What is bagel AGENTS.md?

Instructions for Bagel, a tool that analyses robotics and IoT data files through a chat connection. It uses SQL, a language for querying data, to answer questions about recorded messages.

Use it to start Bagel with Docker, connect it over SSE, analyse ROS, PX4, ArduPilot, Betaflight, or IoT files, and check the queries used for answers.

It explains how to install Bagel, connect an AI coding tool to it, inspect data sources, and avoid doing data calculations manually.

How Extelligence-ai/bagel configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Extelligence-ai/bagel. 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/Extelligence-ai/bagel/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Extelligence-ai/bagel

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/extelligence-ai/bagel/agents-md/github.svg)](https://agentmods.dev/instructions/extelligence-ai/bagel/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/extelligence-ai/bagel/agents-md"><img src="https://agentmods.dev/badge/instructions/extelligence-ai/bagel/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/extelligence-ai/bagel/agents-md"><img src="https://agentmods.dev/badge/instructions/extelligence-ai/bagel/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 601 This file is loaded in full into every session.

When invoked 601 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.

Model	Per session	Once invoked
Fable 5.1	$0.00601	$0.00601
Opus 5	$0.00300	$0.00300
Sonnet 5	$0.00120	$0.00120
Haiku 4.5	$0.00060	$0.00060

Measured 10d ago against content hash 25e8740d1e58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bagel 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 10d 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 · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bagel for agents

Instructions for AI agents asked to set up, use, or develop Bagel.

Set up Bagel for a user

Requires Docker. Pick the service matching their stack (see the table in README Quickstart): ros2-kilted, ros2-jazzy, ros2-iron, ros2-humble, ros1-noetic, ros1-noetic-cv, px4, ardupilot, betaflight, or iot.
Start it: docker compose run --service-ports <service> and wait for Uvicorn running on http://0.0.0.0:8000.
- Port 8000 taken? MCP_SERVER_PORT=8100 docker compose run --service-ports <service> and use 8100 below.
Connect the MCP client to http://localhost:8000/sse (SSE transport). Claude Code: claude mcp add --transport sse bagel http://localhost:8000/sse
Verify with a smoke test on bundled data: "Summarize the metadata of the ROS2 bag ./data/sample/ros2/mcap".
To analyze the user's own files, mount them: uncomment volumes under the chosen service in compose.yaml before starting.

Use Bagel well

Answers come from DuckDB SQL over real messages. Do not do the math yourself; ask Bagel and show the user the generated query.
Call describe_source first, and describe_topic before writing predicates (field paths and units vary by source).
Reduction etiquette: preview_pipeline first, report detected events and kept seconds, get user confirmation, then run_pipeline.
Output artifacts are written under the artifacts directory; tools return the paths.

Develop on Bagel

Runtime-independent tests run on the host: uv sync then uv run pytest test/*.py test/pipeline test/sink (full list in .github/workflows/test.yaml, job host-tests).
Service-bound tests run inside the images: docker compose build <service> --build-arg DEV_MODE=true then docker compose run --rm <service> uv run pytest ./test.
Every test file must be reachable by CI: test/test_ci_reachability.py fails the build otherwise (add new paths to host-tests or a Dockerfile).
Lint: uv run ruff check and uv run ruff format before committing.
Versioning: image tags and server.json follow pyproject.toml; published semver image tags are immutable (bump the version instead of retagging).

Read the full file on GitHub · 45 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.

10d ago First seen · 45 lines · 601 tokens per session scan A 25e8740d1e58

Subscribe to this mod's changes

bagel AGENTS.md is an instructions file published in the GitHub repository Extelligence-ai/bagel (397 stars, last pushed yesterday), licensed Apache-2.0. It adds 601 tokens to every session, about $0.0030 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.

Data and AI Hardware and IoT ardupilot betaflight drone mcp robotics ros2

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

bagel: Instructions file for Codex