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/dannote/figma-use/agents-mdgit clone --depth 1 https://github.com/dannote/figma-useWrote 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/dannote/figma-use/agents-md)<a href="https://agentmods.dev/instructions/dannote/figma-use/agents-md"><img src="https://agentmods.dev/badge/instructions/dannote/figma-use/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 | $0.01763 | $0.01763 |
| Opus 5 | $0.00881 | $0.00881 |
| Sonnet 5 | $0.00353 | $0.00353 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
figma-use 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 4d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Guide
Architecture
packages/
cli/ # Citty-based CLI, 100+ commands
plugin/ # RPC handlers (built on-demand by CLI via esbuild)
CLI communicates directly with Figma via Chrome DevTools Protocol (CDP). No proxy server, no manual plugin installation.
Build & Test
bun install
bun run build # Build CLI bundle
bun test # Run integration tests
# Figma must be running with:
open -a Figma --args --remote-debugging-port=9222
Feature Completion Checklist
When implementing a new feature, ensure ALL of these are done before committing:
1. Implementation
- CLI command in
packages/cli/src/commands/ - RPC handler in
packages/plugin/src/rpc.ts(if needed) - Export from
packages/cli/src/commands/index.ts
2. Tests
- Add test file in
packages/cli/tests/commands/ - Test happy path and edge cases
- Run
bun testto verify all tests pass
3. Documentation
- CHANGELOG.md — add entry under
## [Unreleased]or new version section - README.md — update if it's a user-facing feature
- SKILL.md — update if it changes how agents should use the tool
- REFERENCE.md — update command reference if adding/changing commands
4. Review Before Commit
bun test # All tests pass?
bun run build # Build succeeds?
git diff # Review all changes
git diff --cached # Review staged changes
Adding Commands
- Create
packages/cli/src/commands/my-command.ts:
import { defineCommand } from 'citty'
import { sendCommand } from '../client.ts'
import { printResult } from '../output.ts'
export default defineCommand({
meta: { description: 'My command' },
args: {
id: { type: 'string', required: true },
json: { type: 'boolean', description: 'Output as JSON' }
},
async run({ args }) {
const result = await sendCommand('my-command', { id: args.id })
printResult(result, args.json)
}
})
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.
- 4d ago First seen · 221 lines · 1,763 tokens per session scan A 3517e4624b25
figma-use AGENTS.md is an instructions file published in the GitHub repository dannote/figma-use (594 stars, last pushed 2mo ago), licensed MIT. It adds 1,763 tokens to every session, about $0.0088 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.
Other instructions, from other repositories
Figma-Context-MCP CLAUDE.md
Instructions for GLips/Figma-Context-MCP, covering framelink mcp for figma, build & development commands, running the server, running a single test and releasing.
figma-console-mcp CLAUDE.md
Instructions for southleft/figma-console-mcp, covering figma console mcp, build & test, release process, known issues and architecture.
figwright CLAUDE.md
Instructions for awdr74100/figwright: Read AGENTS.md first — it's the single source of guidance for this repo: architecture, layout, tech stack, commands, conventions, release flow, and gotchas.
naksha-studio copilot-instructions.md
Instructions for Adityaraj0421/naksha-studio, covering naksha design team — github copilot, activation triggers, the design team, design rules for code generation and css custom properties (always use these patterns).
exfig CLAUDE.md
Instructions for DesignPipe/exfig, covering toon format convention, context7 for external libraries, claude.md, quick reference and build & test.
canicode CLAUDE.md
Instructions for let-sunny/canicode, covering canicode, core goal, target environment, tech stack and project structure.