photoshop-mcp: Instructions file for Codex

AGENTS.md

photoshop-mcp AGENTS.md is an instructions file for Codex, OpenCode from alisaitteke/photoshop-mcp. It costs 1,271 tokens per session, scanned A, original, MIT.

Project instructions for using PhotoshopMCP, a tool that lets an AI assistant control Adobe Photoshop through a connection. They describe how to start it, its architecture, and its prerequisites.

In plain words
What is it for?
They help configure PhotoshopMCP for coding editors or a standalone chat interface, check that Photoshop and Node.js are available, and understand how commands reach Photoshop.
Why use it?
They give an agent a clear entry point and workflow for working with Photoshop instead of leaving setup and tool selection unclear.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md.

This is alisaitteke/photoshop-mcp's own configuration. It tells Codex and OpenCode how to work on photoshop-mcp 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 photoshop-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alisaitteke/photoshop-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/alisaitteke/photoshop-mcp/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/alisaitteke/photoshop-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.

agentmods badge for photoshop-mcp AGENTS.md

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

agentmods 80×15 button for photoshop-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/alisaitteke/photoshop-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/alisaitteke/photoshop-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,271 This file is loaded in full into every session.
When invoked 1,271 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 $0.01271 $0.01271
Opus 5 $0.00635 $0.00635
Sonnet 5 $0.00254 $0.00254
Haiku 4.5 $0.00127 $0.00127

Measured today against content hash 56470dbe29bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

photoshop-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 today.

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 · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — photoshop-mcp

Navigation map, not a reference manual. Start with llms.txt or the site index llms.txt, then follow links as needed.

Entry strategy

Scenario Path
Cursor / Claude Desktop / VS Code Configure mcpServersnpx -y @alisaitteke/photoshop-mcp (stdio)
Claude Code claude mcp add photoshop -- npx -y @alisaitteke/photoshop-mcp
Standalone chat UI (no IDE) npx -p @alisaitteke/photoshop-mcp photoshop-mcp-ui
Local development npm install && npm run build && node dist/index.js — see docs/development.md

Prerequisites: Photoshop running on Windows or macOS, Node.js 18+. This is unofficial and not affiliated with Adobe.

Tool surface: 118 MCP tools — 102 atomic photoshop_* + 16 recipe photoshop_recipe_*; 23 MCP prompt templates (ps.*).

Architecture (agent view)

AI host (Cursor / Claude / UI)
  │  MCP stdio
  ▼
PhotoshopMCPServer (Node.js)
  │  ExtendScript via AppleScript (macOS) or COM (Windows)
  ▼
Adobe Photoshop

Optional: UXP bridge plugin (uxp-plugin/) on 127.0.0.1:38452 for Neural Filters only.

Deep dive: docs/architecture.md.

Follow the server instructions advertised on MCP initialize (src/prompts/instructions.ts):

1. DISCOVER: tools/list + prompts/list (or get_capabilities once per session)
2. STATE:    photoshop_get_state before mutating; photoshop_get_preview after major steps
3. ACT:      prefer photoshop_recipe_* for multi-step outcomes (single undo step)
4. RECOVER:  on error, read structured envelope (code, suggested_next_tool) → get_state → retry one step

Tool selection

Need Use
Multi-step outcome (remove BG, export for web, portrait enhance) photoshop_recipe_*
Single precise edit atomic photoshop_*
Vague user intent MCP prompt prompts/get (e.g. ps.remove_background) then call linked recipe/tool
Generative AI (Fill, Remove, Expand) photoshop_generative_* — requires Adobe account + credits
Neural Filters (skin smooth, colorize, …) photoshop_neural_filter — requires UXP bridge loaded
Version / feature check photoshop_get_capabilities

Read the full file on GitHub · 120 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. today Changed · -5 tokens per session 56470dbe29bb
  2. 9d ago First seen · 120 lines · 1,276 tokens per session scan A e05a725bbe2a

Subscribe to this mod's changes

photoshop-mcp AGENTS.md is an instructions file published in the GitHub repository alisaitteke/photoshop-mcp (402 stars, last pushed yesterday), licensed MIT. It adds 1,271 tokens to every session, about $0.0064 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 2026-08-30.

Related

Other instructions, from other repositories

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens