Seeed-Jetson-DevelopTool: Instructions file for Codex

AGENTS.md

Seeed-Jetson-DevelopTool AGENTS.md is an instructions file for Codex, OpenCode from Seeed-Projects/Seeed-Jetson-DevelopTool. It costs 1,667 tokens per session, scanned A, original, MIT.

Repository instructions for a PyQt6 desktop application that helps Seeed Jetson developers work with devices. They define rule priority and strict conventions for UI styling, components, feedback, internationalization, and device-tool features.

In plain words
What is it for?
Use them before changing the application's interface, especially when adding pages, controls, status feedback, fonts, colors, or other desktop UI elements.
Why use it?
They keep interface changes consistent with the project's design system and prevent common implementation mistakes, such as hard-coded styles or inappropriate dialog boxes.

Instructions file for CodexOpenCode

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

This is Seeed-Projects/Seeed-Jetson-DevelopTool's own configuration. It tells Codex and OpenCode how to work on Seeed-Jetson-DevelopTool 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 Seeed-Jetson-DevelopTool configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Seeed-Projects/Seeed-Jetson-DevelopTool. 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/Seeed-Projects/Seeed-Jetson-DevelopTool/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopTool

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 Seeed-Jetson-DevelopTool AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/seeed-projects/seeed-jetson-developtool/agents-md/github.svg)](https://agentmods.dev/instructions/seeed-projects/seeed-jetson-developtool/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/seeed-projects/seeed-jetson-developtool/agents-md"><img src="https://agentmods.dev/badge/instructions/seeed-projects/seeed-jetson-developtool/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 Seeed-Jetson-DevelopTool AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/seeed-projects/seeed-jetson-developtool/agents-md"><img src="https://agentmods.dev/badge/instructions/seeed-projects/seeed-jetson-developtool/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,667 This file is loaded in full into every session.
When invoked 1,667 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 $0.01667 $0.01667
Opus 5.5 $0.00667 $0.00667
Sonnet 5.5 $0.00333 $0.00333
Haiku 4.5 $0.00167 $0.00167

Measured 4d ago against content hash 3b22fc4f5761, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Seeed-Jetson-DevelopTool 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 4d 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 · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — 项目规则

本文件是 AI 编码代理(Codex / Claude / 同类工具)在本仓库工作时的操作守则。先读它,再动手。

项目一句话

Seeed Jetson Develop Tool:PyQt6(qtpy)桌面客户端,面向 Seeed Jetson 开发者的上位机 —— 烧录、设备诊断、远程开发、应用市场、Skills、OTA、社区。深色科技风 UI。

规则优先级

  1. 用户明确指令(本次会话中最高)
  2. 本文档(AGENTS.md)
  3. design.md(UI 设计规范,唯一权威)
  4. CONTEXT.md(架构背景)
  5. 既有代码里的既有模式(新代码遵循,不是照抄所有历史代码)

任何 UI 改动前必须先读 design.md,并严格遵守。UI 规范冲突时以 design.md 为准。

UI 改动铁律(违反即返工)

  • 颜色 / 字体 / 圆角 / 阴影 token 只允许来自 gui/theme.py 常量;禁止在页面代码写字面量色值。
  • 组件一律用工厂函数:make_button / make_label / make_card / make_input_card / make_section_header / make_log_view / make_input_field / make_tab_button / ShinyProgressBar / StepIndicator / StatusBadge / EmptyStateWidget / ToastNotification。
  • 禁止原生 QMessageBox;用 theme.show_info_message / show_warning_message / show_error_message / ask_question_message。
  • 字号必须经 pt()(Windows DPI 缩放);font-family 走 build_app_font() / build_mono_font(),不硬编码。
  • Emoji 必须彩色:含 emoji 的 QLabel 用 make_label() 或 set_emoji_font_for_label()。
  • 新页面继承 widgets/page_base.PageBase;筛选列表页继承 widgets/list_page_base.ListPageBase。禁止脱离设计系统自建页面骨架。
  • 操作反馈:Toast 通知 + StatusBadge;禁止用"日志追加一行"代替操作反馈。
  • 空状态用 EmptyStateWidget,禁止裸 "No data"。
  • 耗时操作必须 QThread + 信号回主线程,禁止阻塞 UI。
  • QGraphicsDropShadowEffect 不与高频 QTimer 重绘叠加(Windows 崩溃史);阴影对象销毁时 clear_shadow()。

国际化铁律

  • 文案唯一入口:seeed_jetson_develop.gui.i18n.t(key, **kwargs)。
  • **禁止使用 gui/runtime_i18n.py(已废弃)**及其 ZH_EN_EXACT 字典方式。
  • 新文案必须同时写入 locales/en/<module>.json 与 locales/zh-CN/<module>.json。
  • Key 命名:<module>.<区域>.<名称> 小写点分式,如 ai_chat.btn.send、skills.search.placeholder。
  • 占位符用 {name}(str.format);支持 t("…", lang=…) 与运行时 retranslate_ui() 切换。

代码地图

run_v2.py                        # 启动入口(python3 run_v2.py [--debug-console])
seeed_jetson_develop/
  gui/
    theme.py                     # ★ 设计 token + 组件工厂(唯一权威)
    styles.py                    # 旧版浅色 QSS(历史兼容,新代码勿扩展)
    ai_chat.py                   # AI 悬浮球入口(点击进入 Agent 页,inject_* 转发)
    i18n.py                      # ★ 现代 key 式国际化
    runtime_i18n.py              # 已废弃,禁止使用
    main_window_v2.py            # 主窗口组装
    widgets/                     # ★ 组件库:page_base / list_page_base / empty_state /
                                 #   toast_notification / loading_spinner / breathing_* /
                                 #   animated_* / ripple_button / focus_ripple_edit / ...
  modules/<flash|devices|apps|skills|agent|remote|ota|community>/
    page.py                      # 各功能页(迁移目标:全部基于 PageBase)
    thread.py / *.py             # 后台线程与业务逻辑
  modules/agent/                 # ★ AI Agent 页:复用本机 claude/codex CLI 驱动 Jetson/
                                 #   Physical AI(backend.py 流式包装 / cli_tools.py CLI
                                 #   检测与 skills 目录约定 / agent_setup_dialog.py 本机补装)
  locales/en|zh-CN/*.json        # 双语文案
  skills/{openclaw,claude,codex}/<slug>/  # ★ 内置技能库(运行时读取此包内树):
                                 #   openclaw→SKILL.md、claude→CLAUDE.md、codex→AGENTS.md,
                                 #   内容相同仅 marker 文件名不同;references/scripts 子目录原样。
                                 #   仓库顶层 skills/ 是同构副本,新增技能时两棵树都要同步。
  data/                          # BSP / 产品图 / Recovery 元数据
  core/                          # events(事件总线) / runner / config ...
design.md                        # ★ UI 设计规范(改动 UI 先读它)
AGENTS.md                        # 本文件
CONTEXT.md                       # 架构演进背景

Read the full file on GitHub · 92 lines

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. 4d ago Changed · +7 lines · +186 tokens per session 3b22fc4f5761
  2. 1mo ago First seen · 85 lines · 1,481 tokens per session scan A e227fc1bb401

Subscribe to this mod's changes

Seeed-Jetson-DevelopTool AGENTS.md is an instructions file published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (56 stars, last pushed yesterday), licensed MIT. It adds 1,667 tokens to every session, about $0.0067 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 2026-09-23.

Related

Other instructions, from other repositories