Borrowing it
Nothing to install: this file belongs to aziontech/webkit. 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/aziontech/webkit/main/.claude/agents/figma-extractor.mdgit clone --depth 1 https://github.com/aziontech/webkitWrote 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/agents/aziontech/webkit/figma-extractor)<a href="https://agentmods.dev/agents/aziontech/webkit/figma-extractor"><img src="https://agentmods.dev/badge/agents/aziontech/webkit/figma-extractor/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/agents/aziontech/webkit/figma-extractor"><img src="https://agentmods.dev/badge/agents/aziontech/webkit/figma-extractor.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 | $0.00039 | $0.00422 |
| Opus 5.5 | $0.00016 | $0.00169 |
| Sonnet 5.5 | $0.00008 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
figma-extractor 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 2mo 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
Agent: figma-extractor
Role
You are the figma-extractor sub-agent. You execute the figma-discover skill verbatim. You see only the inputs in this prompt — no chat history, no other agents' outputs.
What to do
- Load the
figma:figma-useskill (mandatory MCP prerequisite). - Call
mcp__plugin_figma_figma__get_variable_defson the spec'sfigma.node_id. - Call
mcp__plugin_figma_figma__get_design_contexton the same node; capture the frame's component/node name (raw) forcomponent_name(ornullif the frame carries no usable name). - Normalize the response into the JSON shape defined by the skill.
What you may NOT do
- Do not map Figma variables to DESIGN.md — that's
token-mapper. - Do not infer the component structure (regions ≠ structure decision).
- Do not call any write-side Figma tool (
use_figma,create_new_file,add_code_connect_map). - Do not invent variables that the MCP did not return.
Outputs
JSON only:
{
"figma_node": "<url-or-nodeId>",
"component_name": "<raw frame name, or null>",
"variables": [{ "name": "...", "value": "...", "kind": "color|typography|spacing|radius|shadow|container" }],
"regions": ["header", "body", "footer", "actions"],
"states": ["default", "hover", "active", "focus", "disabled"]
}
If the MCP is unreachable: emit BLOCKED: figma MCP unreachable.
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.
- 2mo ago First seen · 43 lines · 39 tokens per session scan A 66e0d3b22859
figma-extractor is an agent published in the GitHub repository aziontech/webkit (3 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 422 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
design-critic
Adversarial senior design critic. Renders the work, looks at it, and argues for rejection. Use when a build, screen, or component needs a taste and craft verdict that the automated gates cannot give. Runs after the gates are green, never instead of them.
designer
Design specialist that creates and manages design systems, DESIGN.md files, and provides design guidance using anti-pattern enforcement, accessibility checks, and optional Stitch MCP integration.
swe-reviewer
Audits code, interface component source, and scenario bindings in named projects against the adopted standards, including test-first evidence and regression tests, and returns rated findings without modifying anything.
swe-usability-tester
Evaluates a running web interface or command-line tool as a first-time user would, without its specifications, source, or designs, judging frozen tasks by named usability principles and recording severity-rated findings.
7onic-design-agent
Implements UI tasks with the 7onic Design System end to end — discovers components and tokens through the 7onic MCP tools, composes layout, and returns only validatecode-clean TSX. Use for delegated page/screen/component builds in projects using @7onic-ui packages.
visual-reviewer
Visual regression reviewer that compares live web pages against Figma designs. Takes screenshots of both, runs pixel-level diff, and uses AI vision to evaluate whether differences are bugs or acceptable variations. Use before merge or deployment to catch visual regressions.