Borrowing it
Nothing to install: this file belongs to alfredxw/denova. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alfredxw/denova/master/AGENTS.mdgit clone --depth 1 https://github.com/alfredxw/denovaWrote 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/alfredxw/denova/agents-md)<a href="https://agentmods.dev/instructions/alfredxw/denova/agents-md"><img src="https://agentmods.dev/badge/instructions/alfredxw/denova/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.
<a href="https://agentmods.dev/instructions/alfredxw/denova/agents-md"><img src="https://agentmods.dev/badge/instructions/alfredxw/denova/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03677 | $0.03677 |
| Opus 5.5 | $0.01471 | $0.01471 |
| Sonnet 5.5 | $0.00735 | $0.00735 |
| Haiku 4.5 | $0.00368 | $0.00368 |
Grade A, and why
denova 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 10d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目目标
面向创作者的 AI 创作工具,支持完整创作流程与游戏交互。
设计与代码
- 一步完成功能性需求与必要验证,选择最简单完整、长期可维护的方案;到位不要求消除所有无关瑕疵。鼓励在相关职责内扩大改动以降低总代码量或复杂度,明确收益和边界;收益不成立时保持局部,不无限扩大重构。避免投机抽象、配置和临时方案,不以未完成的复杂改造破坏现有流程。
- 优先复用已有组件、抽象和依赖,先查文档与类型;成熟依赖能降低复杂度时优先采用。提示词需求优先评估 Skills,工具需求优先评估已有 Tools / Bash Execute。
- 模块按职责和变化原因组织,保持高内聚、低耦合,避免杂项包和过度拆分。高频变更文件接近 500 行、超过 800 行时分别加强职责与复杂度审查;行数是提醒,不是先拆分才能修复的门槛。在原职责内的小修复可直接完成,新增独立职责应拆分。
- 不为缩短代码新增一次性 helper;仅在澄清概念、隔离复杂逻辑、复用边界或改善测试时抽取。模块默认私有,仅暴露调用方需要的 API。
- 避免含义不清的布尔值或
nil参数,使用具名配置、枚举或语义明确的方法。穷尽处理有限状态、事件和消息类型,不用默认分支吞掉新增状态。 - 新接口、状态类型、Agent 能力和跨模块抽象需说明职责与调用约束;涉及用户参与的设计决策,保留清楚的原因注释。
- goroutine 必须有 recover 边界,优先复用已有执行封装;恢复后记录错误并完成必要清理,不静默吞掉 panic。
- 前后端的关键操作、状态变化和失败应有可定位日志,说明操作与原因,文件和行号由日志机制提供。注释、日志、内部错误和终端固定输出使用英文。
- 遇到不熟悉的功能,不要立即从零实现。先检索 GitHub 上维护活跃、许可证明确的同类开源项目,比较实现思路、依赖和已知问题。优先借鉴经过验证的设计,不要直接复制不兼容或来源不明的代码。
产品与交互
- 写作、游戏与共通能力是并列一级菜单;点击只进入对应目的地,不维护额外全局模式,不提供模式切换器,任何时候只有一个一级菜单高亮。
- 共通能力的设计和验证必须覆盖写作与游戏,尤其是布局、导航、会话、设置和版本管理。
- 所有用户可见交互、文案、错误和空状态提供独立中英文资源,按当前语言单语展示;用户错误通过本地化 message / error key 呈现。
- UI 优先使用 shadcn/ui 和已有组件、编辑器依赖。主题以暗色黑、浅色白为底,少量红黄绿点缀;检查两种主题,使用自适应布局,避免固定宽度。
- Avoid unnecessary secondary labels and descriptions. Let the layout do the explaining.
- 列表通过点击整个父项展开或收起,不只允许点击左侧箭头。
Agent 与模型上下文
agent/是独立的 Native Agent Runtime,不感知外部 runtime、产品运行时选择或多 runtime 调度。Native、Codex、Claude 等运行时的选择、适配、能力差异和共通产品控制由 Denova 应用层承担;不得通过给agent.Definition、Session 或其执行循环注入外部 runtime 来实现切换。共通 UI 和产品 journal 可以复用,但不能因此把应用层编排职责下沉到agent/。- 应用层的多 runtime 能力聚合在
internal/agents/runtime独立 package 中,不新增 Go module,也不以搬进internal/app代替抽象分层。产品层通过绑定会话的统一接口使用控制和状态;Native 执行与外部协议适配保持隔离,产品上下文准备和领域提交仍由产品层负责。运行时已有的 Plan/Todo 由运行时执行,应用只保存已确认的快照并复用展示组件,不提供第二套可写 Todo 工具。原生能力优先,但应权衡协议适配成本,不能为了统一表面行为扩大实现范围。 - 游戏不支持 Goal,UI、API 与执行层均不得开启 Goal。写作和通用对话可统一 Goal 的产品入口与状态展示,但 Native Goal 的执行和验收由独立 Native runtime 负责,不能与外部 runtime 的执行实现混合。
- Denova 内置的提示词、上下文片段、工具与 schema 描述、模型可见工具反馈统一使用英文,不重复注入双语;保持产品中立,不提及或类比其他 Agent 产品、CLI 或品牌。对照研究仅放在审计文档中。
- Skill 文档及其参考资料允许使用中文,不受内置提示词的英文限制。
- 上下文改动优先保护缓存前缀匹配;每个注入片段必须有明确来源、用途和容量上限,上限应覆盖合理使用规模,并明确超限处理,避免随意截断。
- 模型输出与工具输入 schema 应容忍可修正的错误;列表操作尽量支持逐项成功或失败,避免局部错误导致整批昂贵重试。
- LLM 任务默认不限总运行时间和迭代次数,不写死强制中断上限;确有安全或循环控制需求时提供可配置限制,并保留用户取消能力。连接建立、测试等待等基础设施边界不属于 LLM 总运行时长限制。
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.
- 10d ago Changed · +1 lines · +15 tokens per session 1434b44787e9
- 12d ago Changed · +1 lines · +69 tokens per session d9b9e0356674
- 17d ago Changed · +1 lines · +21 tokens per session 94da2f5b930e
- 21d ago Changed · +1 lines · +38 tokens per session 51aee8f1915e
- 23d ago Changed · +20 lines · +337 tokens per session bf471431b98a
- 1mo ago Changed · +2 lines · +117 tokens per session f2b2ee380d3d
- 1mo ago Changed · +3 lines · +315 tokens per session 8e1649ad330a
- 1mo ago Changed · +138 tokens per session f43c8b2017ab
- 2mo ago Changed · -22 lines · -460 tokens per session 7e17f0419a94
- 2mo ago First seen · 101 lines · 3,087 tokens per session scan A c7224b58a862
denova AGENTS.md is an instructions file published in the GitHub repository alfredxw/denova (986 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,677 tokens to every session, about $0.0147 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 2026-08-30.
denova AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| denova AGENTS.mdalfredxw/denova | Instructions file | 986 | yesterday | Apache-2.0 | A | 3,677 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |