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 Peiiii/nextclaw --skill service-app-creatorgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/service-app-creator)<a href="https://agentmods.dev/skills/peiiii/nextclaw/service-app-creator"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/service-app-creator/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/peiiii/nextclaw/service-app-creator"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/service-app-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00074 | $0.01513 |
| Opus 5 | $0.00037 | $0.00757 |
| Sonnet 5 | $0.00015 | $0.00303 |
| Haiku 4.5 | $0.00007 | $0.00151 |
Grade A, and why
service-app-creator 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 6d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NextClaw Service App Creator
本 skill 是 Service 运行形态、service-app.json、Service Action、risk 和验证入口的唯一 owner。若用户表达的是“做一个完整 NextClaw 小应用”,先由 nextclaw-app-creator 判断是否还需要 Panel;本 skill 不拥有 Panel UI 或 bridge 字段。
不要再把所有 schema v2 Service 都等同于 command/args + MCP stdio + native-process。当前 NextClaw 同时支持:
- Portable WASI Service:
protocol: "wasi-component",由 NextClaw 随产品提供的 runner 执行 Rust/WASI Component; - native-process Service:
protocol: "mcp",由宿主启动 Node、Python、系统命令或其它本地进程。
先选择运行形态
优先 Portable WASI
满足以下条件时选择 Portable:
- Service 可以表达为明确的 Action,或确实需要 Resident / Provider 生命周期;
- KV、SQLite、受授权文件、允许域名、密钥槽位、Provider、model slot 或 agent slot 能覆盖需求;
- 希望同一份
.napp在支持的平台运行,且不把用户完整宿主权限交给 Guest; - 应用面向分发、安装或长期维护,安全能力边界比快速脚本更重要。
选择后必须读取 references/portable-wasi-service-app.md,不能凭本入口猜 WIT、manifest、生命周期或构建命令。
仅在真实需要时选择 native-process
以下情况选择 native-process:
- 必须直接运行 Node/Python/系统程序、平台 SDK、驱动、socket 或外部守护进程;
- 依赖无法由当前 Portable Runtime 能力合同承接;
- 用户明确只要一个快速、本机、无需 Rust 工具链的 Service helper,并接受宿主用户权限边界;
- 正在维护现有 workspace
service-apps/<id>/MCP Service。
选择后必须读取 references/native-process-service-app.md。不能仅因开发机暂时缺少 Rust,就把需要可移植或受限能力边界的应用静默降级为宿主进程。
Rust 工具链边界
必须准确区分创作者与最终用户:
- 在本机创建并构建 Rust/WASI Guest,需要
cargo、rustc和wasm32-wasip2;先运行nextclaw app doctor --profile wasi。 - 安装和运行已经构建好的 Portable
.napp不要求最终用户安装 Rust、Cargo、Wasmtime 或系统 Node。WebAssembly Component 已在包内,runner 由 NextClaw 提供。 - 纯 Panel App 和 native-process Service 不因 Portable Runtime 的存在而需要 Rust。
如果用户目标明确要求 Portable,但工具链检查失败,保留已创建的源码和失败证据,说明缺少的开发依赖;未经授权不要自动安装 Rust,也不要把未构建源码说成可交付应用。
两种交付边界
完整或可发布的 schema v2 Mini App
Service 应位于应用包根:
my-app/
├── manifest.json
├── marketplace.json
├── panels/<panel-id>.panel/ # 可选
├── service-components/<service-id>/
│ └── service-app.json
└── ...runtime-specific sources and artifacts
根 manifest.json.components 是组件归属的事实源。Portable 使用 runtime.profile: wasi;native-process 使用 runtime.profile: native-process。适用的 build/check/test/dev/call/pack/validate-publish 命令都从包根运行。
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.
- 6d ago Changed · -65 lines · +5 tokens per session eea650750f80
- 10d ago First seen · 162 lines · 69 tokens per session scan A b2c2b72b8a30
service-app-creator is a skill published in the GitHub repository Peiiii/nextclaw (256 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 1,513 once invoked, about $0.0004 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
technical-integrations
Hunt existing integration patterns and design vendor/framework-agnostic API, RFC, SDK, and integration plans for new external vendor integrations.
claude-api
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports anthropic/@anthropic-ai/sdk/claudeagentsdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports openai/other AI SDK, general programming, or ML/data-science tasks.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
synthetic-parallel-reasoning
Automates Protocol 75 v4.0, forcing 4 parallel external API calls (Domain Expert, Adversarial Skeptic, Cross-Domain Pattern Matcher, Zero-Point First Principles) with an Adversarial Convergence Gate. The 'Einstein Protocol' application.
openclaw-github-dedupe
Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions. Supports autonomous mode for provided-link-only closeout, merge/fix follow-through, changelog, and post-merge issue/PR cleanup.
openclaw-pr-batch-sweep
Select, review, repair, validate, and land batches of up to 20 low-risk OpenClaw contributor pull requests using Vincent's maintainer preferences and bounded sub-agent lanes. Use for "next 20", broad contributor PR sweeps, merge-candidate mining, or continued PR-batch work where drafts, maintainer work, trivial…