What is mari AGENTS.md?

Repository instructions for Mari and marilib, a combined project with wireless-device firmware and a Python control system. The two parts have separate builds and tests but communicate through a defined serial protocol.

Use them when changing firmware, the Python package, path-based CI, build commands, or the protocol connecting a Mari gateway to marilib.

They explain which files and commands belong to each half and how changes in one half can affect the other. This helps avoid unnecessary builds and broken communication between the firmware and Python code.

mari AGENTS.md — Instructions file by DotBots

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/dotbots/mari/agents-md

Clone the repo

git clone --depth 1 https://github.com/DotBots/mari

Made for: Codex, OpenCode.

Per session 542 This file is loaded in full into every session.

When invoked 542 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	$0.00542	$0.00542
Opus 5	$0.00271	$0.00271
Sonnet 5	$0.00108	$0.00108
Haiku 4.5	$0.00054	$0.00054

Measured yesterday against content hash 66581adc49a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mari 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 yesterday.

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 · 54 lines

What it actually says

mari + marilib (unified)

Unified repository: Mari TSCH-over-BLE link-layer firmware (firmware/) + the marilib Python control plane and agents (marilib/). Both halves are self-contained — each owns its own build config, tests, and examples. CI is path-filtered so a Python-only change doesn't trigger firmware builds and vice versa.

Layout

firmware/      ← C, nRF52840/nRF5340, SES + emBuild — see firmware/AGENTS.md
marilib/       ← Python package + tests + examples  — see marilib/AGENTS.md
README.md      ← repo overview (both halves)
AGENTS.md      ← this file (cross-cutting)
LICENSE        ← Apache 2.0 (covers both halves)
.gitignore     ← merged (firmware + Python patterns)
.pre-commit-config.yaml  ← merged (clang-format + hatch fmt + isort)
.github/workflows/       ← path-filtered: firmware/** vs marilib/**

Build

Half	Build cmd
Firmware	`make -C firmware docker` (CI path), or `make -C firmware node
marilib	`cd marilib && pip install -e .`; `cd marilib && hatch test`

Cross-half coupling

Wire protocol: marilib talks to a UART-attached Mari gateway over HDLC. Framing contract: marilib/marilib/serial_hdlc.py ↔ firmware/app/03app_gateway_app/hdlc.[ch]. Both halves must agree on framing and on MetricsProbePayload layout (marilib/marilib/mari_protocol.py ↔ firmware/mari/models.h).
marilib_timestamp field in firmware/app/03app_node/main.c — legacy shared-struct artifact slated for removal (see consolidation roadmap in dotbot-testbed/AGENTS.md).

Branch policy

Default branch: develop (gitflow). main is the release branch.
Feature branches off develop; PRs target develop.

Don't

Don't change paths that submodule consumers (currently only swarmit) traverse without bumping their submodule pointer and updating internal path references.
Half-specific don'ts live in firmware/AGENTS.md and marilib/AGENTS.md.

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.

yesterday First seen · 54 lines · 542 tokens per session scan A 66581adc49a9

Subscribe to this mod's changes

mari AGENTS.md is an instructions file published in the GitHub repository DotBots/mari (5 stars, last pushed 15d ago), licensed BSD-3-Clause. It adds 542 tokens to every session, about $0.0027 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 2026-08-31.

DevOps and cloud Git and workflow Testing

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 · 5,182 tokens

buildNext

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

mari AGENTS.md