What is ADOS-MCP AGENTS.md?

Repository instructions for ADOS-MCP, a TypeScript server that connects coding agents to the ADOS drone platform through the Model Context Protocol.

Use them when developing or reviewing ADOS-MCP, especially before editing files, building, testing, linting, or checking types.

They give agents the project’s architecture, commands, coding rules, and testing expectations so changes fit the existing codebase.

How altnautica/ADOS-MCP configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to altnautica/ADOS-MCP. 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/altnautica/ADOS-MCP/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/altnautica/ADOS-MCP

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/altnautica/ados-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/altnautica/ados-mcp/agents-md)

Your own site

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

Per session 1,166 This file is loaded in full into every session.

When invoked 1,166 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	$0.01166	$0.01166
Opus 5	$0.00583	$0.00583
Sonnet 5	$0.00233	$0.00233
Haiku 4.5	$0.00117	$0.00117

Measured 8d ago against content hash a94d4192bdd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ADOS-MCP 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 8d 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 · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - ADOS MCP Server

Agentic coding instructions for ADOS MCP, the Model Context Protocol server for the ADOS drone platform.

Purpose

Work in this repository as an engineering agent for the MCP server. Keep changes typed, tested, and scoped. The server is a thin shim over existing platform interfaces; it holds no telemetry buffers and runs no inference.

Read First

Check git status --short before edits and preserve unrelated changes.
Inspect the nearest existing tool, plane, transport, or test before introducing a new pattern.
Keep TypeScript strict. This repo uses noUncheckedIndexedAccess and verbatimModuleSyntax.

Stack and Commands

TypeScript 5 (ES modules, ES2022 target, Node16 module resolution).
MCP SDK: @modelcontextprotocol/sdk.
Runtime: Node >= 20. Package manager: pnpm 10.28.1.
License: MIT.

pnpm install
pnpm build
pnpm test
pnpm lint
pnpm typecheck

Use pnpm dev for local development (runs via tsx). Run pnpm build before committing to verify the TypeScript compilation succeeds. Use pnpm test for focused test runs.

Architecture Map

Entry point: src/index.ts
Server setup: src/server.ts
CLI: src/cli.ts
Config: src/config.ts
Version: src/version.ts
Transport layer: src/transport/
Tool planes (read, admin, flight): src/plane/
Gate (safety class checks): src/gate/
Auth (token validation, scopes): src/auth/
Audit trail: src/audit/
Param metadata: src/param-metadata/
Extension catalog: src/catalog/
Discovery (mDNS): src/discovery/
Registry (tool registration): src/registry/
Utilities: src/util/
Tests: test/
Architecture docs: docs/architecture.md

Coding Rules

Keep TypeScript strict. Avoid any in source files; use unknown with narrowing at boundaries. Test files may use any (ESLint is relaxed there).
Every tool must declare a safety class and go through the gate before execution. Never bypass the gate.
Every call produces one redacted audit event. Do not skip audit logging.
Token scopes control access. Flight and destructive scopes are off by default. Never grant them implicitly.
Transports are swappable. Keep transport-specific logic in src/transport/.
Keep source files near 300 lines when practical.

Read the full file on GitHub · 121 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.

8d ago First seen · 121 lines · 1,166 tokens per session scan A a94d4192bdd6

Subscribe to this mod's changes

ADOS-MCP AGENTS.md is an instructions file published in the GitHub repository altnautica/ADOS-MCP (0 stars, last pushed yesterday), licensed MIT. It adds 1,166 tokens to every session, about $0.0058 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.

Hardware and IoT

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

ADOS-MCP: Instructions file for Codex