agentmods.dev

dsh-compat AGENTS.md

A set of project instructions for Simidas/dsh-compat, a compiler and validator that converts Claude Code or Codex plugins into DSH-compatible files.

In plain words
What is it for?
It guides inspection and conversion work, deterministic output, layered implementation, security checks, and regression testing for supported and rejected inputs.
Why use it?
It defines the project’s boundaries, safety rules, source tracking, conversion labels, and evidence required before claiming compatibility.

Instructions file for CodexOpenCode

2 17d ago A scan 456 tokens original Apache-2.0
View the source file Simidas/dsh-compat
Install

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.

agentmods
npx agentmods add instructions/simidas/dsh-compat/agents-md
Clone the repo
git clone --depth 1 https://github.com/Simidas/dsh-compat

Made for: Codex, OpenCode.

Per session 456 This file is loaded in full into every session.
When invoked 456 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00456 $0.00456
Opus 5 $0.00228 $0.00228
Sonnet 5 $0.00091 $0.00091
Haiku 4.5 $0.00046 $0.00046

Measured yesterday against content hash 68aba75cfd5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dsh-compat 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 yesterday.

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.md · 35 lines

What it actually says

dsh-compat 项目规则

事实源

  • project-control.md 是项目状态、任务、阻塞和决策的唯一事实源。
  • 聊天、提交信息和 README 不能替代控制文件。
  • 每次完成工作后，先更新验证证据，再更新任务状态。

产品边界

  • 产品是 Claude Code / Codex 插件到 DSH 的兼容编译器与验证器，不是通用 Agent 配置同步器。
  • Phase 1 只读检查；Phase 2 才生成文件；未经 Owner 明确确认，不安装插件、不执行源插件代码、不发布包。
  • 所有转换结果必须标记 DIRECT、ADAPTED、UNSUPPORTED 或 BLOCKED，禁止静默丢弃。

安全规则

  • inspect 和 convert 不运行 prepare、postinstall、hook、script、binary 或 MCP server。
  • 拒绝路径穿越、逃逸目标目录的符号链接、凭据型 URL 和未声明的远程下载。
  • 权限、Sandbox、Hooks 和 Subagents 不能证明等价时必须 fail-closed。
  • 来源必须记录 URL/path、解析版本、commit SHA 或内容摘要、license 和转换时间。

实现约束

  • 默认技术栈：TypeScript、Node.js 22、pnpm。
  • Parser、canonical IR、planner、emitter、validator 分层；不得让 source adapter 直接写 DSH 文件。
  • 输出必须确定性：相同输入、规则版本和 DSH 目标版本产生字节级一致结果。
  • 只修改当前任务直接相关文件，不重构无关模块。

验证门禁

  • 每个组件类型至少有正常、降级、拒绝和恶意输入 fixture。
  • 每个修复必须包含回归测试。
  • 支持声明必须有静态 fixture 或真实 DSH headless 行为证据；README 宣称不算完成。
  • 任何权限放宽、脚本执行或兼容状态变化都视为破坏性变更。
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. yesterday First seen · 35 lines · 456 tokens per session scan A 68aba75cfd5b

Subscribe to this mod's changes

dsh-compat AGENTS.md is an instructions file published in the GitHub repository Simidas/dsh-compat (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 456 tokens to every session, about $0.0023 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.

SecurityTestingawesomeclaude-codecodexdeepseek-harnessdshdsh-plugin
Related

Other instructions, from other repositories

awesome-dsh-plugin AGENTS.md

Instructions for beancookie/awesome-dsh-plugin, covering agents.md, 内容来源（source of truth）, 目录结构（每个文件夹的作用）, 添加插件 and 整理流程（分类与数量）.

beancookie/awesome-dsh-plugin · 2,209 tokens

DSH-better-sidebar 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-alpha 适配要点（alpha 通道） and 4. npm 发版（github release → npm publish）.

omdsh-dev/DSH-better-sidebar · 2,881 tokens

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）.

Aisland-SJL/dsh-worktable · 4,863 tokens

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.

imsai-sh/awesome-deepseek-harness-plugins · 1,057 tokens

dsh-config-manager AGENTS.md

Instructions for xiajiajun516/dsh-config-manager, covering agents.md — dsh config manager 仓库协作指南, 🗣️ 语言与交流, 📦 项目概览, 🗂️ 仓库结构与职责 and ui 分层（改动前必读，避免放错层）.

xiajiajun516/dsh-config-manager · 7,380 tokens

dsh-mcp-panel AGENTS.md

Instructions for PerryLink/dsh-mcp-panel, covering agents.md, layout, hard rules applied here, config and build.

PerryLink/dsh-mcp-panel · 1,748 tokens