What is imgx-mcp CLAUDE.md?

A set of project instructions for imgx-mcp, a command-line and MCP server project for generating and editing images. It documents the architecture, development commands, tests, and release process.

Use it when developing imgx-mcp, running its tests and bundles, adding image providers, or following its release workflow.

It gives contributors a shared reference for how the project is organized, tested, built, and released. This reduces guesswork when changing or publishing the project.

How somacoffeekyoto/imgx-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to somacoffeekyoto/imgx-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/somacoffeekyoto/imgx-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/somacoffeekyoto/imgx-mcp

Made for: Claude Code.

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/somacoffeekyoto/imgx-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/somacoffeekyoto/imgx-mcp/claude-md)

Your own site

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

Per session 583 This file is loaded in full into every session.

When invoked 583 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	$0.00583	$0.00583
Opus 5.5	$0.00233	$0.00233
Sonnet 5.5	$0.00117	$0.00117
Haiku 4.5	$0.00058	$0.00058

Measured 2mo ago against content hash 79e69ebc04d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

imgx-mcp 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 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.

CLAUDE.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — imgx-mcp

Overview

AI image generation and editing — CLI + MCP server. v1.1.1.

Release flow

All steps in RELEASING.md are mandatory. The flow covers: imgx-mcp (test → version update → build → publish) → app-division-ops docs → public distribution.

Development commands

npm test                # Vitest — 54 tests (config 11 + history 37 + storage 6)
npm run bundle          # tsc + esbuild → dist/cli.bundle.js + dist/mcp.bundle.js
npm run build:skill-zip # Python script → dist/image-generation-skill.zip

Architecture

CLI and MCP are two entry points sharing the same core:

CLI (argument parsing, output formatting)    MCP Server (tool definitions, stdio)
 ↓                                            ↓
Core
 ├─ Capability enum        ← model-independent feature definitions
 ├─ ImageProvider interface ← provider contract
 ├─ Provider Registry      ← registration and lookup
 ├─ Storage                ← file I/O (session ID directory support)
 └─ History                ← session management, undo/redo, history
 ↓
Provider (model-specific)
 ├─ Gemini  ← @google/genai
 └─ OpenAI  ← native fetch (no npm dependency)

Adding a new provider requires no changes to the CLI or MCP layers.

Project configuration

.imgxrc — Project-level defaults (output dir, provider, model, aspect ratio, resolution). Searched from CWD upward. Shareable via git (no API keys).
Project-scoped history — When .imgxrc is detected, history is stored at <project-root>/.imgx/output-history.json (isolated per project).
Config resolution order — CLI flags → environment variables → .imgxrc → user config → provider defaults.

Version files (7 locations)

package.json
server.json (2 places)
src/cli/index.ts
src/mcp/server.ts
.claude-plugin/plugin.json
.claude-plugin/marketplace.json
.cursor-plugin/plugin.json

Key directories

src/core/       # Shared business logic (config, history, storage, providers)
src/cli/        # CLI entry point and commands
src/mcp/        # MCP server entry point and tool definitions
src/providers/  # Provider implementations (gemini/, openai/)
skills/         # Claude Code Skill (SKILL.md + references)
dist/           # Built bundles + Skill ZIP (committed to git)
tests/          # Vitest test suites

Read the full file on GitHub · 68 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.

2mo ago First seen · 68 lines · 583 tokens per session scan A 79e69ebc04d3

Subscribe to this mod's changes

imgx-mcp CLAUDE.md is an instructions file published in the GitHub repository somacoffeekyoto/imgx-mcp (1 stars, last pushed 7mo ago), licensed MIT. It adds 583 tokens to every session, about $0.0023 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 2026-08-31.

Creative and media gemini-api image-generation imge mcp nanobanana-api skills

imgx-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
imgx-mcp CLAUDE.mdsomacoffeekyoto/imgx-mcp	Instructions file	1	7mo ago	MIT	A	583	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

imgx-mcp: Instructions file for Claude Code