agentmods.dev

DarwinRelay AGENTS.md

DarwinRelay AGENTS.md is an instructions file for Codex, OpenCode from dcierra/DarwinRelay. It costs 3,046 tokens per session, scanned A, original, MIT.

A set of repository instructions for coding agents working on DarwinRelay, a macOS runtime that lets software use tools such as shell commands, files, browsers, and desktop controls.

In plain words
What is it for?
Use it as guidance before making non-trivial changes in the DarwinRelay repository.
Why use it?
It tells agents what the project does, which files to read first, and how to respect its authority and security boundaries.

Instructions file for CodexOpenCode

not rated 1 12d ago A scan 3,046 tokens original MIT
View the source file dcierra/DarwinRelay
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/dcierra/darwinrelay/agents-md
Clone the repo
git clone --depth 1 https://github.com/dcierra/DarwinRelay

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.

agentmods badge for DarwinRelay AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dcierra/darwinrelay/agents-md.svg)](https://agentmods.dev/instructions/dcierra/darwinrelay/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dcierra/darwinrelay/agents-md"><img src="https://agentmods.dev/badge/instructions/dcierra/darwinrelay/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,046 This file is loaded in full into every session.
When invoked 3,046 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 $0.03046 $0.03046
Opus 5 $0.01523 $0.01523
Sonnet 5 $0.00609 $0.00609
Haiku 4.5 $0.00305 $0.00305

Measured 3d ago against content hash b53acd54a46a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

DarwinRelay 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 · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the primary repository guide for coding agents working on DarwinRelay. Read it before modifying code. Human-facing product documentation starts in README.md; runtime architecture and security details live under docs/ and in SECURITY.md.

What DarwinRelay is

DarwinRelay is a macOS MCP execution runtime. It intentionally exposes broad local authority to an MCP client: shell/filesystem operations, real PTYs, long-running jobs, persisted Codex history, a managed background Chrome workspace, and native desktop control through Accessibility, ScreenCaptureKit, Vision and CoreGraphics.

It is not a sandbox. Security work in this repository is about making powerful authority explicit, bounded, auditable and fail-closed — not pretending arbitrary shell access is contained.

Read these files first

For any non-trivial task, inspect:

  1. README.md — product surface and user workflows.
  2. AGENTS.md — coding-agent rules and repository map.
  3. SECURITY.md — trust boundaries and failure semantics.
  4. docs/ARCHITECTURE.md — component/data-flow architecture.
  5. docs/AGENT_OPERATIONS.md — runtime tool catalog and agent operating guidance.
  6. docs/DESKTOP_CONTROL.md — native UI control model and limitations.
  7. docs/DEVELOPMENT_MODEL.md — canonical public/private/upstream workflow and history mapping.
  8. UPSTREAM.md — upstream lineage and attribution policy.

Repository map

  • bridge.mjs — MCP server, tool schemas, dispatch, shell/filesystem/jobs/Codex/native-UI integration and high-level policy.
  • mcp-http.mjs — authenticated HTTP/OAuth MCP transport.
  • lib/ — PTY/federation/browser/native helper clients and shared runtime modules.
  • desktop-helper/ — Swift native desktop-control helper and virtual cursor source.
  • chrome-extension/ — unpacked Chrome extension for the managed background browser workspace.
  • scripts/chrome-native-host.mjs — Native Messaging host implementation installed into Application Support.
  • menubar/ — Swift menu-bar app and bundle builder.
  • launchd/ — LaunchAgent templates.
  • scripts/ — install, signing, diagnostics, lifecycle, browser-profile and deployment helpers.
  • tests/ — deterministic protocol/integration/lifecycle tests plus the mutable native AppKit fixture.
  • .github/workflows/ci.yml — public GitHub-hosted CI split into descriptive jobs.

Read the full file on GitHub · 229 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 · 229 lines · 3,046 tokens per session scan A b53acd54a46a

Subscribe to this mod's changes

DarwinRelay AGENTS.md is an instructions file published in the GitHub repository dcierra/DarwinRelay (1 stars, last pushed 12d ago), licensed MIT. It adds 3,046 tokens to every session, about $0.0152 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.

accessibilityai-agentsbrowser-automationchatgptcodexcomputer-use
Related

Other instructions, from other repositories

Screenhand CLAUDE.md

Claude Code instructions for manushi4/Screenhand, covering claude.md, project, commands, architecture and key entry points.

manushi4/Screenhand · 3,380 tokens

Screenhand AGENTS.md

AGENTS.md instructions for manushi4/Screenhand, covering agents.md, project, commands, architecture and key entry points.

manushi4/Screenhand · 1,930 tokens

open-codex-computer-use AGENTS.md

AGENTS.md instructions for iFurySt/open-codex-computer-use, covering open-codex-computer-use, 每轮开始先读, 代码改完前要读, 按任务需要选读 and 工作规则.

iFurySt/open-codex-computer-use · 637 tokens

open-codex-computer-use CLAUDE.md

Claude Code instructions for iFurySt/open-codex-computer-use, a project described as: 👾 Open Computer Use – Open-Source Alternative to Codex Computer Use.

iFurySt/open-codex-computer-use · 16 tokens

pi AGENTS.md

AGENTS.md instructions for TGYD-helige/pi, covering pi extensions monorepo — agent guidelines, project overview, required agent skills, ponytail — minimal-code discipline and mattpocock/skills — engineering workflow skills.

TGYD-helige/pi · 4,423 tokens

ghost-os CLAUDE.md

Instructions for ghostwright/ghost-os, covering ghost os -- developer guide, build & run, architecture, key files and 29 mcp tools.

ghostwright/ghost-os · 1,958 tokens