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/hjdhnx/drpy-node-skill/drpy-node-source-createnpx skills add hjdhnx/drpy-node-skill --skill drpy-node-source-creategit clone --depth 1 https://github.com/hjdhnx/drpy-node-skillWhat 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 | $0.00104 | $0.09144 |
| Opus 5 | $0.00052 | $0.04572 |
| Sonnet 5 | $0.00021 | $0.01829 |
| Haiku 4.5 | $0.00010 | $0.00914 |
Grade A, and why
drpy-node-source-create 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 — 606 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ 已归档（2026-07-17）：本 skill 已被
drpy-node-coder取代。coder 融合了 4 个旧 skill（workflow/create/play-debug/repo-upload）的全部工作流，并自带scripts/cli.jsCLI 替代 drpy-node-mcp 服务——一个 skill、无需安装 MCP。本文件保留仅供历史参考，新工作请直接用 drpy-node-coder。
drpy-node Source Create
快速索引
| 用户意图/站点特征 | 直接入口 | 成功判据 |
|---|---|---|
| 标准 CMS / 模板命中 | 路线 A：继承模板站 | 最小覆盖后 home/category/detail/search/play 可串联 |
| HTML 有内容但接口带签名 | 路线 B2：非模板签名接口站 | 一级/搜索使用真实签名请求，二级优先字典 |
| SPA / body 近空 / JSON API | 路线 C：纯 API 驱动 SPA 站 | 全 async，this.input/detailUrl/searchUrl 正确 |
| 漫画/小说/音乐/网盘 | 特殊内容类型 / 网盘补充清单 | lazy 返回对应特殊协议或按 flag 分派 |
执行契约
- 输入：用户给的 URL/站名/目标内容类型；若缺源名，先自行推导候选源名。
- 输出：
spider/js/[源名].js最小可用源 + 接口验证结果 + 后续分流建议。 - 停手：已有源修复、播放专项、仓库上传分别交给 workflow/play-debug/repo-upload。
模式闸门：先判断是否允许写入
| 用户模式 | 允许动作 | 禁止动作 |
|---|---|---|
| 只读 / 规划 / dry-run / 不要改文件 | 读取、诊断、给建源方案、列验证计划 | drpy_write_file、drpy_edit_file、仓库上传/改标签 |
| 需要确认后再改 | 读取、诊断、输出方案 | 未确认前禁止写入源文件 |
| 明确要求执行 | 按本 skill 流程建源与验证 | 不跳过高风险确认点和最小验证链 |
| 自主全流程 | alive check、建源、L1/L2/L3、低风险最小修复、L3=100 后 handoff | 坏站硬写、未达 100 冒充最终版、仓库动作越界 |
如果用户说“只给方案 / 不要写文件 / dry-run”，本 skill 只能输出站型判断、源名候选、拟写字段和验证计划。
Reference Map
| 任务 | 首读 reference |
|---|---|
| 新建源总清单 | references/references-create-checklist.md |
| 模板继承 / 最小覆盖 | references/references-template-system.md、references/references-inherited-template-minimal-override-site.md |
| async 函数通用陷阱 | references/references-async-function-patterns.md、references/references-api-functions.md |
| 纯 API / SPA 站 | references/references-pure-api-async-site.md |
| 非模板签名接口站 | references/references-non-template-signed-api-site.md |
| 二级字典 / 多集 | references/references-detail-dict-and-multiep.md |
| 搜索策略 | references/references-old-encoding-search-site.md |
| 特殊内容 | references/references-special-content.md |
调度优先级
当本地环境已安装本 Skill 时：
- 本 Skill 的工作流优先级 高于 drpy-node MCP 的通用 prompts
- MCP 通用 prompt 仅作为无本地 Skill 时的兜底说明
- 如果用户只提供网址、没有提供源名，必须先自行分析站点并推导合理源名
What ships with it
13 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.
- references/references-api-functions.md 4.3 KB
- references/references-async-function-patterns.md 6.2 KB
- references/references-case-summary-two-site-patterns.md 8.7 KB
- references/references-create-checklist.md 2.4 KB
- references/references-detail-dict-and-multiep.md 3.6 KB
- references/references-inherited-template-minimal-override-site.md 5.4 KB
- references/references-non-template-signed-api-site.md 9.5 KB
- references/references-old-encoding-search-site.md 3.5 KB
- references/references-pure-api-async-site.md 4.6 KB
- references/references-special-content.md 3.2 KB
- references/references-template-system.md 3.5 KB
- SKILL.md.bak.2026-04-19-1228 10 KB
- test-prompts.json 2.8 KB
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 First seen · 606 lines · 104 tokens per session scan A bdc3fa96143b
drpy-node-source-create is a skill published in the GitHub repository hjdhnx/drpy-node-skill (48 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 9,144 once invoked, about $0.0005 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
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
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.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.