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 agentmods add skills/lilithgames/a2wave/user-manual-syncnpx skills add LilithGames/a2wave --skill user-manual-syncgit clone --depth 1 https://github.com/LilithGames/a2waveWrote 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/lilithgames/a2wave/user-manual-sync)<a href="https://agentmods.dev/skills/lilithgames/a2wave/user-manual-sync"><img src="https://agentmods.dev/badge/skills/lilithgames/a2wave/user-manual-sync.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00071 | $0.02218 |
| Opus 5 | $0.00036 | $0.01109 |
| Sonnet 5 | $0.00014 | $0.00444 |
| Haiku 4.5 | $0.00007 | $0.00222 |
Grade A, and why
user-manual-sync 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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Manual (Wiki) Sync
Overview
a2wave 的「使用手册」是 Web 内置的 /wiki 页面,面向终端用户讲解平台功能怎么用。
内容是一组 Markdown,由 Vite 在构建时打包进前端 —— 没有后端 API,不读 docs/,不进运行镜像之外的任何源。
| 关注点 | 位置 |
|---|---|
| 章节正文(中文) | apps/web/src/content/manual/zh/NN-slug.md |
| 章节正文(英文,可选) | apps/web/src/content/manual/en/NN-slug.md |
| 加载/排序逻辑 | apps/web/src/lib/manual.ts |
| 页面组件(左目录+右正文) | apps/web/src/pages/wiki.tsx |
路由 /wiki /wiki/:slug |
apps/web/src/app.tsx |
| 侧栏入口 + 文案 | apps/web/src/components/layout.tsx、apps/web/src/locales/{zh,en}.json |
| E2E | e2e/tests/pages/wiki.spec.ts、e2e/utils/test-constants.ts |
区分:这里说的是「面向用户的产品使用手册」,不是开发者文档(
docs/)、也不是平台 Skill 功能。
当前结构(v2): 共 15 章,落地页(/wiki 首屏)是 01-overview.md(slug overview,标题「概览与导航」),含「按场景 / 按角色速查」两张表;其后是 getting-started、concepts,各功能章,末尾 faq、glossary。读者定位为「终端用户 + 集成开发者」,触发方式等章含真实调用示例。
When to Use
新功能开发完成 / 改动触及用户可感知行为时,必须走一遍本 skill 判断手册是否要更新:
- 新增页面、路由、导航项
- 新增或改变某项能力的用法(Agent / Provider / MCP / Skill / 代码源 / 知识库 / 运行记录)
- 新增或调整触发方式、外部集成、鉴权方式
- 改变面向用户的操作流程、术语、限制(铁律)
仅内部重构、不影响用户用法时,可不更新,但要在 PR/commit 里说明「无用户可见变更,手册无需更新」。
Core Workflow
判断影响范围 → 选择动作(改/增章节) → 遵守命名与交叉链接约定 → 校验 → 同步 E2E
1. 判断该改哪一章
对照现有章节(apps/web/src/content/manual/zh/ 下 01..NN)。功能属于已有主题就改对应文件;是全新主题就新增一章。
2A. 改现有章节(最常见)
直接编辑对应 zh/NN-slug.md,用面向用户的口吻补充「这是什么 / 怎么用 / 注意什么」。不要写实现细节、文件路径、内部 API。
2B. 新增章节
- 在
apps/web/src/content/manual/zh/新建NN-slug.md:NN(数字前缀)决定目录排序;要插在中间用如025-xxx.md(Number('025')=25)。slug即路由,访问地址为/wiki/<slug>,用小写连字符。- 第一行必须是一级标题
# 标题,loader 取它作为目录项名称。
- 不需要改
manual.ts/app.tsx/layout.tsx/ i18n ——import.meta.glob在构建时自动发现新文件。 - 同步落地页:在
01-overview.md的「按场景速查 / 按角色速查」表里补一行,链接到新章节(/wiki/<slug>),否则新功能在总览页不可发现。
3. 约定
- 交叉链接用站内路径:
[成员管理](/wiki/members),slug 与目标文件名后半段一致。MarkdownContent会把/开头(但/api/除外)的链接渲染成 React Router<Link>原地跳转;/api/*(服务端路由,如/api/docs)与外部http(s)://走普通<a>新开标签——所以站内一律写/wiki/<slug>,别写成完整 URL;指向/api/docs等服务端地址直接写该路径即可。 - 口吻:终端用户视角,简洁、可操作;善用表格与有序步骤。
- 硬约束相关(铁律,以及「飞书一 App 一单连接」这类实现约束)若涉及,务必准确转述,可参考
AGENTS.md的产品铁律与docs/PRODUCT.md,但重写为用户口吻,不要直接粘贴开发文档。 - 提示卡片(callout):需要强调时用 GFM alert 语法,
MarkdownContent会渲染成彩色卡片:> [!NOTE](说明/蓝)、> [!TIP](建议/绿)、> [!IMPORTANT](重要/主色)、> [!WARNING](注意/琥珀)、> [!CAUTION](警告/红);标记单独一行,内容写在其后的>行。普通引用仍用不带标记的>。 - 标题锚点:H2/H3 自动生成 id 与悬停锚点;章节有 ≥3 个 H2 时,正文顶部会自动出现「本页大纲」(直接读渲染后 DOM 的 h2[id],无需另维护)。无需手动维护,正常写
##/###即可。 - 作用域:上述「站内链接原地跳转 / callout / 标题锚点」仅在 wiki 生效——
wiki.tsx给MarkdownContent传了wikiprop。其它复用点(changelog、run/test 抽屉的 agent 输出)默认关闭这些增强,保持普通<a target=_blank>、无 callout/锚点。在别处复用MarkdownContent时按需自行决定是否传wiki。 - 英文:有精力就在
en/放同名NN-slug.md(slug 与 zh 一致,便于切语言保持同章节);没有则留空,运行时自动回退中文。
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.
- 3d ago First seen · 100 lines · 71 tokens per session scan A 5f2ad831ae61
user-manual-sync is a skill published in the GitHub repository LilithGames/a2wave (24 stars, last pushed 6d ago), licensed Apache-2.0. It adds 71 tokens to every session and 2,218 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
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.
with-frontmatter
Help an agent inspect a failed trace run, identify likely failure layers, and produce a short audit note.
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
lyria
Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before calling OpenMontage googlemusic, designing Lyria 3 Clip or Pro prompts, using image-to-music or custom lyrics, choosing between Lyria 3 and Lyria RealTime, diagnosing Google music-generation failures, or preparing…
comfyui
Use when working with ComfyUI workflows in OpenMontage, including comfyuiimage/comfyuivideo/comfyuimusic, custom workflowjson/workflowpath inputs, outputnode selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.
dashscope
DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.