marmot AGENTS.md

marmot AGENTS.md is an instructions file for Codex, OpenCode from marmot-protocol/marmot. It costs 862 tokens per session, scanned A, original, MIT.

A set of instructions for AI agents working on the Marmot protocol, a technical communication protocol. It explains which project documents cover each part of the protocol and what to read before editing.

In plain words
What is it for?
Use it when editing Marmot protocol documentation, especially to find the correct surface, ownership rules, reading order, and scope.
Why use it?
It helps agents stay within the right documentation boundaries and avoid putting implementation details into specification files.

Instructions file for CodexOpenCode

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/marmot-protocol/marmot/agents-md
Clone the repo
git clone --depth 1 https://github.com/marmot-protocol/marmot

Made for: Codex, OpenCode.

Per session 862 This file is loaded in full into every session.
When invoked 862 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.

ModelPer sessionOnce invoked
Fable 5 $0.00862 $0.00862
Opus 5 $0.00431 $0.00431
Sonnet 5 $0.00172 $0.00172
Haiku 4.5 $0.00086 $0.00086

Measured 3d ago against content hash eef75df0b1e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

marmot 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 3d 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 · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - marmot

Agent map for the Marmot protocol.

Scope

This repository is the spec text for protocol surfaces a clean-room implementation would need. The canonical directory tree, surface ownership model, and feature/component split live in layout.md.

Do not put darkmatter module names, database schemas, queue mechanics, local API shapes, or crate-specific test plans in normative spec files. Put those in implementation-model.md or implementation-repository docs.

Surface map

Each surface has a README.md (human orientation) and an AGENTS.md (agent operating rules: scope, read order, boundary, verification). Start at the surface you are editing; its AGENTS.md carries the rules specific to it, so this top-level file stays cross-surface only.

Surface / doc Start here
Stable invariants: identity, encodings, registries, errors foundation/AGENTS.md
Required group flows and group-state transitions protocol-core/AGENTS.md
Versioned MLS app_data_dictionary component bytes app-components/AGENTS.md
How Marmot bytes move over a network (Nostr, QUIC) transports/AGENTS.md
Optional or user-visible flows that span surfaces features/AGENTS.md
Where new text belongs (canonical tree + ownership) layout.md
How to write the spec (placement + detail rules) principles.md
Map from deprecated MIPs to this spec's surfaces mip-coverage.md
Non-normative mapping to this repo's code implementation-model.md

Read Order

  1. README.md
  2. layout.md
  3. principles.md
  4. The AGENTS.md for the surface you are changing (it links its README and the owning docs).
  5. mip-coverage.md only when mapping from deprecated MIPs.
  6. implementation-model.md only when local implementation guidance matters.

Rules

  • Principles explain how to write the spec. Keep exact client requirements in the document for the surface they affect.
  • Keep Marmot component ids in the private-use MLS range.
  • Component major versions are represented by component ids. A breaking version gets a new component id and document.
  • Component payloads are direct bytes for that component id. Do not add a generic Marmot envelope inside each component.
  • Keep transport data in transport components. Nostr routing belongs in marmot.transport.nostr.routing.v1.
  • Treat Nostr relays in the Nostr routing component as canonical signed group state for Nostr-routed groups.
  • Keep app components in app-components/. Feature docs MAY require and reference them.
  • Transport docs own outer envelopes, delivery addressing, publish targets, fetch rules, and transport validation.
  • Protocol-core docs own required group flows and group-state transitions.
  • Feature docs own optional or user-visible flows and cross-reference the surfaces that implement them.
  • AppDataUpdate proposal forms and their default request path are defined in app-components/README.md ("GroupContext Update Processing").

Read the full file on GitHub · 74 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.

  1. 3d ago First seen · 74 lines · 862 tokens per session scan A eef75df0b1e3

Subscribe to this mod's changes

marmot AGENTS.md is an instructions file published in the GitHub repository marmot-protocol/marmot (138 stars, last pushed 8d ago), licensed MIT. It adds 862 tokens to every session, about $0.0043 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.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js 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