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 agentmods add instructions/kairoz9/dsh-mcp-admin/agents-mdgit clone --depth 1 https://github.com/kairoz9/dsh-mcp-adminWrote 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/instructions/kairoz9/dsh-mcp-admin/agents-md)<a href="https://agentmods.dev/instructions/kairoz9/dsh-mcp-admin/agents-md"><img src="https://agentmods.dev/badge/instructions/kairoz9/dsh-mcp-admin/agents-md.svg" alt="Measured on agentmods" 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 | $0.01155 | $0.01155 |
| Opus 5 | $0.00577 | $0.00577 |
| Sonnet 5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
dsh-mcp-admin AGENTS.md 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 4d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Agent & Contributor Guide for dsh-mcp-admin
dsh-mcp-admin is an official-standard plugin for DeepSeek Harness (dsh) that provides:
- Host-side MCP Management:
/mcpcommand and@RemoteRPC backend managing MCP servers across profiles. - Browser-side Settings Panel: Full-featured GUI in the settings modal with live connection states, add/edit/delete/toggle controls, and bilingual (zh/en) i18n support.
📁 Repository Structure
.
├── src/
│ ├── host/ # Node.js backend (Host half)
│ │ ├── index.ts # Cordis apply entry point, commands & @Remote service
│ │ ├── profile-store.ts # Profile discovery, YAML patch parser & atomic writer
│ │ ├── profile-store.test.ts # YAML reconciliation & comment preservation tests
│ │ ├── server-inventory.ts # Live tool counts & connection state machine
│ │ └── server-inventory.test.ts
│ ├── client/ # Browser frontend (Client half)
│ │ ├── index.ts # Client entry point, remote mount & slot injection
│ │ ├── McpAdminSection.tsx # React settings section component
│ │ ├── McpAdminSection.css # Standalone component styling (Figma token-aligned)
│ │ ├── css.d.ts # Text loader CSS ambient types
│ │ ├── locales.ts # Bilingual dictionaries (zh & en)
│ │ ├── server-draft.ts # Form validation, state derivations & draft modeling
│ │ └── server-draft.test.ts # Client draft & i18n unit tests
│ └── types/
│ └── dsh.d.ts # Portable ambient types for @deepseek-ai/* packages
├── scripts/
│ ├── build.mjs # esbuild atomic bundler (host ESM + client CJS closure)
│ └── release.mjs # Automated SemVer bumper, doc syncer & git tagger
├── .github/
│ ├── workflows/ci.yml # GitHub Actions CI (typecheck, test, build, pack)
│ ├── workflows/release.yml # Automated GitHub Release publisher with notes
│ └── release.yml # GitHub release notes categorization template
├── cordis.patch.yml # Default plugin wiring patch
├── package.json
└── tsconfig.json
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.
- 4d ago First seen · 91 lines · 1,155 tokens per session scan A d5fe8abde9d8
dsh-mcp-admin AGENTS.md is an instructions file published in the GitHub repository kairoz9/dsh-mcp-admin (5 stars, last pushed 20d ago), licensed MIT. It adds 1,155 tokens to every session, about $0.0058 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 instructions, from other repositories
dsh-mcp-panel AGENTS.md
Instructions for PerryLink/dsh-mcp-panel, covering agents.md, layout, hard rules applied here, config and build.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
deepseek-harness CLAUDE.md
Claude Code instructions for deepseek-ai/deepseek-harness, a project described as: DeepSeek Harness: Everything is a Plugin.
DSH-better-sidebar AGENTS.md
AGENTS.md instructions for omdsh-dev/DSH-better-sidebar, covering dsh-better-sidebar 仓库规则（agents）, 1. 仓库硬约束（必须遵守）, 2. ci 挂载冒烟（plugin-mount job / pnpm test:mount）, 3. dsh 0.1.2 适配要点（0.1.2-rc.1+ 基线） and 4. npm 发版（github release → npm publish）.
dsh-worktable AGENTS.md
Instructions for Aisland-SJL/dsh-worktable, covering dsh-worktable 项目规则, 协作方式（用户定案，最高优先级）, 边界, 构建与验证 and 领域约定（会话中必须遵守）.
awesome-deepseek-harness-plugins AGENTS.md
Instructions for imsai-sh/awesome-deepseek-harness-plugins, covering repository instructions, the submission gate is the product, generated files, cross-repo contracts (no ci spans both repositories) and permanent urls.