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 pingfanfan/hello-dsh --skill dsh-skill-devgit clone --depth 1 https://github.com/pingfanfan/hello-dshWrote 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/pingfanfan/hello-dsh/dsh-skill-dev)<a href="https://agentmods.dev/skills/pingfanfan/hello-dsh/dsh-skill-dev"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/dsh-skill-dev/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/pingfanfan/hello-dsh/dsh-skill-dev"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/dsh-skill-dev.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 | $0.00059 | $0.01567 |
| Opus 5.5 | $0.00024 | $0.00627 |
| Sonnet 5.5 | $0.00012 | $0.00313 |
| Haiku 4.5 | $0.00006 | $0.00157 |
Grade A, and why
dsh-skill-dev 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
给 DSH 写技能
技能是 DSH 里成本最低的扩展方式：一个 Markdown 文件，不写代码，不构建，不发包，改完不重启。
本文规则来自官方 packages/skill/skill-filesystem/README.md 与 packages/skill/tool-skill/README.md。涉及版本行为时以实际运行结果为准，不要照抄记忆。
最小形态
~/.dsh/skills/<name>/SKILL.md # 目录形式，可带附加资源
~/.dsh/skills/<name>.md # 或扁平单文件
---
name: my-skill
description: 当需要做某件具体的事时使用。
---
（正文是直接交给模型的指令）
嵌套的 **/SKILL.md 不会被发现，只扫一层。
发现路径
按 rank 排序，数字小的优先，同名时高优先级胜出：
| Rank | 来源 | 路径 |
|---|---|---|
| 100 | project-dsh |
<项目>/.dsh/skills |
| 200 | project-agents |
<项目>/.agents/skills |
| 300 | custom |
配置的自定义目录 |
| 400 | user-dsh |
~/.dsh/skills |
| 500 | user-agents |
~/.agents/skills |
项目根 = 最近的含 .git 的祖先目录，没有则用当前工作目录。
~/.agents/skills 是跨 agent 共享目录，Claude Code 等工具的技能放这里 DSH 也能发现。
三个必须知道的行为
一、fail-closed：写错键名整条丢弃
调用策略的键名必须是 kebab-case。写成驼峰，整个技能被丢弃，不是忽略那个字段：
user-invocable: true # 对
userInvocable: true # 整条技能消失，只有一条警告
disable-model-invocation: false # 对
disableModelInvocation: false # 整条技能消失
值也必须是布尔或可接受的布尔词（true/false、yes/no、on/off、1/0，大小写不敏感）。写 maybe 同样导致整条丢弃。
这是有意的安全设计：一个声明了"不要暴露给用户"的技能，如果因为拼写错误被宽容处理，就会出现在本不该出现的界面上。丢弃比错误暴露安全。
排查顺序：技能没出现 → 先查 frontmatter 键名，再查路径。
二、description 决定它会不会被用到
模型最初只看到一份目录，里面只有每个技能的 name 和 description。正文要等模型决定加载之后才会被读进去。
所以 description 的唯一任务是让模型在正确时机想起它：
# 无效
description: 一个用于代码审查的技能
# 有效
description: 当需要审查代码改动、pull request 或 diff 时使用，按正确性、
生命周期、安全、测试强度的顺序给出中文审查意见。
写法：以「当……时使用」开头，再说清它会做什么。这是官方 11 个技能的统一格式。
三、正文改动即时生效
每次加载都会重新读取文件，所以改正文不需要任何缓存失效动作。
目录也会在会话中途刷新。 tool-skill 在每个 agent/pre-step 都会重新快照一次目录，membership 或 description 变化时会向会话追加一份完整的替换目录。所以会话进行到一半时新建的技能，下一步就能被发现并加载，不需要开新会话。（实测确认过：会话开始后创建技能目录，同一次运行里模型就能加载到它。）
会触发目录重新发现的：新增/删除技能目录、SKILL.md 的增删改、扁平 .md 的增删。
不会触发的：references/、scripts/、assets/ 下的改动。
正文怎么写
参照官方自己的写法（仓库 .agents/skills/，11 个）：
- 开头声明这是判断指引，不是清单。 清单会让模型机械打勾，判断标准让它权衡。
- 列出事实来源，并说明「读它，不要复述它」。 防止技能变成会过期的二手资料。
- 分层：阻断项 / 检查项 / 不要做的事。 优先级要显式。
- 给正例反例对照。 比抽象描述有效得多。
- 单独写「不要做的事」。 模型有默认倾向，不明说就会做。这一节挡住的问题往往比「要做什么」更多。
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 · 128 lines · 59 tokens per session scan A 7d977a285aec
dsh-skill-dev is a skill published in the GitHub repository pingfanfan/hello-dsh (101 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,567 once invoked, about $0.0002 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
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…
skill
Ten native DSH tools give a text-only agent eyes. Use these structured tools directly; do not shell out to the bundled Python scripts or reproduce their implementation. Vision API credentials and model settings are managed by the plugin, so tool calls do not receive credentials.
modsearch
Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return…
submit-dsh-plugin
A submission checklist and workflow for adding a DeepSeek Harness plugin to the community’s public catalogue. It prepares the catalogue entry and checks the plugin’s repository, metadata, tests, and required files.
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
industry-research-method
A Chinese-language method for researching an industry by mapping its supply chain, tracking policies and news, and writing sourced reports. It separates the chain into upstream inputs, midstream production, and downstream distribution or use.