figma-compaction-mcp: Instructions file for Codex

AGENTS.md

figma-compaction-mcp AGENTS.md is an instructions file for Codex, OpenCode from s9hn/figma-compaction-mcp. It costs 498 tokens per session, scanned A, original, MIT.

Instructions for an AI agent working on figma-compaction-mcp, an open-source bridge that sends compact Figma design information to the agent.

In plain words
What is it for?
Use it when implementing, inspecting, or summarizing designs from Figma URLs in this project.
Why use it?
It tells the agent which tool to use for Figma links and helps keep large amounts of design data out of its working context.

Instructions file for CodexOpenCode

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

This is s9hn/figma-compaction-mcp's own configuration. It tells Codex and OpenCode how to work on figma-compaction-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 figma-compaction-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to s9hn/figma-compaction-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/s9hn/figma-compaction-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/s9hn/figma-compaction-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 figma-compaction-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/s9hn/figma-compaction-mcp/agents-md.svg)](https://agentmods.dev/instructions/s9hn/figma-compaction-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/s9hn/figma-compaction-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/s9hn/figma-compaction-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 498 This file is loaded in full into every session.
When invoked 498 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 $0.00498 $0.00498
Opus 5 $0.00249 $0.00249
Sonnet 5 $0.00100 $0.00100
Haiku 4.5 $0.00050 $0.00050

Measured 7d ago against content hash 20f71abbcdbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

figma-compaction-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 7d 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 · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — figma-compaction-mcp

Project Context

  • This project is open source and intended for public use.
  • It is an MCP bridge that sits between an AI agent and Figma design data.
  • The core product value is token reduction through compact caller-facing context.

Core Intent

  • When a developer pastes a full Figma node URL into an agent prompt, the agent should call get_figma_compact_context first.
  • This server should internally call Figma MCP, prune the upstream result, and return compact plain-text context.
  • The server acts as a middle layer that keeps raw Figma MCP output out of the caller model context whenever possible.

Routing Rules

  • Prefer get_figma_compact_context over direct Figma MCP get_design_context when the user asks to implement, inspect, or summarize a Figma link.
  • If the bridge returns a fallback handoff, continue with the standard Figma MCP tools for that same node.
  • Only use raw upstream Figma MCP output directly when the user explicitly asks for it or when debugging this bridge.
  • If the prompt contains an @https://www.figma.com/... link, treat it as a normal Figma URL after removing the leading @.

Product Direction

  • Main UX goal: install with npm, register one MCP server, then use Figma links naturally in prompts.
  • Preferred internal source is the local Figma desktop MCP server at http://127.0.0.1:3845/mcp.
  • Compact context is the first-class public contract.

Architecture Notes

  • This project uses link-based internal fetching through a local Figma MCP server.
  • The implementation model is: this process is an MCP server outwardly and an MCP client inwardly.
  • Do not return raw Figma JSON or large upstream MCP payloads to the caller except for tightly scoped debugging.
  • Parser/compaction logic should stay separate from transport and Figma-fetching logic.

Constraints

  • Keep AGENTS context short and practical for future AI contributors.
  • Treat token reduction, predictable routing, traceability, and low-friction setup as first-order requirements.
  • Prefer solutions that preserve the “one MCP install, paste Figma link, implement” workflow.
  • If the bridge cannot safely compact the upstream response, hand off cleanly to the normal Figma MCP flow instead of returning raw upstream payload from this server.

Read the full file on GitHub · 35 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. 7d ago First seen · 35 lines · 498 tokens per session scan A 20f71abbcdbe

Subscribe to this mod's changes

figma-compaction-mcp AGENTS.md is an instructions file published in the GitHub repository s9hn/figma-compaction-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 498 tokens to every session, about $0.0025 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.

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

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.

github/spec-kit · 7,104 tokens