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-codernpx skills add hjdhnx/drpy-node-skill --skill drpy-node-codergit 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 | $0.00168 | $0.03672 |
| Opus 5 | $0.00084 | $0.01836 |
| Sonnet 5 | $0.00034 | $0.00734 |
| Haiku 4.5 | $0.00017 | $0.00367 |
Grade A, and why
drpy-node-coder scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 多引擎源(php/hipy/cat) | 路线 E | `references-multi-engine-sources.md` | `fetch` + curl `?do=py/php/cat&extend=`（**必须带 extend**；hipy 改源需 kill daemon）| How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
drpy-node Coder
drpy-node 爬虫源的建、修、测、放、传全链路一体化 skill。自带 CLI 工具，无需安装 MCP 服务。
便携性说明（先读）
- ✅ 无需 MCP：所有能力内置在
scripts/cli.js，AI 直接node scripts/cli.js <命令>调用。 - ✅ 零 npm 依赖：无需
npm install。localDsCore测试引擎 bundle（14M，全内联 cheerio/axios/drpyS/htmlParser）+ sqlite + 编码 wasm 自带于scripts/vendor/。 - ⚠️ 前置：本机需有
drpy-node项目（CLI 复用其req/pdfa/drpyS/DS解密 源码模块——这些互相 import、非 bundle，搬不动；但localDsCore已内联进vendor/，test/evaluate不再依赖drpy-node-bundle目录）。 - 首次使用：
cd scripts && node cli.js setup <drpy-node-绝对路径> && node cli.js doctor。 - 调用范式：
node scripts/cli.js [--root <drpy-node路径>] <命令> [参数] [--flags]。所有命令输出 JSON：成功{"ok":true,"data":...}、失败{"ok":false,"error":...}。 - 输出读取：少数命令（test/evaluate）首次加载测试引擎时 stdout 可能有一次初始化日志，业务 JSON 始终是 stdout 最后一行，按最后一行
{解析。
总控工作流（5 步闭环）
用户输入
│
Step1 识别输入 ──仅 URL──→ 分析站点 → 建源路线
│（已有源名/文件）
Step2 评估现状：syntax+validate(L1) → test 单接口(L2) → evaluate 全流程(L3)
│
Step3 判断失败类型：A规则不通 / B评估串联 / C播放链
│ 🛑 检查点1：确认诊断结论
Step4 分流执行：本 skill 修 / 转播放调试 / 转仓库
│
Step5 收束：evaluate 复评 → 🛑 检查点2 → 上传建议 / 结束
核心原则：先评估 → 再分流 → 再修复 → 再验证 → 最后给上传建议。不要一上来就重写。
模式闸门：先判断是否允许写入
| 用户模式 | 允许 | 禁止 |
|---|---|---|
| 只读/dry-run/只规划 | 读取、诊断、给方案和验证计划 | fs write/edit、house upload/* |
| 需确认后改 | 读取、诊断、输出拟改字段+验证计划 | 未确认前改源或仓库元数据 |
| 明确执行 | 按 L1/L2/L3 证据最小修复 | 跳过大改确认点、直接仓库 mutation |
| 自主全流程（"修到100""自动完成""做源并上传"） | alive check→建源→低风险修复→播放→L3=100→上传 | 坏站硬写、未达目标冒充完成、目标不明上传 |
任务分派表（场景 → 路线 + 首读 reference + 关键命令）
| 场景 | 路线 | 首读 reference | 关键 CLI 命令 |
|---|---|---|---|
| 仅 URL，新建源 | 建源 A/B/C/D | references-create-checklist.md、references-template-system.md |
fetch guess analyze template fs write syntax validate test evaluate |
| 已有源评估低分 | 诊断 A/B/C | references-workflow-triage.md、references-framework-internals.md |
fs read resolved evaluate test |
| detail 通但 play 异常 | 播放专项 | references-play-lazy-summary.md |
test <src> detail test <src> play iframe fetch + Playwright（见下） |
| 上传/替换/改标签 | 仓库守门 | references-upload-decision.md |
house verify house upload house list house info house tags |
| 模板继承排查 | 路线 A | references-template-summary.md、references-inherited-template-minimal-override-site.md |
guess resolved |
| 纯 API/SPA 站 | 路线 C | references-pure-api-async-site.md、references-api-functions.md |
fetch analyze |
| 签名接口站 | 路线 B2 | references-non-template-signed-api-site.md |
fetch + 浏览器抓包 |
| 二级字典/多集 | detail 规范 | references-detail-dict-and-multiep.md |
debug test <src> detail |
| 搜索异常 | 搜索策略 | references-search-strategies.md、references-old-encoding-search-site.md |
test <src> search |
| async 函数陷阱 | 通用 | references-async-function-patterns.md |
— |
| 特殊内容(漫画/小说/音乐/网盘) | 路线 D | references-special-content.md |
— |
| 多引擎源(php/hipy/cat) | 路线 E | references-multi-engine-sources.md |
fetch + curl ?do=py/php/cat&extend=（必须带 extend；hipy 改源需 kill daemon） |
What ships with it
46 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/cli-commands.md 5.5 KB
- references/migration-from-mcp.md 4.7 KB
- 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 6.5 KB
- references/references-framework-internals.md 5.5 KB
- references/references-inherited-template-minimal-override-site.md 5.4 KB
- references/references-multi-engine-sources.md 9.9 KB
- references/references-non-template-signed-api-site.md 9.5 KB
- references/references-old-encoding-search-site.md 3.5 KB
- references/references-play-lazy-summary.md 4.8 KB
- references/references-pure-api-async-site.md 4.6 KB
- references/references-search-strategies.md 8.1 KB
- references/references-special-content.md 3.2 KB
- references/references-template-summary.md 7.7 KB
- references/references-template-system.md 3.5 KB
- references/references-upload-decision.md 4.9 KB
- references/references-workflow-triage.md 2.9 KB
- scripts/.gitignore 38 B
- scripts/cli.js 6.6 KB runs code
- scripts/commands/fs.js 12 KB runs code
- scripts/commands/house.js 13 KB runs code
- scripts/commands/spider.js 12 KB runs code
- scripts/commands/system.js 4.5 KB runs code
- scripts/commands/test.js 18 KB runs code
- scripts/commands/validate.js 10 KB runs code
- scripts/data/skills-zh.md 12 KB
- scripts/data/skills.md 11 KB
- scripts/data/spider-static.js 8.9 KB runs code
- scripts/lib/argv.js 2.3 KB runs code
- scripts/lib/dsHelper.js 1.8 KB runs code
- scripts/lib/fsUtil.js 962 B runs code
- scripts/lib/output.js 757 B runs code
- scripts/lib/pathResolver.js 2.6 KB runs code
- scripts/lib/runtime.js 5.3 KB runs code
- scripts/package.json 381 B
- scripts/README.md 4.6 KB
- scripts/vendor/localDsCore.bundled.js 13872 KB runs code
- scripts/vendor/node-sqlite3-wasm.wasm 1223 KB
- scripts/vendor/simplecc_wasm_bg.wasm 1105 KB
- scripts/vendor/sqlite/node-sqlite3-wasm.js 34 KB runs code
- scripts/vendor/sqlite/node-sqlite3-wasm.wasm 1243 KB
- scripts/vendor/sqlite/package.json 44 B
- test-prompts.json 3.0 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 · 160 lines · 168 tokens per session scan A 10504eb127c2
drpy-node-coder is a skill published in the GitHub repository hjdhnx/drpy-node-skill (48 stars, last pushed 1mo ago), licensed MIT. It adds 168 tokens to every session and 3,672 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…