI about what website to visit and what data to extract, then attempts the extraction and reports back on…
bestagentkits/cloud-harness-mcp
Plugin Claude Code
Operate a private Cloud Harness MCP coding workspace with safe file, execution, Git, automation, and recovery workflows.
Plugin Claude Code
Bundles 1 skill, 2 commands · 118 tokens together
Persistent causal memory for Claude Code — decisions, outcomes, and lessons that survive compaction. Same-context counterfactuals (natural experiments), a falsifiable prediction ledger, and an activation skill that teaches when to recall and record.
MCP server Claude CodeCodexCursor +2
MCP server "reqwise-figma" as configured in hoangpm96/reqwise-figma-mcp. Launched with ./scripts/reqwise-mcp.sh.
Skill Claude CodeCodex
Diagnose a denied Tenuo call and make the legitimate call work with the smallest change to authority. Use when a call, test, or agent step fails with a Tenuo denial, monotonicity, proof-of-possession, chain, expiry, approval, or unknown-argument error. Do not use to design new authority from scratch (use…
Skill Codex
Deutschsprachige Recherche-Skill fuer aktuelle Themen, Personen, Produkte, Firmen, Repositories, Forschung und Trends in einem frei waehlbaren Zeitraum, standardmaessig in den letzten 30 Tagen. Nutze diese Skill, wenn ein Nutzer nach "letzte 30 Tage", "aktuell", "neueste Reaktionen", "was sagt die Community", "Trend"…
Skill Claude Code
A work-discipline protocol that makes Opus 4.8 (or any non-frontier model) operate at Fable-5-grade quality. Core idea — output quality = model capability x work discipline: spend extra orchestration to buy single-pass quality via six levers (plan gate, small-card execution, adversarial self-check, real-product…
BingHanOfUESTC/open_agent_team
Agent Claude Code
A team-coordination agent for running a complete research project from defining the question through literature review, coding, experiments, iteration, paper writing, and delivery.
Plugin Claude Code
Bundles 1 skill, 1 agent, 8 MCP servers · 46 tokens together
Production-readiness scanner for Next.js projects. Finds infrastructure gaps and suggests fixes.
Command Claude Code needs its repo
Create a Feature Track entry for a feature.
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: