Borrowing it
Nothing to install: this file belongs to shchnk1103/Universe-Keyboard. 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/shchnk1103/Universe-Keyboard/main/AGENTS.mdgit clone --depth 1 https://github.com/shchnk1103/Universe-KeyboardWrote 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/shchnk1103/universe-keyboard/agents-md)<a href="https://agentmods.dev/instructions/shchnk1103/universe-keyboard/agents-md"><img src="https://agentmods.dev/badge/instructions/shchnk1103/universe-keyboard/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/shchnk1103/universe-keyboard/agents-md"><img src="https://agentmods.dev/badge/instructions/shchnk1103/universe-keyboard/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 | $0.02132 | $0.02132 |
| Opus 5 | $0.01066 | $0.01066 |
| Sonnet 5 | $0.00426 | $0.00426 |
| Haiku 4.5 | $0.00213 | $0.00213 |
Grade A, and why
Universe-Keyboard 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 2d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本仓库的 AI 协作规则。所有 agent 在开始工作前必须先阅读本文件。
基本沟通规则
- 始终使用中文回复。
- 除非用户明确要求实施或修改,否则先讨论方案,不直接改文件。明确授权后,在该任务范围内持续推进;不因加载技能、角色切换或上下文压缩重复请求相同授权。
- 代码改动必须优先保证可读性。
- 可以适当增加注释,但注释应解释意图、边界或复杂原因,避免复述代码。
- 遇到不确定问题时,先核查事实并区分假设。已授权范围内的常规实现选择可自主决定;影响产品合同、权限、必需证据或不可逆动作的缺口才请求决定。
- 适当使用第一性原理分析:输入是什么、状态在哪里、副作用是什么、输出如何验证。
工作入口
新会话开始时先阅读:
AGENTS.mddocs/KNOWLEDGE_INDEX.mddocs/ACTIVE_WORK.md(当前 Active 工作项 ≤10;生命周期以 Assignment 为准)- 按
docs/READING_MAPS.md中的任务类型加载对应文档 - 涉及代码改动时再阅读
docs/PROJECT_CONTEXT.md - 运营卫生规则见
docs/kos/kos-2.1-operational-maturity.md(不替代 KOS 2.0 冻结原则) - KOS 2.2 目前为 advisory,Adopted pin
v0.7.0:入口是docs/kos/UPGRADE_STATUS.md与.kos/project.json。校验绿不是 Product / merge / Release。未授权required。
CONTEXT_INDEX.md 保留为详细文档注册表,不再是新会话的第一导航入口。
需要确定长期团队所有权、跨线程协作或永久线程 bootstrap 时,阅读 docs/VIRTUAL_ENGINEERING_TEAM.md。
正式任务进入 Ready 或开始执行前,必须按 docs/ASSIGNMENT_POLICY.md 核对 Assignment;任何必需字段为 UNKNOWN 时停止并交回 Product Lead。边界明确的只读问题使用该 Policy 的例外。阶段依赖与当前授权解释见 docs/AI_WORKFLOW.md。
需要领域 agent 时,必须选择 docs/playbooks/ 下的对应操作手册,并遵守其停止、交接和证据规则。
调试原则
- 根因不清楚时,不要直接猜修。
- 优先增加精准日志、复现路径和观测点。
- 对输入法卡死、延迟、候选异常、RIME session 异常等问题,先区分:
- UI 主线程问题
- KeyboardCore 状态机问题
- RIME session / bridge 问题
- App Group / 文件系统 / 部署状态问题
- 日志必须放在能缩小问题范围的位置,避免无意义刷屏。
- 输入热路径中的日志和持久化不能同步阻塞按键处理。
修改边界
- 不做与任务无关的重构。
- 不随意改动 RIME 部署边界:主 App 可部署,Keyboard Extension 运行期只处理 session。
- 不用
@unchecked Sendable或不安全隔离来绕过 Swift 6 并发问题。 - UI 改动必须遵守
docs/UI_STYLE_GUIDE.md。 - 修改
Packages/KeyboardCore时优先补充或更新单元测试。 - 修改历史、决策或已知限制时,更新对应文档,不把流水账塞进
docs/PROJECT_CONTEXT.md或CLAUDE.md。
GitHub 发布与分支清理
- Codex 沙箱内的 GitHub CLI 认证失败不得单独解释为 token 过期。先按
docs/kos/codex-github-cli-auth-troubleshooting.md做一次沙箱/主机对照;主机成功后停止重复登录,不猜测或复用旧代理配置。 - 发布按用户授权的具体动作推进:commit、push、PR、merge、Release 分别核对范围。仅要求本地提交不推送;推送使用边界清晰的功能分支。技能不能扩展外部动作权限。
- 合并 / 视为可合并之前,必须先在本地跑通与 CI 等价的质量门(见下「本地 CI 门禁」)。禁止在相关套件未绿时推送并请求合并到默认分支;若用户明确说「只推不合并 / 草稿 PR」,可推功能分支但必须在报告中写明本地未跑或未绿的步骤。
- “已推送功能分支”不等于“可以清理分支”。PR 未合并、检查失败或远端状态无法确认时,必须同时保留本地和远端功能分支。
- 只有在拉取最新远端状态后,确认该工作的提交已经可从
origin的默认分支到达,才允许清理功能分支。 - 清理时先同步默认分支,再使用安全删除方式删除本地分支;确认远端默认分支仍包含对应提交后,才删除远端功能分支。禁止用强制删除掩盖未合并状态。
- 发布与清理过程必须报告提交、远端分支、PR、合并可达性检查和实际删除结果;任一步失败都停止清理并保留可恢复检查点。
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.
- 2d ago Changed · +3 lines · +178 tokens per session ed5113d3342f
- 4d ago Changed · +13 tokens per session 5285e08f2771
- 9d ago First seen · 99 lines · 1,941 tokens per session scan A ec242f69bd51
Universe-Keyboard AGENTS.md is an instructions file published in the GitHub repository shchnk1103/Universe-Keyboard (5 stars, last pushed yesterday), licensed MIT. It adds 2,132 tokens to every session, about $0.0107 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
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.