dsh-pihuo-plugins: Skill for Claude Code

.agents/skills/dsh-plugin-author/SKILL.md

dsh-plugin-author is a skill for Claude Code from xun404/dsh-pihuo-plugins. It costs 87 tokens per session (1,456 once invoked), scanned A, original, MIT.

A guide and starter process for building plugins for DeepSeek Harness, an AI-agent framework. It covers tools, services, model connections, event hooks, and plugin bundles.

In plain words
What is it for?
Use it when scaffolding or implementing a DeepSeek Harness plugin, adding a model tool, connecting a model provider, or creating a bundle.
Why use it?
It helps developers choose the right extension type and create the required files and structure.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is xun404/dsh-pihuo-plugins's own configuration. It tells Claude Code how to work on dsh-pihuo-plugins itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dsh-pihuo-plugins configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is pnpm --dir ../deepseek-harness dsh web --patch /absolute/path/to/<pkg>/cordis.yml.

Reuse

Borrowing it

Nothing to install: this file belongs to xun404/dsh-pihuo-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/xun404/dsh-pihuo-plugins/main/.agents/skills/dsh-plugin-author/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/xun404/dsh-pihuo-plugins

Made for: Claude Code.

Wrote 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.

agentmods badge for dsh-plugin-author

README.md
[![agentmods](https://agentmods.dev/badge/skills/xun404/dsh-pihuo-plugins/dsh-plugin-author/github.svg)](https://agentmods.dev/skills/xun404/dsh-pihuo-plugins/dsh-plugin-author)
Your own site
<a href="https://agentmods.dev/skills/xun404/dsh-pihuo-plugins/dsh-plugin-author"><img src="https://agentmods.dev/badge/skills/xun404/dsh-pihuo-plugins/dsh-plugin-author/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.

agentmods 80×15 button for dsh-plugin-author

Your own site · 80×15
<a href="https://agentmods.dev/skills/xun404/dsh-pihuo-plugins/dsh-plugin-author"><img src="https://agentmods.dev/badge/skills/xun404/dsh-pihuo-plugins/dsh-plugin-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.01456
Opus 5.5 $0.00035 $0.00582
Sonnet 5.5 $0.00017 $0.00291
Haiku 4.5 $0.00009 $0.00146

Measured 2mo ago against content hash d31589bad086, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dsh-plugin-author 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 2mo 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.

.agents/skills/dsh-plugin-author/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

编写 dsh 插件

本技能是开发流程。运行时细节读 dsh-plugin-runtime;层与安装读 dsh-plugin-compose;命名与 seam 读 dsh-plugin-conventions;浏览器半读 dsh-plugin-client。模板只在 references/templates.md。

规范对照仓库:../deepseek-harness(若存在)。与源码冲突时以源码为准。

1. 分类,再动手

按用户目标选一种,且只选一种作为主交付。对照 conventions 的扩展点表:

用户要的 形态 必读
模型可调用的能力 工具插件:inject: ['tools'] + defineTool 本技能 §3 + templates §工具
可替换的底层能力 seam 三角(Definition / Provider / Consumer) seams
新模型提供方 ctx.llm.registerAdapter templates §适配器
拦截 / 策略 事件钩子(优先 tools/*、agent/*) templates §钩子
Web UI / 设置卡片 / Chat 节点 浏览器半 dsh-plugin-client
把已有模块装进 profile 组合包(dsh.bundle + patch) dsh-plugin-compose

不要为「以后可能扩展」先拆三角。一个包能诚实承担的职责就放一个包。

2. 落盘位置

本仓库是树外插件集,不要往 ../deepseek-harness/packages/ 加第一方包,除非用户明确要求改 harness。

默认骨架:

<pkg>/
  package.json          # name、exports、dsh.bundle
  cordis.patch.yml      # insert 本包行
  src/index.ts          # name / inject / Config / apply
  tsconfig.json
  README.md
  • 包名:dsh-<name> 或 @<scope>/dsh-<name>。不要用 @deepseek-ai/。
  • 插件 export const name 用短横线 id,与 patch id 对齐(见 conventions)。
  • TypeScript 插件必须有自包含 prepare 构建,git 安装才能用。步骤见 compose。

先列出将要创建的文件,再写。不要先写实现再补 manifest。

3. 实现顺序

  1. 写 package.json 与 cordis.patch.yml(compose 清单)。
  2. 导出 name、inject、可选 Config(Schemastery,不是普通对象)、apply。三种形态见 runtime;默认用函数形态。只有要提供 ctx.<key> 时才用 Service 子类。
  3. inject 列出 apply 会读取的服务。可选服务用 ctx.get('x'),不要写进 inject。
  4. 所有注册走 ctx(register / on / effect)。禁止模块顶层副作用。禁止自己 removeListener / clearInterval 来「对应」ctx.on / ctx.effect。
  5. 部署可能不同的值放进 Config。硬编码超时、路径、模型名是错的。
  6. 需要清理的外部资源包进一个 ctx.effect(() => disposer)。有顺序依赖的清理放进同一个 disposer。

Read the full file on GitHub · 99 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 2mo ago First seen · 99 lines · 87 tokens per session scan A d31589bad086

Subscribe to this mod's changes

dsh-plugin-author is a skill published in the GitHub repository xun404/dsh-pihuo-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,456 once invoked, about $0.0003 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 2026-08-31.

Related

dsh-plugin-author compared with skills from other repositories

dsh-plugin-author next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dsh-plugin-authorxun404/dsh-pihuo-pluginsSkill22mo agoMITA87Claude Code
dsh-plugin-guidePerryLink/dsh-plugin-guideSkill65yesterdayApache-2.0A62Claude Code, Codex
codex-syncWalvez/dsh-codex-syncSkill301mo agoMITB40Claude Code, Codex
dsh-plugin-developmentw2112515/dsh-plugin-developmentSkill112mo agoMITA130Codex
dsh-tui-guideccch1mneyyy/dsh-TUISkill7.2ktodayMITA41Claude Code, Codex
modsearchliustack/modsearchSkill95211d agoMITA99Claude Code
submit-dsh-pluginimsai-sh/awesome-deepseek-harness-pluginsSkill370yesterdayMITA103Codex