deploygate-agent-plugin CLAUDE.md

Repository instructions for a DeployGate MCP plugin, a connector that lets coding agents work with DeployGate's mobile-app distribution service. They describe the project, commands, architecture, and tests.

In plain words
What is it for?
Use them when developing or reviewing a plugin that uploads iOS or Android app packages, manages distribution pages and team members, or sets up CI/CD through the DeployGate REST API.
Why use it?
They give coding agents the project rules and routine commands needed to build, test, and maintain the plugin consistently.

Instructions file

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/deploygate/deploygate-agent-plugin/claude-md
Clone the repo
git clone --depth 1 https://github.com/DeployGate/deploygate-agent-plugin
Per session 978 This file is loaded in full into every session.
When invoked 978 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 $0.00978 $0.00978
Opus 5 $0.00489 $0.00489
Sonnet 5 $0.00196 $0.00196
Haiku 4.5 $0.00098 $0.00098

Measured yesterday against content hash 521aff8b2415, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploygate-agent-plugin CLAUDE.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.

CLAUDE.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides repository guidance for coding agents working in this repository.

Project Overview

DeployGate MCP (Model Context Protocol) plugin for Claude Code and Codex. Provides tools for uploading mobile apps (iOS IPA, Android APK/AAB), managing distribution pages, team members, and CI/CD setup via the DeployGate REST API.

The plugin runs as a stdio-based MCP server. It is bundled into a single file (plugin/scripts/bundle.js) via esbuild for zero-dependency distribution.

Commands

npm run build        # TypeScript compile only (does not touch plugin/scripts/bundle.js)
npm run bundle       # tsc + esbuild bundle to plugin/scripts/bundle.js (release workflow only)
npm test             # Run all tests (vitest)
npm run test:watch   # Run tests in watch mode
npm run dev          # TypeScript watch mode
npm start            # Run the MCP server directly

CI runs npm run build && npm test on every PR and push to main. plugin/scripts/bundle.js is regenerated and committed automatically by the release-please workflow when it opens/updates a release PR — do not run npm run bundle and commit the result manually. A pre-commit hook in .githooks/ (installed by npm install via prepare) blocks accidental commits of the bundle.

Architecture

Entry point: src/index.ts — creates McpServer and DeployGateClient, registers all tool modules, connects via stdio transport.

API client: src/client.tsDeployGateClient class wrapping the DeployGate REST API (https://deploygate.com). Handles Bearer token auth, JSON/form-data requests, file uploads, and structured error responses via DeployGateApiError.

Tool modules (src/tools/*.ts): Each file exports a register*Tools(server, client) function that registers MCP tools with Zod parameter schemas. Tools return ContentBlock[] (text content, optional isError flag).

  • auth.tslogin_start, login_wait, logout, get_user_info
  • upload.tsupload_app (supports IPA/APK/AAB + optional iOS simulator zip)
  • distributions.ts — CRUD for distribution pages
  • udids.ts — iOS device UDID listing
  • notifications.ts — notification settings URL generation (no client needed)
  • members.ts — multi-step member management (workspace → project → team → app)
  • shared-teams.ts — workspace-wide shared team management

Read the full file on GitHub · 63 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. yesterday First seen · 63 lines · 978 tokens per session scan A 521aff8b2415

Subscribe to this mod's changes

deploygate-agent-plugin CLAUDE.md is an instructions file published in the GitHub repository DeployGate/deploygate-agent-plugin (3 stars, last pushed 7d ago), licensed MIT. It adds 978 tokens to every session, about $0.0049 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.