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-skill-adaptergit 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-skill-adapter)<a href="https://agentmods.dev/skills/hackerfish/awesome-dsh-skills/dsh-skill-adapter"><img src="https://agentmods.dev/badge/skills/hackerfish/awesome-dsh-skills/dsh-skill-adapter/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-skill-adapter"><img src="https://agentmods.dev/badge/skills/hackerfish/awesome-dsh-skills/dsh-skill-adapter.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 | $0.00036 | $0.00348 |
| Opus 5 | $0.00018 | $0.00174 |
| Sonnet 5 | $0.00007 | $0.00070 |
| Haiku 4.5 | $0.00004 | $0.00035 |
Grade A, and why
dsh-skill-adapter 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 11d 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 Skill Adapter
- Inspect the source Skill, license, revision, task triggers, tools, side effects, output contract, and verification steps.
- Do not port a skill verbatim when its license, provenance, or permitted reuse is unclear; independently summarize its workflow instead.
- Keep decision rules and checks; remove role-play, repeated host-agent rules, invented capability claims, and agent-specific private tool names.
- Map each action to an enabled DSH capability: filesystem, configured shell, web search, browser plugin, or subagent.
- For an unavailable capability, state a prerequisite or manual handoff. Never claim a replacement tool ran when it did not.
- Write the adapted file at
.agents/skills/<name>/SKILL.mdor.dsh/skills/<name>/SKILL.mdusing a kebab-case name plusnameanddescriptionfrontmatter. - Require confirmation before deletion, publishing, deployment, external messages, or credential changes.
- Verify that every command, path, and tool either exists in the active session or is labeled as a prerequisite.
- Deliver the source/license assessment, DSH capability map, installation path, adapted
SKILL.md, two trigger prompts, and one near-miss prompt.
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.
- 11d ago First seen · 19 lines · 36 tokens per session scan A e731b0ed9994
dsh-skill-adapter is a skill published in the GitHub repository hackerFish/awesome-dsh-skills (5 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 348 once invoked, about $0.0002 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
dsh-plugin-dev
A guide for building and debugging plugins for DeepSeek Harness, a developer-preview tool built on the Cordis component framework. It explains how plugins are exported, loaded, and connected to services.
dsh-first-plugin
A step-by-step guide for building and installing a first DSH plugin. DSH is a software tool whose plugins can add tools, connect outside services, or respond to agent events.
dsh-onboarding
Guidance for helping someone use DeepSeek Harness, a local runtime for coding agents, for the first time. It explains the runtime, profiles, workspace, permissions, and how extensions are discovered.
dsh-skill-dev
A specialist review agent for software that handles purchasing, suppliers, payments, or spending approvals.
dsh-troubleshoot
A troubleshooting guide for DeepSeek Harness, including its process, configuration, plugins, tools, skills, and model connections.
api-design
Guidance for designing public programming interfaces, meaning the methods and data structures other code is allowed to use. It emphasizes adding only interfaces with real callers and making invalid uses impossible to compile.