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 skills add sahajamit/figma-cli --skill figma-filesgit clone --depth 1 https://github.com/sahajamit/figma-cliWrote 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/sahajamit/figma-cli/figma-files)<a href="https://agentmods.dev/skills/sahajamit/figma-cli/figma-files"><img src="https://agentmods.dev/badge/skills/sahajamit/figma-cli/figma-files/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/skills/sahajamit/figma-cli/figma-files"><img src="https://agentmods.dev/badge/skills/sahajamit/figma-cli/figma-files.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 | $0.00036 | $0.01764 |
| Opus 5.5 | $0.00014 | $0.00706 |
| Sonnet 5.5 | $0.00007 | $0.00353 |
| Haiku 4.5 | $0.00004 | $0.00176 |
Grade A, and why
figma-files 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.
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
figma — File & Project Commands
Quick start
# Verify token
figma me
# Get file structure
figma files get <file-key> --depth 1
# Get specific nodes
figma files nodes <file-key> --ids 1:2,3:4
# List frames
figma files frames <file-key>
# Export images
figma images export <file-key> --ids 1:2,3:4 --format png
# List comments
figma comments list <file-key>
figma me
Show current user info (verify token works).
figma me [--json]
JSON output:
{
"id": "123456",
"handle": "John Doe",
"email": "[email protected]",
"img_url": "https://..."
}
figma files get <file-key>
Get file structure and metadata.
figma files get <file-key> [--depth N] [--version ID] [--geometry paths] [--json]
Options:
--depth N— depth of node tree (use 1-2 for large files)--version ID— get a specific version--geometry paths— include vector path data
JSON output: Full Figma file JSON (name, document tree, lastModified, version).
figma files nodes <file-key>
Get specific nodes by ID.
figma files nodes <file-key> --ids 1:2,3:4 [--json]
JSON output:
{
"name": "File Name",
"nodes": {
"1:2": { "document": { "id": "1:2", "name": "Node", "type": "FRAME", ... } }
}
}
figma files frames <file-key>
List all frames in a file.
figma files frames <file-key> [--json]
JSON output: Array of FigmaNode objects with type "FRAME".
figma images export <file-key>
Export nodes as images (PNG, SVG, JPG, PDF).
figma images export <file-key> --ids 1:2,3:4 [--format png] [--scale 2] [--output-dir ./exports] [--json]
Options:
--ids— (required) comma-separated node IDs--format— png, svg, jpg, pdf (default: png)--scale— 0.01 to 4 (default: 2)--output-dir— output directory (default: current directory)
JSON output:
{
"fileKey": "abc123",
"outputDir": "./exports",
"format": "png",
"exported": [{ "nodeId": "1:2", "filename": "1-2.png", "path": "./exports/1-2.png" }],
"failed": []
}
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 · 253 lines · 36 tokens per session scan A 57793599124e
figma-files is a skill published in the GitHub repository sahajamit/figma-cli (9 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 1,764 once invoked, about $0.0001 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.
figma-files compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| figma-filessahajamit/figma-cli | Skill | 9 | 6mo ago | MIT | A | 36 | Claude Code |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 3d ago | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |