Openship-App: Instructions file for Codex

AGENTS.md

Openship-App AGENTS.md is an instructions file for Codex, OpenCode from kareemessam09/Openship-App. It costs 4,367 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Openship-App, an unofficial Android client for Openship, a self-hosted deployment platform. They describe its Kotlin Multiplatform structure, Compose interface, and communication methods.

In plain words
What is it for?
Use them before changing the Android interface, shared code, API clients, deployment actions, or real-time event handling.
Why use it?
They help contributors understand the project boundaries and follow its existing architecture when making changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: names the TodoWrite tool; mentions AGENTS.md; mentions Codex.

This is kareemessam09/Openship-App's own configuration. It tells Codex and OpenCode how to work on Openship-App itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Openship-App configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kareemessam09/Openship-App. 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/kareemessam09/Openship-App/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/kareemessam09/Openship-App

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 Openship-App AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kareemessam09/openship-app/agents-md/github.svg)](https://agentmods.dev/instructions/kareemessam09/openship-app/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kareemessam09/openship-app/agents-md"><img src="https://agentmods.dev/badge/instructions/kareemessam09/openship-app/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.

agentmods 80×15 button for Openship-App AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kareemessam09/openship-app/agents-md"><img src="https://agentmods.dev/badge/instructions/kareemessam09/openship-app/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,367 This file is loaded in full into every session.
When invoked 4,367 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04367 $0.04367
Opus 5.5 $0.01747 $0.01747
Sonnet 5.5 $0.00873 $0.00873
Haiku 4.5 $0.00437 $0.00437

Measured 2mo ago against content hash 593f2a9e5d4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Openship-App 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 2mo 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 · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Openship-App — Agent Instructions

Source of truth for AI agents working in this repository. Read this before making any changes. For full API contract details, see README.md.

Project Overview

Openship-App is an unofficial Android client for Openship, the open-source self-hostable deployment platform. Built with Kotlin Multiplatform (KMP) and Compose Multiplatform, using the Model Context Protocol (MCP) as the primary API layer and Server-Sent Events (SSE) for real-time streaming.

  • License: Apache-2.0
  • Status: v0.1 read-only complete; v0.2 MCP redeploy/rollback complete; release packaging done (R8 minified per-ABI APKs). Unofficial community client.
  • Relationship: Unofficial community client for Openship — not affiliated unless upstream says otherwise

Architecture & Protocol Strategy

androidApp/ (Android only)          shared/ (KMP)
┌──────────────────────┐            ┌──────────────────────────────┐
│  Compose UI          │            │  commonMain/                 │
│  - Screens           │───────────▶│  - client/ (REST, SSE, MCP)  │
│  - Navigation        │            │  - model/ (data classes)     │
│  - ViewModels        │            │  - repository/               │
│  - Koin DI           │            │  - util/                     │
│  - Lifecycle         │            │                              │
└──────────────────────┘            │  androidMain/                │
                                    │  - platform/ (Keystore,      │
                                    │    OkHttp engine)            │
                                    └──────────────────────────────┘

Phased API design:

  • Phase 1 (Active — Base v0.1.0): Resilient REST endpoints (/api/health/env, /api/projects, /api/deployments, /api/system/servers) with parallelized coroutine fetching + SSE (Ktor SSE plugin) for real-time streams: build/deploy logs (/api/deployments/:id/stream) and host monitoring (/api/system/monitor/stream).
  • Phase 2 (Roadmap — v0.2.0+): Model Context Protocol (MCP) (/api/mcp) for AI-native agent tooling and automated operations using the official Kotlin MCP SDK (io.modelcontextprotocol:kotlin-sdk-client 0.15.0).
  • One shared HttpClient with infinite timeouts on streaming channels and AES-256 token persistence.

Read the full file on GitHub · 337 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. 2mo ago First seen · 337 lines · 4,367 tokens per session scan A 593f2a9e5d4a

Subscribe to this mod's changes

Openship-App AGENTS.md is an instructions file published in the GitHub repository kareemessam09/Openship-App (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 4,367 tokens to every session, about $0.0175 per session on Opus 5.5. 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

Openship-App AGENTS.md compared with instructions from other repositories

Openship-App AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Openship-App AGENTS.mdkareemessam09/Openship-AppInstructions file112mo agoApache-2.0A4,367Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode