oh-story-dsh: Instructions file for Codex

AGENTS.md

oh-story-dsh AGENTS.md is an instructions file for Codex, OpenCode from zenstory-ai/oh-story-dsh. It costs 890 tokens per session, scanned A, original, MIT.

Repository instructions for the oh-story-dsh community plugin, which adds creative workspaces to DeepSeek Harness (DSH), a web application. They describe how to manage copied upstream assets, verify changes, and publish releases.

In plain words
What is it for?
Use them when modifying the plugin, syncing story, drama, game, or video skills, running checks, recording decisions, or preparing an npm release.
Why use it?
They reduce mistakes when changing a plugin that depends on fixed upstream files and has separate checks for code, assets, integration, and releases.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is zenstory-ai/oh-story-dsh's own configuration. It tells Codex and OpenCode how to work on oh-story-dsh 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 oh-story-dsh configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zenstory-ai/oh-story-dsh. 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/zenstory-ai/oh-story-dsh/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/zenstory-ai/oh-story-dsh

Made for: Codex, OpenCode.

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 oh-story-dsh AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zenstory-ai/oh-story-dsh/agents-md/github.svg)](https://agentmods.dev/instructions/zenstory-ai/oh-story-dsh/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zenstory-ai/oh-story-dsh/agents-md"><img src="https://agentmods.dev/badge/instructions/zenstory-ai/oh-story-dsh/agents-md/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 oh-story-dsh AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zenstory-ai/oh-story-dsh/agents-md"><img src="https://agentmods.dev/badge/instructions/zenstory-ai/oh-story-dsh/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 890 This file is loaded in full into every session.
When invoked 890 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00890 $0.00890
Opus 5.5 $0.00356 $0.00356
Sonnet 5.5 $0.00178 $0.00178
Haiku 4.5 $0.00089 $0.00089

Measured 13d ago against content hash fc2616f015a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oh-story-dsh 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 13d 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.md · 28 lines

What it actually says

AGENTS.md

oh-story-dsh 是 DeepSeek Harness(DSH)的社区插件,发布一个包 @oh-story/dsh(packages/dsh-plugin),给 DSH Web 加小说、短剧、游戏、视频解说四个创作工作台。Agent、会话、模型与权限归 DSH,插件只加 Skills、Roles、项目文件协议和界面;归属边界见 docs/ARCHITECTURE.md。环境、测试分层与 CI 见 CONTRIBUTING.md。

固定上游资产

  • packages/knowledge/{oh-story,drama,novel-to-game,video-recap} 是四套上游 Skills 的固定副本,manifest.json 记录上游仓库、commit 与逐文件哈希。不要手工修改这些目录。
  • 只用 pnpm assets:sync:{story,drama,game,video}(或 pnpm assets:sync 全部)从相邻 checkout 同步,再跑 pnpm assets:check;同步提交连同 manifest 一起评审,CHANGELOG.md 写清上游版本号与提交。上游路径与破坏性版本的要求见 CONTRIBUTING.md「上游知识资产」。

验证

  • 报告完成前运行 pnpm verify(lint、类型、资产完整性、DSH 边界、单测与构建)。单独检查可用 pnpm lint、pnpm typecheck、pnpm assets:check、pnpm test。
  • 发版前运行 pnpm verify:release(verify 加打包后原生 DSH Web 集成测试)。
  • pnpm test:dsh:real 与 pnpm demo 调用真实 DeepSeek,只在发布前观察 provider 兼容性或重做演示图时运行;缺凭据的 skipped 不算 passed。凭据只放环境变量或临时 Key 文件,不写入仓库。

发布

只按 docs/RELEASING.md 发布:版本、安装示例与 CHANGELOG.md 先更新,经受保护的 PR 合入 main 且该提交的 main CI 四个 Job 全部通过后,才在该提交打与包版本一致的 v<package-version> Tag,由 release.yml 发布。不要移动 Tag、覆盖已发布资产,也不要绕过工作流手动发 npm。CHANGELOG.md 只记用户可见变更,正文中文。

决策笔记

非平凡改动(行为、架构、跨模块契约、流程或工具、测试策略、磁盘格式)在 .agents/notes/{proposed,implemented,rejected}/{feature,bug-fix,simplification,architecture,process,testing}/yyyy-mm-dd-topic.md 留笔记,日期取该决定首次出现的提交,遵循 DeepSeek Harness agent-notes 约定。

  • 先在 .agents/notes/ 找已有笔记:决定不变就原地更新事实;决定反转就开新笔记并链接旧笔记,不把 ## Decision 改成相反内容。
  • 新想法放 proposed/,与代码同一提交移到 implemented/。格式化、改名、版本号等机械改动不需要笔记。
  • 笔记开头是 # Agent Note: <标题>、空行、Status: <状态>;正文中文、小节标题英文:## Problem、## Decision(现在时)或 ## Proposal、## Alternatives considered、## Consequences(proposed/ 与 rejected/ 用 ## Risks),结尾给 来源: 提交列表或 ## Verification。
  • 不建 INDEX.md,目录本身就是状态。
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. 13d ago First seen · 28 lines · 890 tokens per session scan A fc2616f015a1

Subscribe to this mod's changes

oh-story-dsh AGENTS.md is an instructions file published in the GitHub repository zenstory-ai/oh-story-dsh (629 stars, last pushed today), licensed MIT. It adds 890 tokens to every session, about $0.0036 per session on Opus 5.5. 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 2026-10-15.

Related

Other instructions, from other repositories