Borrowing it
Nothing to install: this file belongs to skulidropek/figma-tunnel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/skulidropek/figma-tunnel/main/AGENTS.mdgit clone --depth 1 https://github.com/skulidropek/figma-tunnelWrote 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/skulidropek/figma-tunnel/agents-md)<a href="https://agentmods.dev/instructions/skulidropek/figma-tunnel/agents-md"><img src="https://agentmods.dev/badge/instructions/skulidropek/figma-tunnel/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.
<a href="https://agentmods.dev/instructions/skulidropek/figma-tunnel/agents-md"><img src="https://agentmods.dev/badge/instructions/skulidropek/figma-tunnel/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00372 | $0.00372 |
| Opus 5 | $0.00186 | $0.00186 |
| Sonnet 5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
figma-tunnel 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 9d 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.
What it actually says
Repository guidance
Purpose
This project exposes the currently open Figma document through a small HTTP API. Agents receive one secret share URL, read its llms.txt, and use GET and POST requests.
Architecture
Agent → HTTP API (:8765) → loopback relay (:3055) → Figma API Plugin
src/api/server.mjsowns all public routes, access control, idempotency, live documentation, and local plugin-management routes.src/relay/server.jsis an internal Bun WebSocket relay bound to127.0.0.1.src/plugin/runs inside Figma and executes the command dispatcher incode.js.scripts/contains the Windows bootstrap and service controllers.start.cmdis the only user-facing start command on Windows.
Development checks
node --check .\src\api\server.mjs
node --check .\src\api\health.mjs
node --check .\src\relay\server.js
.\start.cmd
There is no build step. The plugin JavaScript and HTML are runtime artifacts and must remain directly executable by Figma.
Rules
- Keep the public interface HTTP-only.
- Keep
/local/control/*loopback-only and inaccessible through Cloudflare. - Keep the relay loopback-only; never expose port
3055. - Read operations work in both access modes. Write operations require write mode and
Idempotency-Key. - Preserve stable JSON error bodies and the generated
llms.txt/OpenAPI descriptions when routes change. - Error responses must link to the nearest valid documentation scope: service, share, or individual route/operation.
- Preserve progress updates for long plugin work.
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.
- 9d ago First seen · 39 lines · 372 tokens per session scan A 2d2620801aeb
figma-tunnel AGENTS.md is an instructions file published in the GitHub repository skulidropek/figma-tunnel (1 stars, last pushed 17d ago), licensed MIT. It adds 372 tokens to every session, about $0.0019 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.
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.
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 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).
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).
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.
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.