Borrowing it
Nothing to install: this file belongs to Peiiii/nextclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Peiiii/nextclaw/master/.agents/wiki/skills/operations/nextclaw-desktop-release/SKILL.mdgit 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/nextclaw-desktop-release)<a href="https://agentmods.dev/skills/peiiii/nextclaw/nextclaw-desktop-release"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/nextclaw-desktop-release/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/nextclaw-desktop-release"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/nextclaw-desktop-release.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 | $0.00025 | $0.00748 |
| Opus 5.5 | $0.00010 | $0.00299 |
| Sonnet 5.5 | $0.00005 | $0.00150 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade A, and why
nextclaw-desktop-release 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 2mo 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.
What it actually says
NextClaw Desktop Release
入口
按当前场景只读取一项：
- 打包、public key、launcher floor、产物形状：打包合同。
- 发布、GitHub assets、update channel、Pages/APT：发布自动化。
- Electron runtime、GUI/API、Windows installer、真实 profile 冒烟：运行冒烟。
- 已有 tag/run、部分发布、网络/Pages/CI 失败：发布恢复。
- 无签名 macOS/Windows 交付：Unsigned handoff。
不要一次读取全部 reference；失败分类改变后再切换分支。
永久合同
- 发布 channel 必须显式确认；不得因“发布”、失败恢复、Draft 或版本后缀自行选择 beta。仅用户明确要求 beta/preview，或任务已在 beta 链路，才可运行
release:desktop:beta。 v<runtime>-desktop.<n>是 stable 构建序号，非 beta/prerelease；-desktop-beta.<n>才是 beta。stable Release 必须isPrerelease=false；Draft/recovery 沿用既有 channel 与 release identity。- 原始 electron-builder 输出不是可发布产物；安装包必须包含更新验签 public key，并能验证目标 manifest。
- 以 Electron 内置 Node 为发布运行时事实，不能用开发机 ambient Node 代替。
minimumLauncherVersion来自apps/desktop/desktop-launcher-compatibility.json，只有真实 launcher 合同破坏才提高。- tag/release 只是触发；workflow、assets、channel、release notes URL、适用 Pages/APT 全闭合才完成。
- 隔离 worktree 发布仍须安全回流本地目标分支，不覆盖活跃 WIP。
- Desktop 不授权 NPM publish；stable 只消费已验证的
nextclawstable identity。存在未发布 runtime 语义时停止，转入常规 stable/全平台发布。 /发布NextClaw桌面版成功报告DESKTOP_READY；全平台只在NEXTCLAW_STABLE_READY后进入本 owner，desktop 失败不得重发 NPM/runtime。/发布NextClaw全平台版由 GitHubrelease.yml target=all调用；AI/Delivery 仅触发、监控父 workflow。Standalone Desktop 仅用于窄发布/恢复。DESKTOP_READY、ALL_PLATFORMS_READY只关闭子目标；active contract 下向 lifecycle 返回 stable ID 的acceptance_updates、parent_status，版本/tag/artifact 不能完成 parent-goal。
默认入口
- 本地包合同：
PATH=/opt/homebrew/bin:$PATH pnpm desktop:package:verify - 人工可点击交付：
PATH=/opt/homebrew/bin:$PATH pnpm desktop:package:handoff:verify - Beta：
pnpm release:desktop:beta - Stable：
pnpm release:desktop:stable
最终报告精确 artifact、launcher/runtime 版本、workflow/release URL、public manifest 状态和未闭合项。
What ships with it
5 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.
- 2mo ago First seen · 42 lines · 25 tokens per session scan A 3682525ba457
nextclaw-desktop-release is a skill published in the GitHub repository Peiiii/nextclaw (263 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 748 once invoked, about $0.0001 per session on Opus 5.5. 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.
nextclaw-desktop-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nextclaw-desktop-releasePeiiii/nextclaw | Skill | 263 | yesterday | MIT | A | 25 | Claude Code, Codex |
| graincrawlvincentkoc/dotskills | Skill | 111 | yesterday | MIT | A | 47 | Codex |
| crawlkitvincentkoc/dotskills | Skill | 111 | yesterday | MIT | A | 30 | Codex |
| aetox-deployMikedev115/Aetox | Skill | 48 | 29d ago | none | A | 102 | Claude Code, Codex |
| github-repo-managementmoltis-org/moltis | Skill | 2.9k | 14d ago | MIT | A | 47 | Claude Code, Codex |
| publish-siteandrooAGI/starnet | Skill | 1.7k | 6d ago | MIT | A | 50 | Claude Code, Codex |
| updater_guidesiddsachar/row-bot | Skill | 1.7k | yesterday | Apache-2.0 | A | 22 | Claude Code, Codex |