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 skills/mnlt/teleport/figmanpx skills add mnlt/teleport --skill figmagit clone --depth 1 https://github.com/mnlt/teleportWrote 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/skills/mnlt/teleport/figma)<a href="https://agentmods.dev/skills/mnlt/teleport/figma"><img src="https://agentmods.dev/badge/skills/mnlt/teleport/figma.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 | $0.00067 | $0.01658 |
| Opus 5 | $0.00034 | $0.00829 |
| Sonnet 5 | $0.00013 | $0.00332 |
| Haiku 4.5 | $0.00007 | $0.00166 |
Grade B, and why
figma scanned grade B with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Do NOT suggest editing `~/.claude/settings.local.json` manually.** The `teleport-setup add-key` command handles it with backup, validation, and masked input. Stop execution until the user has run the command and restar Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL -H "X-Figma-Token: $FIGMA_ACCESS_TOKEN" \ How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma
Operates Figma via REST API at https://api.figma.com. Use when you need actual file contents (nodes, components, variables) or fresh asset exports — figma.com pages are JS-rendered and not scrape-friendly.
Usage
- Use for: Exporting frames as PNG/SVG/JPG/PDF, reading design-system components/styles, fetching node trees for code generation, diffing versions.
- Skip for: Creating new designs, Figma desktop/plugin debugging, account/billing, real-time multiplayer state.
Credentials check
[ -n "${FIGMA_ACCESS_TOKEN:-${FIGMA_API_KEY:-$FIGMA_TOKEN}}" ] && echo "FIGMA_ACCESS_TOKEN: PRESENT" || echo "FIGMA_ACCESS_TOKEN: MISSING"
Never echo the variable directly — the value would appear in the conversation transcript. Use only the boolean pattern above.
If MISSING, respond to the user with EXACTLY this message (do NOT paraphrase, do NOT suggest manual JSON edits):
I need your figma credential. Run this in another terminal — it'll open the signup page, validate format, and save it safely with masked input:
teleport-setup add-key figmaThen restart Claude Code (
/exit, thenclaude) and ask me again.
Do NOT suggest editing ~/.claude/settings.local.json manually. The teleport-setup add-key command handles it with backup, validation, and masked input. Stop execution until the user has run the command and restarted.
API
- Base URL:
https://api.figma.com(all paths prefixed/v1/...). - Auth:
X-Figma-Token: $FIGMA_ACCESS_TOKEN— custom header, NOTAuthorization: Bearer. (OAuth apps use Bearer; PAT is whatteleport-setupprovisions.) - PAT scopes are enforced per token, non-upgradable. Read-only by default:
file_content:read,file_metadata:read,library_content:read,projects:read, etc. Write endpoints (comments, dev resources, variables) need matching:writescopes. - Rate limits: leaky-bucket, plan-dependent, per-minute quotas. Typical Pro: ~15/min Tier 1 (file reads), ~50/min Tier 2 (images), ~100/min Tier 3 (team libraries — strictest). On 429, honor
Retry-After; checkX-Figma-Plan-Tier/X-Figma-Rate-Limit-Type. - Pagination:
page_sizedefault 30, max 1000. Cursors viaprev_page/next_page.
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 · 98 lines · 67 tokens per session scan B 57bf004893c7
figma is a skill published in the GitHub repository mnlt/teleport (8 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 1,658 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
21st-ui
Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.
form-list-layout
Configure what a form and a list look like — sysuiform, sysuisection and sysuielement for forms; sysuilist, sysuilistelement and sysuirelatedlist for lists; sysfilter for saved filters. Views, why a field must exist in the dictionary first, and what snowcreatemenu really writes.
run402
Provision Postgres + REST API + auth + content-addressed storage + serverless functions + email — paid with x402 USDC on Base. Prototype tier is free on testnet. Use when the user asks to build a webapp, deploy a site, create a database, generate images, or mentions Run402.
sync-html-design-system
Use when the user changes a UI element in Remarc's macOS app (icon, badge, type label, component variant) and asks to reflect, mirror, encode, or sync it in the HTML design system — typically phrased as "add this to the design system", "mirror in HTML", "encode this on the web version", or "make sure the design system…
kernelcad-authoring
Author or modify kernelCAD models in TypeScript. Scripts live in .kcad.ts files; the kernelCAD CLI (kernelcad evaluate and kernelcad export stl|step|dxf|3mf|glb -o ) executes them via an OpenCASCADE WASM kernel.
kernelcad-mcp
Load when kernelcad mcp is available and you need to inspect or edit a live model without re-running the full CLI on every change. The MCP server exposes dynamic introspection tools that operate on evaluated in-memory state.