dsh-web: Skill for Claude Code

.agents/skills/dsh-web-agent-coding/SKILL.md

dsh-web-agent-coding is a skill for Claude Code, Codex from zhu1090093659/dsh-web. It costs 40 tokens per session (753 once invoked), scanned A, original, Apache-2.0.

A coding workflow for the dsh-web monorepo, a repository that contains multiple related packages in one codebase. It explains how to establish scope, follow repository instructions, and keep host, client, and shared code in their proper areas.

In plain words
What is it for?
Use it for implementation, maintenance, or configuration work in dsh-web, including locating the owning package, reading applicable AGENTS.md instructions, and keeping changes within repository boundaries.
Why use it?
It helps developers make changes in the smallest correct package while preserving unrelated work. It also highlights project-specific restrictions around generated files, external hosts, SDKs, and browser bundles.

Skill for Claude CodeCodex

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is zhu1090093659/dsh-web's own configuration. It tells Claude Code and Codex how to work on dsh-web 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-web configures →

About the project

dsh-web is a plugin ecosystem that adds a web interface and optional tools to DeepSeek Harness, an AI development environment. It is used to provide features such as task boards, mobile remote control, SSH operations, image understanding, file and code panels, Git views, agent presets, and interchangeable skins through independently loaded plugins. The catalogue skills are plugins and related workflows for extending and operating the DSH Web environment.

zhu1090093659/dsh-web · 7,218 stars · on GitHub · dsh-market.com

Reuse

Borrowing it

Nothing to install: this file belongs to zhu1090093659/dsh-web. 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/zhu1090093659/dsh-web/dev/.agents/skills/dsh-web-agent-coding/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zhu1090093659/dsh-web

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-web-agent-coding

README.md
[![agentmods](https://agentmods.dev/badge/skills/zhu1090093659/dsh-web/dsh-web-agent-coding/github.svg)](https://agentmods.dev/skills/zhu1090093659/dsh-web/dsh-web-agent-coding)
Your own site
<a href="https://agentmods.dev/skills/zhu1090093659/dsh-web/dsh-web-agent-coding"><img src="https://agentmods.dev/badge/skills/zhu1090093659/dsh-web/dsh-web-agent-coding/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.

agentmods 80×15 button for dsh-web-agent-coding

Your own site · 80×15
<a href="https://agentmods.dev/skills/zhu1090093659/dsh-web/dsh-web-agent-coding"><img src="https://agentmods.dev/badge/skills/zhu1090093659/dsh-web/dsh-web-agent-coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 753 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00040 $0.00753
Opus 5 $0.00020 $0.00377
Sonnet 5 $0.00008 $0.00151
Haiku 4.5 $0.00004 $0.00075

Measured 7d ago against content hash b5136bf33615, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dsh-web-agent-coding 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 7d 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-web-agent-coding/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dsh-web Agent Coding

This skill is guidance, not a replacement for repository instructions. AGENTS.md is the authoritative source for repository rules.

Establish scope

  1. Confirm the workspace, repository root, current branch, and worktree status before writing. Preserve unrelated changes from other sessions; do not reset, clean, restore, or stage them.
  2. Read the root instructions, then the nearest applicable AGENTS.md. Read packages/AGENTS.md before changing a package and docs/AGENTS.md before writing documentation.
  3. Identify the smallest owner of the behavior: a plugin package, a skin, shared/, a generator in scripts/, or an aggregate package. Keep the change in that owner unless an existing shared abstraction is the real source of truth.

Implement within repository boundaries

  • DSH itself is an external host. Do not modify its checkout or make TypeScript resolve against it. Use the official @deepseek-ai/* SDK through installed dependencies.
  • Keep host, client, and shared logic in their respective package areas. Browser bundles must retain the platform-import and type-only SDK constraints in packages/AGENTS.md.
  • Edit a generated shared copy only through its source in shared/, then run the documented synchronization command.
  • Add a package or change aggregate membership through the repository generators and update required documentation. Do not hand-edit generated output.
  • Record every non-trivial change as an Agent Note under .agents/notes/ in the same change: proposals start in proposed/, shipped decisions in implemented/, declined proposals in rejected/. Follow the lifecycle, class, and format rules there.
  • Adhere to the Software Factory governance baseline: maintain prompt prefix stability (Layer 1/2), route lightweight subagents (flash/flash_lite) for routine research/search/i18n, trigger the anti-thrashing circuit breaker after 3 failed attempts, and follow the 4-step CI self-healing protocol (Log Isolation -> Local Repro -> Minimal Diff -> Gate Check) when resolving errors.
  • Build and exercise the affected behavior before declaring it complete. A commit alone is not delivery.

Read the full file on GitHub · 39 lines

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. 7d ago Changed · +1 lines b5136bf33615
  2. 10d ago First seen · 38 lines · 40 tokens per session scan A ffdc9b7ef9e0

Subscribe to this mod's changes

dsh-web-agent-coding is a skill published in the GitHub repository zhu1090093659/dsh-web (7,218 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 753 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 2026-08-30.

Related

Other skills, from other repositories

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…

shengsheng90/DSH-taskboard · 88 tokens

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.

PerryLink/dsh-industry-research · 96 tokens

company-research-method

A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.

PerryLink/dsh-industry-research · 83 tokens

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

setup-matt-pocock-skills

Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

gongyijie85/mattpocock-skills-dsh · 44 tokens

wayfinder

Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

gongyijie85/mattpocock-skills-dsh · 46 tokens