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 hackerFish/awesome-dsh-skills --skill dsh-plugin-publishgit clone --depth 1 https://github.com/hackerFish/awesome-dsh-skillsWrote 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/hackerfish/awesome-dsh-skills/dsh-plugin-publish)<a href="https://agentmods.dev/skills/hackerfish/awesome-dsh-skills/dsh-plugin-publish"><img src="https://agentmods.dev/badge/skills/hackerfish/awesome-dsh-skills/dsh-plugin-publish/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/hackerfish/awesome-dsh-skills/dsh-plugin-publish"><img src="https://agentmods.dev/badge/skills/hackerfish/awesome-dsh-skills/dsh-plugin-publish.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 | $0.00051 | $0.00595 |
| Opus 5 | $0.00026 | $0.00298 |
| Sonnet 5 | $0.00010 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
dsh-plugin-publish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
DSH 插件发布与生态收录（依据 dsh-video-studio / dsh-voice-input 实战验证）
发布前
lib/构建产物必须提交进 git：GitHub tarball 安装直接取仓库内容，没有lib/装不上- 补 LICENSE（MIT）与中英双语 README（
README.md英文 +README.zh.md中文互链） - README 不写本机绝对路径（
D:\...），统一用$DSH_HOME/profiles/<profile>通用写法
建仓与推送
- 本地：
git init -b main→ commit →git remote add origin [email protected]:<user>/<repo>.git→git push -u origin main - GitHub 建仓用 API：
POST /user/repos（body:name/description/private） - ⚠️ 编码陷阱：PowerShell 5.1 的
Invoke-RestMethod直接传中文 body 会变成问号；必须[Text.Encoding]::UTF8.GetBytes($json)传字节流，并带ContentType 'application/json; charset=utf-8' - 仓库 topics（
PUT /repos/<user>/<repo>/topics）：dsh、deepseek-harness、plugin必带，再按功能加（如voice-input、speech-recognition）
生态收录（awesome-deepseek-harness）
- 目标仓库
Dominic789654/awesome-deepseek-harness：fork → 改README.md（英）+README.zh-CN.md（中）→ 提 PR - 条目放匹配类目（UI 类插件 →
## UI / 客户端/## UI / Clients），一行 markdown 链接 + 一句话描述 - 脚本化要点：fetch 加超时与退避重试（GitHub/raw 偶发网络抖动自愈）；提 PR 前先查同 head 的 open PR 直接复用（幂等，避免重复 PR）
- 仓库 description 与 PR body 用 Node fetch（UTF-8 正确）或 UTF-8 字节流，避开 PowerShell 编码坑
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.
- 12d ago First seen · 28 lines · 51 tokens per session scan A fe194fd5ddc0
dsh-plugin-publish is a skill published in the GitHub repository hackerFish/awesome-dsh-skills (5 stars, last pushed 7d ago), licensed MIT. It adds 51 tokens to every session and 595 once invoked, about $0.0003 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.
Other skills, from other repositories
finishing-a-development-branch
A process for finishing a completed development branch. A branch is a separate line of code changes that can later be merged or submitted as a pull request.
commit-message
Guidance for writing Git commit messages using Conventional Commits, a common format such as fix, feat, or docs followed by a short description. It focuses on explaining why a change was made.
release-skill
A release checklist for publishing a new software version. It covers changing the version number, creating a Git tag, and publishing a GitHub Release.
market-release
A release workflow for publishing a new version of a software package. It uses release-please to create a release pull request, then creates a tag, a GitHub release, and an npm publication after the pull request is merged.
code-review-zh
A Git-based code review workflow that compares changes from a chosen commit, branch, tag, or merge point. It checks both whether the code follows the repository's written standards and whether it implements the requested specification.
release-deploy
A release and deployment skill for preparing a software project for GitHub publication and putting it online.