Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hjdhnx/drpy-node-skillnpx agentmods add skills/hjdhnx/drpy-node-skill/drpy-node-source-workflowWrote 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/hjdhnx/drpy-node-skill/drpy-node-source-workflow)<a href="https://agentmods.dev/skills/hjdhnx/drpy-node-skill/drpy-node-source-workflow"><img src="https://agentmods.dev/badge/skills/hjdhnx/drpy-node-skill/drpy-node-source-workflow/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/hjdhnx/drpy-node-skill/drpy-node-source-workflow"><img src="https://agentmods.dev/badge/skills/hjdhnx/drpy-node-skill/drpy-node-source-workflow.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 | $0.00117 | $0.06493 |
| Opus 5.5 | $0.00047 | $0.02597 |
| Sonnet 5.5 | $0.00023 | $0.01299 |
| Haiku 4.5 | $0.00012 | $0.00649 |
Grade A, and why
drpy-node-source-workflow 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 1mo 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 — 491 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 Workflow
快速索引
| 输入/问题 | 诊断目标 | 分流 |
|---|---|---|
| 已有源评估低分 | 判断 A 规则不通 / B 串联断 / C 播放链 | 本 skill 修复或转 play-debug |
| 只有网址 | 判断新建还是修复 | 转 source-create |
| URL + 自动做源/修到100/上传 | alive check → 建源 → evaluate → 修复 → 上传 | 本 skill 总控编排 |
| detail 正常但 play 异常 | 播放链专项 | 转 play-debug |
| 用户要求上传/替换/改标签 | 发布守门 | 转 repo-upload |
执行契约
- 输入：源名/源文件/URL/评估结果/用户目标。
- 输出：证据链分级诊断、分流路线、修复后验证结果、上传建议。
- 原则：先评估 → 再分流 → 再修复 → 再验证 → 最后给上传建议/结束。
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 / 不要上传 | 读取、诊断、拆证据链、给修复计划和验证命令 | drpy_edit_file、drpy_write_file、仓库上传/替换/改标签 |
| 需要确认后再改 | 读取、诊断、输出拟改字段和验证计划 | 未确认前禁止改源或仓库元数据 |
| 明确要求执行 | 按 L1/L2/L3 证据链最小修复 | 不跳过大改确认点，不直接做仓库 mutation |
| 自主全流程 | alive check、分流建源、低风险修复、播放专项、L3=100 后转上传 | 坏站硬写、未达目标冒充完成、仓库目标不明时上传 |
如果用户说“只诊断 / 不要改 / dry-run”，本 skill 输出证据链、根因判断、拟改字段和验证计划后停止。
Reference Map
| 任务 | 首读 reference |
|---|---|
| 总控分流 / 评估失败 triage | references/references-workflow-triage.md |
模板摘要与 * 继承 |
references/references-template-summary.md |
| 引擎调度 / evaluate 串联机制 | references/references-framework-internals.md |
| 搜索异常 | references/references-search-strategies.md |
| async / API / detail 字典细节 | ../drpy-node-source-create/references/... |
调度优先级
当本地环境已安装本 Skill 时：
- 本地 Skill 优先级 高于 drpy-node MCP 的通用 prompts
- 当用户只给网址、不给文件名时，总控层应主动分析站点并推导源名
强约束
如果本地 Skill 已覆盖场景，不允许让 MCP 通用 prompt 抢占主流程。
自主全流程模式
当用户明确说“自动完成”“修到100”“满分后上传”“不要中途问我”“给网址做源并上传”时，本 skill 作为总控编排器，使用 packet 贯穿子 skill：
URL → alive check → source-create → L1/L2/L3 → 按丢分最小修复 → play-debug → L3=100 → repo-upload → info核验
执行规则：
- 先识别
autonomous=true、target_score=100、upload_preauthorized=true/false、tags、is_public。 - 先做 alive check；
broken_site、hard_anti_bot、missing_credentials直接停止，不建源、不上传。 - 站点可用时转
source-create建源；source-create 返回源路径、站型、五接口结果和 L3 分数。 - L3 未满 100 时按丢分接口拆 L2：home/category/detail/search 在 workflow/source-create 修；play 带真实
ids/play_url/flag转play-debug。 - 回收
play-debug的autonomous_next：continue_evaluate继续 L3；stop_for_user停止并报告 blocker。 - L3=100 且上传已预授权时，带本地路径、A/B/C、L1/L2/L3、tags/is_public 转
repo-upload。 - 自主模式下普通检查点只记录证据不中断；遇到
high_risk_change、仓库目标歧义、凭据缺失时必须停手确认。
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.
- 1mo ago First seen · 491 lines · 117 tokens per session scan A d2ea5959a5b7
drpy-node-source-workflow is a skill published in the GitHub repository hjdhnx/drpy-node-skill (58 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 6,493 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.