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-configurationgit 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-configuration)<a href="https://agentmods.dev/skills/nexus-research-lab/nexus/nexus-configuration"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/nexus-configuration/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-configuration"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/nexus-configuration.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 | $0.00058 | $0.01080 |
| Opus 5 | $0.00029 | $0.00540 |
| Sonnet 5 | $0.00012 | $0.00216 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
nexus-configuration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nexus 配置
配置命令使用宿主注入的 NEXUSCFG_COMMAND_PATH;示例中的 nexuscfg 只代表该入口。宿主绑定当前 Agent、DM/Room round 与 owner scope,服务端返回真实 owner_main|agent_self|room_host|room_member authority。不要声明、切换或覆盖 identity/scope,也不要使用 owner 控制面、数据库或配置文件替代本能力。
固定生命周期
所有 mutation 固定走 inspect → plan → apply → verify。
-
只 inspect 相关 domain;排障时加
--verify:"$NEXUSCFG_COMMAND_PATH" --json inspect --domain agents --verifyPowerShell 使用
& "${env:NEXUSCFG_COMMAND_PATH}" ...,不要混用 shell 变量语法。 -
以顶层
inspection中的authority、access.allowed_operations、definition.operations、revision与 checks 为准。不要根据 Skill 猜 operation、target 或 input;需要角色与 domain 分流时读取 references/roles-and-domains.md。 -
mutation 先用同一 domain/operation/target/input 执行 plan。输入必须是一个不含秘密的 JSON object:
"$NEXUSCFG_COMMAND_PATH" --json plan --domain agents --operation update_self_profile --input '{"name":"新名称"}' -
核对 plan 的 normalized change、summary、risk、runtime effect、
current_revision、plan_digest与 confirmation/secret slots。requires_confirmation=true时等待用户针对该 plan 明确同意;只有随后 apply 才加--confirm。 -
apply 保持同一 change,携带 plan revision 与稳定 request ID;revision 冲突时回到 inspect/plan,不覆盖新状态:
"$NEXUSCFG_COMMAND_PATH" --json apply --domain agents --operation update_self_profile --input '{"name":"新名称"}' --expected-revision '<revision>' --request-id 'config-agent-profile-UNIQUE' -
读取顶层
result的写后 checks;不确定时重新 inspect--verify或用history --domain '<domain>'核对。数据库已写入不等于 runtime 已生效,以返回的 runtime effect 和验证结果为准。
秘密与权限
- 不向用户索取或在聊天、命令参数、文件、日志中写入 token、密码、私有 header、授权码或密钥。Agent 永不使用
--secrets-stdin;members.create使用{"$secret":"member-password"}占位,apply 由宿主确认卡片收集密码;其他域出现 secret slot 时,引导用户在 Settings 或人工终端完成。 - Connector OAuth/device 与 Channel 扫码、验证码继续使用对应专用授权流程,不把凭据塞进通用 config input。
- permission denied 表示当前 Agent/DM/Room 没有该 operation。报告真实边界,不换 target、不伪造身份,也不传隐藏的
--scope-user-id/--global-scope。 host只读;部署环境、启动参数和桌面状态根通过部署或原生桌面控制面修改。
What ships with it
2 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.
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.
- 2d ago Changed · +4 lines 56e709f66437
- 3d ago Changed · +4 lines · +5 tokens per session bea4feefb69e
- 12d ago First seen · 49 lines · 53 tokens per session scan A 80c0447222ff
nexus-configuration is a skill published in the GitHub repository nexus-research-lab/nexus (145 stars, last pushed yesterday), licensed Apache-2.0. It adds 58 tokens to every session and 1,080 once invoked, about $0.0003 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.
web-design
Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.
agent-optimization
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.