dsh-pihuo-plugins: Skill for Claude Code

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

dsh-plugin-conventions is a skill for Claude Code, Codex from xun404/dsh-pihuo-plugins. It costs 92 tokens per session (1,076 once invoked), scanned A, original, MIT.

A set of rules for designing plugins for the DeepSeek Harness, including how to name services, structure packages, expose configuration, and connect new behavior to extension points. It also covers lifecycle cleanup, logging, security boundaries, and comments.

In plain words
What is it for?
It is for choosing between services, events, slots, tools, providers, and consumers; designing package layouts; placing settings in configuration; and reviewing plugin comments, context keys, and extension points.
Why use it?
It helps developers add behavior without changing the core agent loop or creating incompatible plugin interfaces. The rules make configuration, registration, dependencies, and model-visible inputs easier to reason about.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is xun404/dsh-pihuo-plugins's own configuration. It tells Claude Code and Codex 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 →

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-conventions/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/xun404/dsh-pihuo-plugins

Made for: Claude Code, Codex.

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-conventions

README.md
[![agentmods](https://agentmods.dev/badge/skills/xun404/dsh-pihuo-plugins/dsh-plugin-conventions.svg)](https://agentmods.dev/skills/xun404/dsh-pihuo-plugins/dsh-plugin-conventions)
Your own site
<a href="https://agentmods.dev/skills/xun404/dsh-pihuo-plugins/dsh-plugin-conventions"><img src="https://agentmods.dev/badge/skills/xun404/dsh-pihuo-plugins/dsh-plugin-conventions.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,076 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 $0.00092 $0.01076
Opus 5 $0.00046 $0.00538
Sonnet 5 $0.00018 $0.00215
Haiku 4.5 $0.00009 $0.00108

Measured 8d ago against content hash 7c492d001f1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dsh-plugin-conventions 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 8d 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-conventions/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

插件规范

本技能是规范与选型。实现步骤见 dsh-plugin-author,审查清单见 dsh-plugin-review

对照:../deepseek-harness/docs/architecture.mddocs/capability-seams.mddocs/cookbook/adding-a-package.md

展开:references/seams.mdreferences/package.mdreferences/extension-points.mdreferences/comments.md

硬规则

  1. 没有内核可打补丁。 新行为挂到已有扩展点(服务 / 事件 / slot)。不要 fork agent loop,除非用户明确要换驱动器。
  2. 注册必须可逆。 模块顶层禁止副作用。卸载后不得残留监听、定时器、工具、适配器。
  3. 模型可见即已记录。 任何进入模型请求的新输入都要能从会话日志重建。不要用只有内存里才有的旁路去「喂」模型。
  4. 可调参数进 Config。 检验:能否只改 cordis.yml 而不改代码?配置错误必须在加载时失败,不要运行期静默改写。
  5. 政策与机制分离。 工具的 execute 做能力;允许/拒绝/超时走 tools/* 事件或独立 policy 插件。
  6. Consumer 不依赖 Provider。 双方只依赖 Service Definition。见 seams。
  7. 一个 Context key 一种合同。 单数 key = 一台引擎/当前配置;复数 key = 注册表。Host 与 Client 禁止用同一 key 表达不兼容类型。
  8. 树外包不要冒充第一方。 包名不用 @deepseek-ai/。不要改 dsh-base / dsh-web-app 来「顺便」带上自己。
  9. 动态包不是产品交付。 cordis_define / cordis_run 只活在内存,重启即空,vm 不是安全边界。可安装功能做成普通组合包。
  10. 注释必须完整、准确、可单独维护。 导出符号、非显然约束、协议/生命周期边界都要有 JSDoc;注释与代码不一致是错误。细则见 comments.md

选型口诀

  • 只要换实现、接口稳定 → 拆 Definition / Provider,Consumer 继续 inject 接口。
  • 只要给模型新能力 → 注册工具,schema 自动进提示词。
  • 只要换一次请求里模型看见的东西 → agent/pre-stepagent.inject(),并保证可从日志重建。
  • 只要按会话不同能力 → agent preset + isolate,不要在工具里读「当前是谁」硬分叉。
  • 只要 Web 上多一块 UI → dsh-plugin-client,不要在 Host 插件里 import 'react'

命名

东西 规则
npm 包 dsh-<name>@<scope>/dsh-<name>
patch / export const name 短横线,稳定,与包的主职责一致
ctx key camelCase;注册表用复数
工具 name snake_case,模型直接看到
事件 domain/action,与现有 agent/*tools/*session/* 对齐

角色词(Controller / Store / Registry / Provider / Policy …)的选用表在 package.md。不要因为类 extends Service 就把类名做成 FooService 却承担注册表职责。

本仓库布局

每个可安装插件一个顶层目录(或 packages/<name>,一旦开了 workspace 就统一)。目录内自包含:manifest、patch、源码、README。共享工具库如果不是 bundle,就不要声明 dsh.bundle

Read the full file on GitHub · 58 lines

Files

What ships with it

4 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.

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. 8d ago First seen · 58 lines · 92 tokens per session scan A 7c492d001f1e

Subscribe to this mod's changes

dsh-plugin-conventions is a skill published in the GitHub repository xun404/dsh-pihuo-plugins (2 stars, last pushed 22d ago), licensed MIT. It adds 92 tokens to every session and 1,076 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 2026-08-31.

Related

Other skills, from other repositories

dsh-plugin-guide

Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…

PerryLink/dsh-plugin-guide · 76 tokens

codex-sync

Operate dsh-codex-sync from this session — preview and import Codex chats, toggle Skills/MCP/import settings, check MCP mirror health, install the reverse MCP bridge.

Walvez/dsh-codex-sync · 40 tokens

dsh-plugin-development

Use when designing, creating, modifying, packaging, installing, reviewing, auditing, or diagnosing a DeepSeek Harness plugin: a live dynamic Cordis plugin driven by cordisdefine, a source-backed workspace plugin under packages, or an out-of-tree installable bundle using dsh.bundle and cordis.patch.yml. Also use for…

w2112515/dsh-plugin-development · 130 tokens

dsh-web-community-plugin-developer

Develop a DSH community plugin and register it in the dsh-web Community Plugins index — author the plugin in the contributor's own repository following the official cordis bundle standard, add its entry to packages/dsh-community-plugins/community.json, regenerate the index with scripts/community-index, rebuild and…

zhu1090093659/dsh-web · 123 tokens

dsh-web-skin-developer

Build a new skin for the dsh-web skin collection (DSH Web GUI) and publish it into the Skin Center — the first-level settings section — scaffold with scripts/dsh-skin-new, author the v2 skin.json manifest plus skin.css token remap (pure asset directory, no package.json, no build step), validate with scripts/dsh-skin…

zhu1090093659/dsh-web · 120 tokens

dsh-sdk-upgrade

Safely select and install a compatible official @deepseek-ai SDK release for dsh plugin projects (dsh-web, dsh-trading, and similar monorepos) from npm using an isolated worktree, explicit cohort review, CI-equivalent validation, and controlled rollout — including syncing the project's declared DSH host-version floor…

zhu1090093659/dsh-web · 176 tokens