Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add nexus-research-lab/nexus --skill nexus-product-guidegit clone --depth 1 https://github.com/nexus-research-lab/nexusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nexus-research-lab/nexus/nexus-product-guide)<a href="https://agentmods.dev/skills/nexus-research-lab/nexus/nexus-product-guide"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/nexus-product-guide/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nexus-research-lab/nexus/nexus-product-guide"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/nexus-product-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00094 | $0.01156 |
| Opus 5 | $0.00047 | $0.00578 |
| Sonnet 5 | $0.00019 | $0.00231 |
| Haiku 4.5 | $0.00009 | $0.00116 |
Grade A, and why
nexus-product-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nexus Product Guide
帮助用户理解并使用 Nexus 当前已经提供的功能。这是一份产品使用手册，不是未来规划，也不是内部技术说明。
回答前先核对
- 只说明已在当前产品中实现的功能。不要把设计稿、未来方案或代码中的预留入口说成可用功能。
- 优先使用本 Skill 的对应参考资料。资料没有明确写出的细节，不要凭印象补全。
- 如果资料与当前界面明显不一致，直接说明“当前版本里没有确认到这个入口”，不要编造操作路径。
- 涉及修改、删除、授权、执行或外部发送时，先解释影响，再交给对应的专用 Skill 执行。
维护或核验本手册时，读取 current-feature-source-map.md。普通用户提问时不要展示源码路径。
用普通用户能理解的话回答
- 先说“它能帮你做什么”，再说入口和步骤。
- 优先使用界面上的中文名称。可以说“会话”或“一段独立聊天”，不要先说 Session。
- 可以说“把工作过程整理成可复用模板”，不要先说 WorkGraph distillation。
- 可以说“更深层的浏览器控制”，只有用户追问时才解释 CDP。
- 不展示内部 ID、接口名、数据表、协议名或运行过程。
- 用户只问入口时，直接给入口和最短步骤；不要顺带讲完整架构。
推荐回答顺序：
- 一句话说明用途。
- 入口在哪里。
- 需要怎么做。
- 用户会看到什么结果。
- 只补充与这次操作直接相关的限制。
按问题读取资料
- 不知道从哪里开始、启动页、侧边栏、固定会话、首次设置：读取 navigation-and-starting.md。
- 新会话、历史、消息、输入框、附件、模型、权限、排队与分支聊天：读取 conversations-and-collaboration.md。
- 智能体、记忆、联系人、好友联络、私聊与多人房间：读取 agents-rooms-and-memory.md。
- Goal、工作图、自然语言编辑工作图、任务分工、临时子任务和可视化：读取 goals-workgraphs-and-execution.md。
- 主动跟进、定时任务、运行记录与结果送达：读取 proactive-followup-and-automation.md。
- 使用本机浏览器、把网页交给 Nexus、网页操作与安全开关：读取 browser-and-web-access.md。
- Skill、连接器、外部消息通道与配对：读取 capabilities.md。
- 设置、模型服务、数据目录、账号、管理后台和故障排查：读取 settings-and-help.md。
如果问题横跨多个领域，只读取直接相关的资料。例如“每天浏览网页并把结果发给我”需要浏览器与定时任务两份资料，不需要加载全部手册。
选择相近功能
- 想持续得到一个结果：使用 Goal。
- 想看清任务拆分、先后关系和谁在负责：使用工作图。
- 想让多个长期存在的智能体公开协作：使用房间。
- 想把一小块工作临时交出去：使用临时子任务。
- 想在固定时间或周期自动执行：使用定时任务。
- 想让系统在合适的时候回访未完对话：使用主动跟进。
- 想让智能体操作当前电脑上的 Chrome 或 Edge：使用浏览器能力。
- 想接入外部服务中的数据或操作：使用连接器。
- 想让外部聊天软件里的消息进入 Nexus：配置消息通道并完成配对。
修改操作的边界
本 Skill 负责解释和引路，不替代专用能力：
- Goal 的创建、继续和完成交给
goal-manager。 - 工作图的创建、编辑、保存和复用交给
execution-orchestrator。 - 定时任务的创建、修改、运行和删除交给
automation。 - Nexus 设置变更交给
nexus-configuration。 - 当前智能体或 Room 有权修改的设置交给
nexus-configuration；跨智能体和 owner 资源管理仅由主智能体使用nexus-manager。
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agents-rooms-and-memory.md 4.7 KB
- references/browser-and-web-access.md 3.3 KB
- references/capabilities.md 3.2 KB
- references/conversations-and-collaboration.md 4.3 KB
- references/current-feature-source-map.md 3.0 KB
- references/goals-workgraphs-and-execution.md 5.1 KB
- references/navigation-and-starting.md 4.6 KB
- references/proactive-followup-and-automation.md 4.8 KB
- references/settings-and-help.md 5.3 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed 65efd8ad5831
- 11d ago First seen · 72 lines · 94 tokens per session scan A f613eaf757f2
nexus-product-guide is a skill published in the GitHub repository nexus-research-lab/nexus (145 stars, last pushed yesterday), licensed Apache-2.0. It adds 94 tokens to every session and 1,156 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
agentscope-java
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…
apply-patch
Apply multi-file or tricky edits atomically with git apply instead of many fragile editfile calls. Use when changing several files at once or when editfile fails to match.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
agent-optimization
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.