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.
npx agentmods add instructions/thealmightymight/pixso-mcp/agents-mdgit clone --depth 1 https://github.com/TheAlmightyMight/pixso-mcpWrote 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.
[](https://agentmods.dev/instructions/thealmightymight/pixso-mcp/agents-md)<a href="https://agentmods.dev/instructions/thealmightymight/pixso-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/thealmightymight/pixso-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00897 | $0.00897 |
| Opus 5 | $0.00449 | $0.00449 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
pixso-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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
Project Overview
Pixso MCP Server — a bridge that lets LLMs (e.g., Codex) interact with Pixso design files via the Model Context Protocol. The project has two parts that communicate over WebSocket (port 3667):
- MCP Server (
server/) — Node.js server using@modelcontextprotocol/sdk, communicates with MCP clients via Streamable HTTP (port 3668, endpoint /mcp) and with the Pixso plugin via WebSocket (port 3667). - Pixso Plugin (
plugin/) — runs inside Pixso;ui.htmlmaintains the WebSocket connection,main.jshandles commands in the plugin's main thread using thepixsoAPI.
Commands
npm start # Run the MCP server (node server/index.js)
npm run lint:all # ESLint across the project
No build step — all source files are plain JS (ES modules, "type": "module").
Project Structure
server/
index.js — MCP server entry point, wires bridge + tool handlers
bridge.js — WebSocket bridge: connection management, callPlugin()
tools.js — MCP tool definitions and call handlers
plugin/
main.js — Pixso plugin main thread (sandbox, single-file)
ui.html — WebSocket client UI with auto-reconnect
manifest.json — Pixso plugin manifest
tokens.js — статистика токенов для ответа MCP сервера
count-tokens.js — утилита: запрашивает выделение и считает токены
Architecture & Data Flow
MCP Client (Codex) <--HTTP:3668/mcp--> server/index.js
|
server/bridge.js <--WebSocket:3667--> plugin/ui.html <--postMessage--> plugin/main.js
|
server/tools.js (tool definitions + dispatch)
server/index.js: Entry point. Creates MCP server, starts WebSocket bridge, registers tool handlers.server/bridge.js: Manages WebSocket connection to the Pixso plugin. ExportsstartBridge()andcallPlugin(command, params). Pending requests tracked in aMap<id, resolve>.server/tools.js: Определяет MCP-инструменты (get_selection,get_selection_png,get_selection_svg,diagnose_export,get_design_tokens). ЭкспортируетhandleToolCall(name).plugin/ui.html: WebSocket client with auto-reconnect (5s). Forwardsrequestmessages from server tomain.jsviaparent.postMessage, and sendsmcp-responsemessages back to the server.plugin/main.js: Runs in Pixso's plugin sandbox. HandlesgetSelection,exportNodes, andgetDesignTokenscommands via thepixsoglobal API.serializeNode(node, profile)extracts node properties with token-saving optimizations.getDesignTokensextracts design tokens (colors, typography, effects, variables) from the entire document.
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.
- 5d ago First seen · 71 lines · 897 tokens per session scan A 95141a91049b
pixso-mcp AGENTS.md is an instructions file published in the GitHub repository TheAlmightyMight/pixso-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 897 tokens to every session, about $0.0045 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 2026-09-01.
Other instructions, from other repositories
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).
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.