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/flanchanxwo/pixiv-cli/pixiv-cli-docsnpx skills add FlanChanXwO/pixiv-cli --skill pixiv-cli-docsgit clone --depth 1 https://github.com/FlanChanXwO/pixiv-cliWrote 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/flanchanxwo/pixiv-cli/pixiv-cli-docs)<a href="https://agentmods.dev/skills/flanchanxwo/pixiv-cli/pixiv-cli-docs"><img src="https://agentmods.dev/badge/skills/flanchanxwo/pixiv-cli/pixiv-cli-docs.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 | $0.00058 | $0.01310 |
| Opus 5 | $0.00029 | $0.00655 |
| Sonnet 5 | $0.00012 | $0.00262 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
pixiv-cli-docs 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 5d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pixiv-cli Docs
新增、修改或审查本仓库文档。文件职责与路由表以本文件的 文档路由 章节为准。
流程
-
读取
AGENTS.md、本 SKILL 和目标文件，确定内容应落在哪个 locale、maintainer 文件、README 或贡献者入口。 -
按目标 locale 写作；命令、路径、包名、schema field、error code 和 code-id 保持英文。更新 public contract 时先改 canonical English，再同步已有 Simplified Chinese 语义。
-
检查命令、参数、输出、安全边界和代码实现是否一致；涉及 CLI/MCP/SDK/config/安装或 release 行为时，同时检查对应测试、
AGENTS.md、PR 模板和产品skills/pixiv-cli/。 -
同一规则只写一处，其他位置用链接路由，不复制大段内容；历史计划、验收报告和 release evidence 不因当前流程变化而改写。
-
完成后检查相对链接、locale 导航、Markdown fence、文件存在性和语义一致性，并运行：
go test ./scripts/tests/documentation -count=1 git diff --check
文档路由
拿不准写到哪里时，先看读者。用户需要查到的接口放在 locale 文档里；只有维护代码的人会用到的内容，放进 docs/en/maintainers/（英文基准）和 docs/zh-CN/maintainers/（中文）。
每个位置管什么
| 位置 | 适合放的内容 |
|---|---|
README.md、README.zh-CN.md |
项目介绍、安装、快速开始和最先要看到的安全提醒 |
docs/en/ |
英文公开接口，也是接口定义的基准 |
docs/zh-CN/ |
与英文行为一致的中文说明 |
docs/en/maintainers/、docs/zh-CN/maintainers/ |
架构、开发流程、能力边界和协作规则 |
docs/index.md |
英文文档站入口 |
docs/index-zh-CN.md |
中文文档站入口 |
两份 CONTRIBUTING |
提交 Issue 和 PR 前需要知道的事 |
changelog/ |
每个版本真正发生了什么 |
AGENTS.md |
agent 开工前要读的短规则 |
.agents/skills/ |
可以照着执行的项目流程 |
[!IMPORTANT] 同一条规则只留一份。其他地方给链接，不要换个说法再抄一遍。
两种语言怎么同步
- locale 目录使用 BCP 47 tag，目前是
en和zh-CN。 - 公开接口先确认英文定义，再同步中文。中文不必逐句直译，但不能改掉命令、参数、schema、安全语义或限制。
- 暂时没有翻译时，从
docs/index.md链到英文。不要复制一份英文内容再把它放进中文目录。 - code、command、flag、path、package、schema field、error code 和 wire value 保持英文。
找到该同步的文档
| 变化 | 一起更新 |
|---|---|
| 项目定位、安装、快速开始 | 两份 README |
| CLI command、flag、账号、配置、环境变量或输出 | 两份 CLI reference |
| SDK API、model、error | 两份 SDK 文档 |
| MCP tool、schema、wire 语义 | 两份 MCP tools 文档 |
| 包职责或依赖方向 | docs/en/maintainers/architecture.md、docs/zh-CN/maintainers/architecture.md |
| 测试、构建或发布流程 | docs/en/maintainers/development.md、docs/zh-CN/maintainers/development.md |
| 贡献方式 | 两份 CONTRIBUTING |
| 领域术语 | docs/zh-CN/maintainers/architecture.md 的「领域词汇」 |
[!NOTE] 普通 PR 不写版本说明。准备发布时先审计 tag 范围，再直接写
changelog/vX.Y.Z/en.md和zh-CN.md。纯内部改动也不能漏掉，统一放在Maintenance。
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.
- 5d ago First seen · 89 lines · 58 tokens per session scan A af07fcfe8e69
pixiv-cli-docs is a skill published in the GitHub repository FlanChanXwO/pixiv-cli (130 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 1,310 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
conventional-commit
Workflow for generating conventional commit messages following the Conventional Commits specification. MUST be invoked every time a commit is created. Guides construction of standardized commit messages with correct type, scope, description, body, and footer.
segment-create
Full scaffolding workflow for creating a new Oh My Posh segment. Invoke when asked to add a new segment: generates the Go source, registers the type, creates documentation, updates the sidebar and JSON schema.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
release-notes
Draft concise release notes.
update-release-note
Use the GitHub CLI to update a GitHub release note while preserving the style of previous release notes.
octo-mail
OCTO Agent Mail operations for reading, searching, policy-aware sending, preparing drafts, and checking delivery status exclusively through octo-cli.