figma-lens: Instructions file for Codex

AGENTS.md

figma-lens AGENTS.md is an instructions file for Codex, OpenCode from khanglvm/figma-lens. It costs 527 tokens per session, scanned A, original, MIT.

Repository instructions for using Figma Lens when reading Figma links. They explain which inspection command to use for exact frames, flows, boards, components, searches, and follow-up questions.

In plain words
What is it for?
They are for implementing Figma designs accurately, understanding flows, locating nodes, and checking screenshots and compact design specifications.
Why use it?
They help coding agents inspect the right amount of design information and avoid investigating unrelated parts of a large Figma file.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

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

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-lens AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/khanglvm/figma-lens/agents-md.svg)](https://agentmods.dev/instructions/khanglvm/figma-lens/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/khanglvm/figma-lens/agents-md"><img src="https://agentmods.dev/badge/instructions/khanglvm/figma-lens/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 527 This file is loaded in full into every session.
When invoked 527 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 $0.00527 $0.00527
Opus 5 $0.00264 $0.00264
Sonnet 5 $0.00105 $0.00105
Haiku 4.5 $0.00053 $0.00053

Measured 6d ago against content hash f919b89d5649, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

figma-lens 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 6d 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 · 43 lines

What it actually says

Agent instructions

For read-only Figma node links, use this repository's figma-lens CLI or its native MCP tools. For a single exact implementation frame use extract --intent. For a wrapper, flow, board, collection, or multi-state component use a catalog scout first. For non-implementation inspection use inspect once, open the screenshot with vision, and read the compact spec. Use search or tree with --offline for follow-up questions.

If the supplied node wraps several screens or components, run scout without an intent first and view only its overview screenshot. Read overview.states in visual order. For a stateful component implementation, run the returned next.focusSet verbatim so inner implementation nodes—not presentation frames—are selected. For design-summary or user-flow questions, stop there when the image and ordered states establish the product goal, entry state, main actions, and async/error/end states. Do not investigate every state merely for completeness.

Only when the target or transition remains ambiguous, run at most one intent scout with --render 2, then view candidate 1 and candidate 2 only if needed. Run focus --select <node-id> only for implementation-level detail. Prefer the copy-ready commands in the manifest's next field. Read the focused summary before opening detailed spec data. Do not implement the outer wrapper as though it were one screen, and do not load raw or full-spec artifacts into context by default. Never follow a successful wrapper scout with inspect; inspect is for a single implementation frame.

Use overview positions and spatial-context matches to follow flow labels such as HOVER/YES/NO. If visible copy is missing at focus depth 8, deepen only that focused node with --depth 12 --no-screenshot, then search it offline. Offline search/tree calls without --depth reuse the deepest matching cached subtree automatically.

Treat .env, raw responses, screenshots, and extracted private assets as sensitive. They must remain ignored. Keep the CLI strictly read-only.

For design-to-code work, read only the chosen baseline state's compact visible evidence, use one source-size detail call for important child groups, and run copy-check on implementation JSX/TSX before handoff. Never allowlist guessed copy or sample data; copy-check does not replace the required screenshot comparison.

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. 6d ago First seen · 43 lines · 527 tokens per session scan A f919b89d5649

Subscribe to this mod's changes

figma-lens AGENTS.md is an instructions file published in the GitHub repository khanglvm/figma-lens (0 stars, last pushed 24d ago), licensed MIT. It adds 527 tokens to every session, about $0.0026 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

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 · 5,182 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

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

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

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

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