# open-agent-hub: a set by guanyang

The guanyang/open-agent-hub repository on GitHub: 14 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.

14 cards

- HTML: https://affpapa.org/en/nevibecode/by/guanyang/open-agent-hub
- Instructions for agents: https://affpapa.org/en/nevibecode/agents.md

- [filesystem-context](https://affpapa.org/en/nevibecode/skills/filesystem-context.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 608 installs — filesystem-context — a skill that shows an agent how to keep context in files: scratchpads, offloaded tool output, plans and handoff between sub-agents.
- [memory-systems](https://affpapa.org/en/nevibecode/skills/memory-systems.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 413 installs — memory-systems — a skill for picking an agent memory architecture: storage layers, frameworks like Mem0 and Zep, retrieval strategies and benchmarks.
- [advanced-evaluation](https://affpapa.org/en/nevibecode/skills/advanced-evaluation.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 303 installs — advanced-evaluation — a skill for building LLM evaluation systems using LLMs as judges: direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation.
- [project-development](https://affpapa.org/en/nevibecode/skills/guanyang-project-development.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 301 installs — project-development guides architectural decisions for LLM systems: evaluating task fit, shaping multi-stage processing pipelines, and persisting pipeline state on disk.
- [tool-design](https://affpapa.org/en/nevibecode/skills/tool-design.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 299 installs — tool-design — a skill for building the tool interface layer in agent systems.
- [evaluation](https://affpapa.org/en/nevibecode/skills/evaluation.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 293 installs — evaluation — a skill for testing agent systems with deterministic checks, regression suites, rubrics, quality gates, and production monitoring.
- [context-degradation](https://affpapa.org/en/nevibecode/skills/context-degradation.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 290 installs — A skill for detecting and fixing context degradation: lost-in-middle failures, data poisoning, source conflicts, and task confusion.
- [bdi-mental-states](https://affpapa.org/en/nevibecode/skills/bdi-mental-states.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 287 installs — bdi-mental-states is a skill that converts RDF context into agent beliefs, desires, and intentions to formalize mental states and explain decisions.
- [hosted-agents](https://affpapa.org/en/nevibecode/skills/hosted-agents.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 286 installs — The hosted-agents skill covers remote infrastructure for background agents, including sandboxes, warm pools, persistent sessions, and parallel sub-agents.
- [latent-briefing](https://affpapa.org/en/nevibecode/skills/latent-briefing.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 252 installs — The latent-briefing skill explains task-guided KV cache compaction for passing an orchestrator’s state to a worker.
- [baoyu-imagine](https://affpapa.org/en/nevibecode/skills/baoyu-imagine.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 241 installs — baoyu-imagine — a skill for generating images via OpenAI, Google, DashScope and eight other providers.
- [harness-engineering](https://affpapa.org/en/nevibecode/skills/guanyang-harness-engineering.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 204 installs — harness-engineering is a skill for Claude Code and other platforms that designs an autonomous agent's control system: editable surfaces, feedback, logs, and approval points.
- [self-improvement-loops](https://affpapa.org/en/nevibecode/skills/self-improvement-loops.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 194 installs — A skill for Claude Code, Codex, Cursor, GitHub Copilot, and Gemini CLI that teaches an agent to design recursive self-improvement (RSI) loops.
- [long-horizon-prompting](https://affpapa.org/en/nevibecode/skills/long-horizon-prompting.md) — skill · guanyang · Claude Code, Codex, Cursor +5 · 188 installs — long-horizon-prompting is a skill for designing and checking prompts for long-running agents and multi-agent orchestrations, with explicit success criteria and failure modes.

## Narrow this list
Parameters: `?platform=<claude-code|codex|cursor|copilot|gemini-cli|windsurf|…>`, `&topic=<…>`, `&sort=installs|stars|new|updated` — values in https://affpapa.org/en/nevibecode/agents.md

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
