Borrowing it
Nothing to install: this file belongs to lawliet206/ROS. 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/lawliet206/ROS/main/AGENTS.mdgit clone --depth 1 https://github.com/lawliet206/ROSWrote 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/lawliet206/ros/agents-md)<a href="https://agentmods.dev/instructions/lawliet206/ros/agents-md"><img src="https://agentmods.dev/badge/instructions/lawliet206/ros/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/lawliet206/ros/agents-md"><img src="https://agentmods.dev/badge/instructions/lawliet206/ros/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 | $0.01724 | $0.01724 |
| Opus 5.5 | $0.00690 | $0.00690 |
| Sonnet 5.5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
ROS 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 2mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本文件是给 Coding Agent(Claude Code / Cursor / OpenCode 等)的项目级指南。 目标:让 Agent 在不破坏现有功能的前提下,正确、安全地修改本仓库。
项目是什么
ROS Noetic + ESP32 + J1900 + LiDAR 两轮差速自主移动机器人平台。
- 三机架构:PC(ROS Master,跑 SLAM/导航/视觉)←WiFi→ J1900(车载,雷达驱动 + 摄像头采集)←USB→ ESP32(电机 PID + 编码器里程计 + IMU,rosserial)。
- 核心功能:S9 雷达 SLAM 建图(gmapping)、AMCL + move_base + TEB 多点导航、EKF 里程计/IMU 融合、视觉+雷达融合人体跟随、Gazebo 仿真。
环境版本(不可随意升级/降级)
| 组件 | 版本 |
|---|---|
| OS | Ubuntu 20.04 (Focal) |
| ROS | Noetic(PC 与 J1900 均安装) |
| Python | 3.8(ROS 依赖)+ 3.x(视觉依赖 ultralytics/cv2 可在 PC 单独装) |
| 固件 IDE | Arduino IDE / arduino-cli,支持 ESP32 core 2.x |
| 编译 | catkin_make(不用 catkin tools 的混合布局) |
目录结构(catkin 工作空间根 = 仓库根)
src/robot_bringup/ # ★ 实物包(PC 与 J1900 都要编译部署)
launch/ # bringup / slam / navigation / follow / follow_vision / ekf / odom_ekf
scripts/ # robot_start.sh j1900_start.sh + 6 个 Python 节点
config/ # ekf.yaml patrol_goals.yaml slam.rviz
urdf/robot.urdf # 实物模型(轮距 0.180 m)
src/robot_sim/ # 仿真包(仅 PC)
launch/ # simulation / sim_slam / sim_navigation
scripts/ # sim_slam.sh / sim_navigation.sh / sim_follow.sh
urdf/worlds/rviz/config
esp32_firmware/ # ESP32 固件(独立于 ROS,用 Arduino 编译)
esp32_firmware.ino # ★ 主固件:PCNT 编码器 + 双路 PID + MPU6050 + rosserial
esp32_board_test/ # 板级测试固件(单项验证)
libraries/ros_lib/ # vendored rosserial Arduino 库(已修复 ESP32 ros.h 兼容,勿随意改)
tests/ # pytest 纯逻辑回归测试(协议解析 / 状态机 / 角度换算)
tools/ # 调试工具(不入部署链)
docs/ # 架构文档 / 开发指南 / 论文
重要 launch 与脚本(命名与参数以代码为准,改文档必须同步)
- 实物一键总控(PC 执行):
bash src/robot_bringup/scripts/robot_start.sh {slam|patrol|follow|stop|status} - 车载一键(J1900 执行 / robot_start.sh 通过 SSH 自动调用):
bash src/robot_bringup/scripts/j1900_start.sh {base|vision|stop|status} - 仿真:
bash src/robot_sim/scripts/sim_slam.sh/sim_navigation.sh [map.yaml]/sim_follow.sh - 关键 launch:
slam.launch(gmapping)、navigation.launch(map_server+AMCL+move_base+TEB)、follow_vision.launch(YOLO+雷达融合跟随)、odom_ekf.launch(EKF 节点唯一来源,被 slam/navigation/ekf include,不要重复定义 EKF 节点)。 - 雷达型号切换:
bringup.launch的lidar_model参数(s9_fsrd/ydlidar_x4等)。
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.
- 2mo ago First seen · 87 lines · 1,724 tokens per session scan A d18e65c416ce
ROS AGENTS.md is an instructions file published in the GitHub repository lawliet206/ROS (106 stars, last pushed 27d ago), licensed MIT. It adds 1,724 tokens to every session, about $0.0069 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.
ROS AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ROS AGENTS.mdlawliet206/ROS | Instructions file | 106 | 27d ago | MIT | A | 1,724 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |