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/sivan757/dsh-agent-plugins-market/agents-mdgit clone --depth 1 https://github.com/Sivan757/dsh-agent-plugins-marketWrote 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/sivan757/dsh-agent-plugins-market/agents-md)<a href="https://agentmods.dev/instructions/sivan757/dsh-agent-plugins-market/agents-md"><img src="https://agentmods.dev/badge/instructions/sivan757/dsh-agent-plugins-market/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 5.1 | $0.01106 | $0.01106 |
| Opus 5 | $0.00553 | $0.00553 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
dsh-agent-plugins-market 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 today.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
dsh-agent-plugins-market is the DeepSeek Harness plugin that installs Claude Code / Codex / Cursor / Kimi marketplace suites in place — zero conversion, zero file copying — and injects skills, MCP servers, hooks, commands, agents, and LSP servers into dsh sessions at runtime. Domain vocabulary lives in CONTEXT.md (source, dialect, suite, surface, install state); use those terms exactly. Human onboarding and PR flow live in CONTRIBUTING.md — do not restate them here.
Repository layout
src/
application/ use-case layer: catalog assembly, queries, install orchestration
catalog/ source scanning: manifests, dialects, scan pipeline, lsp-spec validation
client/ Web market page (React + CSS modules), bilingual locales.ts
contracts/ API request/response types shared by routes and client
model/ domain types (suite, source, surfaces)
runtime/ harness-facing effects: reconciler, MCP client bridge, MCP/LSP mounts, status builders
index.ts plugin entry; routes.ts API surface
schemas/ versioned mcp.schema.json and friends (strict validation contracts)
tests/ vitest suites mirroring src/; fixtures under tests/fixtures
docs/ adr/, design/, release/, promotion/, research/, standards/
docs-site/ Astro docs site
scripts/ build helpers (client banner, npm token, lifecycle verification)
Commands
pnpm run typecheck # both tsconfig.json and tsconfig.client.json
pnpm run lint # eslint src tests
pnpm run format:check # prettier — covers ALL files including docs/ and HTML
pnpm run test # vitest run (full suite)
pnpm run test:contract # routes + market contracts only
pnpm run check:architecture # dependency-cruiser over src/
pnpm run check:refactor # typecheck + lint + format:check + test:contract + architecture
pnpm run build # tsc emits lib/, tsdown bundles client/
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.
- today First seen · 52 lines · 1,106 tokens per session scan A a4a1139e2680
dsh-agent-plugins-market AGENTS.md is an instructions file published in the GitHub repository Sivan757/dsh-agent-plugins-market (7 stars, last pushed today), licensed MIT. It adds 1,106 tokens to every session, about $0.0055 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 2026-09-05.
Other instructions, from other repositories
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-config-manager AGENTS.md
AGENTS.md instructions for xiajiajun516/dsh-config-manager, covering agents.md — dsh config manager 仓库协作指南, 🌐 语言, 📦 概览, 🗂️ 结构与分层 and ui 分层铁律.
causal-memory CLAUDE.md
Claude Code instructions for JingxuanC/causal-memory, covering causal memory mcp integration, causal memory integration, after acting on a decision and observing the result, when something fails unexpectedly and when a recorded lesson turns out to be wrong.
dsh-industry-research AGENTS.md
AGENTS.md instructions for PerryLink/dsh-industry-research, covering agents.md, layout, hard rules applied here, checks and release.
dsh-checkpoint-rewind AGENTS.md
AGENTS.md instructions for PerryLink/dsh-checkpoint-rewind, covering agents.md, 仓库布局：发布面 / 本地工程面, 命令, 提交纪律 and dsh 插件约束（红线）.
star-dsh-desktop AGENTS.md
AGENTS.md instructions for dabaicai001/star-dsh-desktop, covering agents.md — starhub 协作指引, 项目是什么, 架构一句话, 目录结构 and 技术栈速查.