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 skills add oil-oil/build-deepseek-harness-plugin --skill build-deepseek-harness-plugingit clone --depth 1 https://github.com/oil-oil/build-deepseek-harness-pluginWrote 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/oil-oil/build-deepseek-harness-plugin/build-deepseek-harness-plugin)<a href="https://agentmods.dev/skills/oil-oil/build-deepseek-harness-plugin/build-deepseek-harness-plugin"><img src="https://agentmods.dev/badge/skills/oil-oil/build-deepseek-harness-plugin/build-deepseek-harness-plugin/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/oil-oil/build-deepseek-harness-plugin/build-deepseek-harness-plugin"><img src="https://agentmods.dev/badge/skills/oil-oil/build-deepseek-harness-plugin/build-deepseek-harness-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00129 | $0.06440 |
| Opus 5.5 | $0.00052 | $0.02576 |
| Sonnet 5.5 | $0.00026 | $0.01288 |
| Haiku 4.5 | $0.00013 | $0.00644 |
Grade A, and why
build-deepseek-harness-plugin 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.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
构建 DeepSeek Harness 插件
目标
用 Harness 官方的插件装配、Client Slot 和服务 API 实现独立插件。优先扩展公开接口，不修改 Harness 核心、不依赖 DOM 结构、不用全局 CSS 强行覆盖产品界面。
官方入口与证据顺序
先读 official-practices.md。其中区分官方契约、目标版本源码事实和本 Skill 的项目约定。常用官方入口：
- 第一个插件
- 开发一个工具
- 插件配置
- 打包与安装
- 插件与生命周期
- Cordis 入门
- 能力的三种角色设计
- 扩展插件形态实操手册
- Client 模块
- Web UI 样式规范
- Settings
- Credentials
- API Gateway 与 Remote
- 会话内动态包走官方
cordis-plugin-development
master 链接只用于导航。目标版本源码、公开类型和生成的 Catalog 优先于在线文档；版本观察必须记录 commit，不能写成永久 API。
Reference 路由
- 每次任务先读 official-practices.md，记录证据基线。
- 每次任务同时读 version-and-integration-boundaries.md，先确定版本分支、启动宿主和后置覆盖层。
- 搭包、配置、构建或检查产物时读 package-and-build.md。
- 做 Client Slot、主题、本地化或界面时读 client-slots-and-theme.md。
- 做持久化、Remote、Settings、Credentials、安装或发布时读 persistence-and-release.md。
What ships with it
12 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.
- agents/openai.yaml 347 B
- assets/readme/deepseek-harness.svg 3.6 KB
- assets/readme/hero.svg 6.4 KB
- references/client-slots-and-theme.md 15 KB
- references/official-practices.md 17 KB
- references/package-and-build.md 15 KB
- references/persistence-and-release.md 20 KB
- references/version-and-integration-boundaries.md 7.8 KB
- scripts/check_plugin.mjs 19 KB runs code
- scripts/check_plugin.test.mjs 13 KB runs code
- scripts/check_references.mjs 6.7 KB runs code
- scripts/check_references.test.mjs 5.0 KB runs code
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.
- 2mo ago Changed · +6 lines 7f9bae093171
- 2mo ago First seen · 297 lines · 129 tokens per session scan A 7941049b9ccd
build-deepseek-harness-plugin is a skill published in the GitHub repository oil-oil/build-deepseek-harness-plugin (45 stars, last pushed 2mo ago), licensed MIT. It adds 129 tokens to every session and 6,440 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.
build-deepseek-harness-plugin compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| build-deepseek-harness-pluginoil-oil/build-deepseek-harness-plugin | Skill | 45 | 2mo ago | MIT | A | 129 | Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 3d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 6d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |