AGENTS.md@lampOSA

This file is byte-identical to the first copy the registry indexed, one of 3 indexed copies. Same content hash, so the same checks give both the same grade.

AGENTS.md@lampOS from autonomous-ai/physical-ai-operating-system is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add autonomous-ai/physical-ai-operating-system/lampOS/AGENTS.md@git:20261109.c8a80a9

Pins git:20261109.c8a80a9 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
autonomous-ai/physical-ai-operating-system
Path
lampOS/AGENTS.md
Versions recorded
5
Latest version
git:20261109.c8a80a9, committed Nov 9, 2026
First version recorded
Nov 4, 2026
Size
13,040 bytes
Repository stars
578
License
Apache-2.0

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# lampOS development rules

Treat this directory as the root of a standalone repository. Follow the
[V2 live interaction scope](docs/architecture.md).

A session that opens with "you are <name>" is a builder's: read [joining.md](docs/joining.md) as it is on `origin/lamp-voice` and follow its "Starting a session".

## How builders work together

This is the protocol in brief, current on 4 November 2026. [joining.md](docs/joining.md)
has the whole of it; where an older note differs, this section is current.
It replaces the three-agent `harness send` route of 12 October.

- **Who decides.** Since the cutover at 4 November 11:00 GMT+7 the PM, an
  agent in the Harness Swarm (Faye), holds the first builder's old PM role:
  it opens and labels issues, keeps each builder's list and the Queue in
  order, assigns work, runs the train bot, promotes to stable and posts the
  hourly figures. The first builder stays on as a builder and the lamp-4ace
  tester. Product calls are the project lead's, and the lead's agent (V2)
  speaks for the lead. Where this file says "the first builder" for one of
  the PM's jobs above, an older note is meant: read the PM.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add autonomous-ai/physical-ai-operating-system/lampOS/AGENTS.md@sha256:7089a80700667084

The line at the top of this page pins the label git:20261109.c8a80a9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wxemnbg547n7y5eq.svg)](https://markdownregistry.com/a/art_wxemnbg547n7y5eq)

2 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in autonomous-ai/physical-ai-operating-system/lampOS/AGENTS.md since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of AGENTS.md from somewhere else? Ask it: where did my AGENTS.md come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 5 versions of this file, between Nov 4, 2026 and Nov 9, 2026, about one every day.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261109.c8a80a9 latest2026-11-09 c8a80a9 13,040 BA view · diff
git:20261104.a80f8572026-11-04 a80f857 12,734 BA view · diff
git:20261104.1429e4e2026-11-04 1429e4e 12,460 BA view · diff
git:20261104.a450fd22026-11-04 a450fd2 12,376 BA view · diff
git:20261104.f749db32026-11-04 f749db3 12,611 BA view
Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (13040 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

autonomous-ai/physical-ai-operating-system · 578 stars · license Apache-2.0 · pushed 2026-11-19 · branch lamp-voice

API

GET https://markdownregistry.com/api/v1/artifacts/art_wxemnbg547n7y5eq
GET https://markdownregistry.com/api/v1/resolve?ref=autonomous-ai/physical-ai-operating-system/lampOS/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/7089a807006670842e097daa89bd87e8828019e6764148e595afc51f42d52b9d

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from autonomous-ai/physical-ai-operating-system

architecture Cursor rule
autonomous-ai/physical-ai-operating-system · .cursor/rules/architecture.mdc · Architecture and coding conventions for AI Lamp OpenClaw
git:20260324.7a91f3b · audit A · 578 stars
docs-on-code-change Cursor rule
autonomous-ai/physical-ai-operating-system · .cursor/rules/docs-on-code-change.mdc · Update docs (markdown) when code changes
git:20260330.9f1fe92 · audit A · 578 stars
multi-ide Cursor rule
autonomous-ai/physical-ai-operating-system · .cursor/rules/multi-ide.mdc · Multi-IDE (Cursor + Claude Code) conventions
git:20260324.7a91f3b · audit A · 578 stars
testing Cursor rule
autonomous-ai/physical-ai-operating-system · .cursor/rules/testing.mdc · Testing conventions
git:20260324.7a91f3b · audit A · 578 stars
AGENTS.md AGENTS.md file
autonomous-ai/physical-ai-operating-system · AGENTS.md
git:20261021.2153b76 · audit A · 578 stars
CLAUDE.md CLAUDE.md file
autonomous-ai/physical-ai-operating-system · CLAUDE.md
git:20261021.2153b76 · audit A · 578 stars
DESIGN.md@docs/architecture DESIGN.md file
autonomous-ai/physical-ai-operating-system · docs/architecture/DESIGN.md
git:20260817.947aa36 · audit A · 578 stars
claude-code-buddy SKILL.md skill
autonomous-ai/physical-ai-operating-system · integrations/companions/claude-desktop-buddy/claude-code-buddy/SKILL.md · Push Claude Code activity to the user's device (e.g. a lamp) over the LAN. The plugin POSTs semantic events to a…
git:20260720.8045490 · audit B · 578 stars
claude-buddy SKILL.md skill
autonomous-ai/physical-ai-operating-system · integrations/companions/claude-desktop-buddy/skill/SKILL.md · MOVED — canonical skill now lives in the platform skills tree.
git:20260720.bfdb5de · audit A · 578 stars
CLAUDE.md@lampOS CLAUDE.md file
autonomous-ai/physical-ai-operating-system · lampOS/CLAUDE.md
git:20261021.a47f2f5 · audit A · 578 stars
agenda-count SKILL.md skill
autonomous-ai/physical-ai-operating-system · lampOS/crates/tasks/src/make_examples/agenda-count/SKILL.md · When I say count my day, the lamp's agent counts my calendar events left today.
git:20261119.f0fc9bb · audit A · 578 stars
relaxing-music SKILL.md skill
autonomous-ai/physical-ai-operating-system · lampOS/examples/relaxing-music/SKILL.md · Play one quiet, 48-second original instrumental piece only when the person speaking to the lamp explicitly asks for…
git:20261109.d4e4e85 · audit A · 578 stars

Every file in autonomous-ai/physical-ai-operating-system

Other files named AGENTS.md@lampOS

AGENTS.md@lampOS AGENTS.md file
autonomous-ai/lampos · lampOS/AGENTS.md
git:20261109.c8a80a9 · audit A · 568 stars
AGENTS.md@lampOS AGENTS.md file
autonomous-ai/autonomous-os · lampOS/AGENTS.md
git:20261109.c8a80a9 · audit A · 577 stars

Browse by kind, by grade A, or by owner.