What is alpha_viam_rover AGENTS.md?

A project guide for a Viam Rover v2 robot running ROS 2, a software framework for controlling robots, on a Raspberry Pi 4. It describes the code areas, navigation hardware, safety process, and required testing evidence.

Use it when working on robot startup, sensors, motors, navigation, cameras, CAN devices, hardware models, configuration, or acceptance tests.

It helps agents locate the right robot subsystem and follow the project’s safety and verification practices before making high-impact changes.

alpha_viam_rover AGENTS.md — Instructions file for Codex and OpenCode by alpharover: A project guide for a Viam Rover v2 robot…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/alpharover/alpha_viam_rover/agents-md

Clone the repo

git clone --depth 1 https://github.com/alpharover/alpha_viam_rover

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/alpharover/alpha_viam_rover/agents-md.svg)](https://agentmods.dev/instructions/alpharover/alpha_viam_rover/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/alpharover/alpha_viam_rover/agents-md"><img src="https://agentmods.dev/badge/instructions/alpharover/alpha_viam_rover/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,004 This file is loaded in full into every session.

When invoked 1,004 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.01004	$0.01004
Opus 5	$0.00502	$0.00502
Sonnet 5	$0.00201	$0.00201
Haiku 4.5	$0.00100	$0.00100

Measured 4d ago against content hash c072f251fadd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

alpha_viam_rover 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 · 80 lines

What it actually says

Viam Rover v2 — Agent Operating Guide (ROS 2 Humble, RPi4)

Purpose Teach coding agents (and humans) how to work on this robot. Use this file to find the right sub‑guides, follow safety rules, and record progress.

Repository shape

bringup/ — OS/ROS bring‑up and launch orchestration
drivers/ — IMU (MPU‑6050), power (INA219), encoders, motor HW (L298N)
nav/ — robot_localization, slam_toolbox, Nav2
perception/ — RGB/Depth camera stacks (future; may move to Jetson)
can/ — SocketCAN (Waveshare MCP2515) + servo control
configs/ — ros2_control, controller configs, QoS, DDS XML
urdf/ — robot model + ros2_control tags
docs/ — ADRs, bring‑up checklists, hardware, Foxglove/MCAP
tests/ — bench and acceptance scripts
bags/ — short MCAP samples and context readme

How agents should navigate

Read this file.
Open the nearest AGENTS.md in your working directory (drivers, nav, etc.). The nearest file overrides the root for local tasks. (Agents)
Log progress in AGENTS_PROGRESS.md (root) after each task.
For any high‑impact change, follow the Escalation procedure below.

Build / test / evidence (always)

Bootstrap with rosdep; build with colcon; tests green; ros2 doctor clean.
Record a short MCAP bag for anything that moves, measures, or maps; add link in your PR and in AGENTS_PROGRESS.md. (Use Git LFS if bags exceed normal repo limits.) (GitHub Docs, Git Large File Storage)

Progress tracking (required) Update AGENTS_PROGRESS.md after each unit of work with:

Task ID (issue/PR), phase, subsystem, files touched
Outcome (pass/fail against acceptance tests)
Evidence links (MCAP in bags/samples/, Foxglove layout JSON, screenshots)
Follow‑ups or risks Keep entries terse and append‑only.

Documentation rules

Decisions → add/update a 1‑page ADR in docs/ADR/ and link it in your PR.
Configs → change the YAML in configs/ (don’t scatter settings).
Hardware/pin changes → update hw/pinmap.yaml and docs/hw/*.

Safety & guardrails (do not bypass)

Motors disabled on boot; watchdog on /cmd_vel; E‑stop documented.
Respect REP‑103/105 frames/units (map/odom/base_link, SI).
Never hard‑code secrets.
Don’t change topic names or message types without an ADR and approval.

Escalation procedure (architect approval required) Mark PR with label needs-architect and request review from @PROJECT_ARCHITECT_HANDLE for any change that touches:

Motor control (ros2_control HW, PWM ranges, watchdogs)
GPIO/pin maps, I²C addresses, or power paths
Message schemas / topic names / TF tree
DDS networking, multi‑robot namespace/DOMAIN_ID, discovery config
SLAM/Nav2 planners or costmaps
Any hardware addition or driver swap Enforcement: CODEOWNERS requires architect review on protected paths, and branch protection requires an approving review before merge. (GitHub Docs)

Monorepo pattern Large repos may ship nested AGENTS.md in subfolders; the nearest one governs. Keep this root file short and link out. (Agents)

Sub‑guides (agents open these next)

bringup/AGENTS.md — install, launch, health checks
drivers/AGENTS.md — IMU/INA219/encoders/L298N specifics
nav/AGENTS.md — EKF, SLAM, Nav2
perception/AGENTS.md — cameras/depth (future)
can/AGENTS.md — SocketCAN + servos

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.

4d ago First seen · 80 lines · 1,004 tokens per session scan A c072f251fadd

Subscribe to this mod's changes

alpha_viam_rover AGENTS.md is an instructions file published in the GitHub repository alpharover/alpha_viam_rover (11 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 1,004 tokens to every session, about $0.0050 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 2026-08-30.

Hardware and IoT

alpha_viam_rover AGENTS.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other instructions, from other repositories

firmware CLAUDE.md

Tutorial_AwesomeModernCPP AGENTS.md

brilliant_sdk AGENTS.md

NeoMind CLAUDE.md

zmk-config AGENTS.md

ext-apps CLAUDE.md