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 southleft/skills-for-figma --skill annotations-figmagit clone --depth 1 https://github.com/southleft/skills-for-figmaWrote 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/southleft/skills-for-figma/annotations-figma)<a href="https://agentmods.dev/skills/southleft/skills-for-figma/annotations-figma"><img src="https://agentmods.dev/badge/skills/southleft/skills-for-figma/annotations-figma/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/southleft/skills-for-figma/annotations-figma"><img src="https://agentmods.dev/badge/skills/southleft/skills-for-figma/annotations-figma.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 | $0.00145 | $0.00871 |
| Opus 5 | $0.00072 | $0.00436 |
| Sonnet 5 | $0.00029 | $0.00174 |
| Haiku 4.5 | $0.00015 | $0.00087 |
Grade A, and why
annotations-figma 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 10d 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.
This is a copy
92% identical to figma-annotations — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
annotations-figma — read & write node annotations
Annotations are designer-authored specs attached to a node. Each can carry a note (plain label
or rich labelMarkdown), a set of pinned properties (fills, width, fontSize, …) that link
the note to specific design attributes, and an optional category (interactions, accessibility,
dev notes, …). They live on the node, survive edits, and are undoable (Cmd+Z). They are the right
place for animation timings, easing curves, interaction behavior, and a11y requirements that don't
belong in the component description.
Skill boundaries
use_figmarules — load the officialfigma-useskill first; it is the full Figma Plugin API reference. Essentials these scripts rely on: plain JS with top-levelawait+return(no IIFE, nofigma.closePlugin();console.logis not returned), inputs inlined asconstat the top of each script, colors in 0–1 range, load fonts before any text op,await figma.getNodeByIdAsync(...), and atomic errors (a failed script applies nothing — read the error, fix, retry).- Valid property types + shapes → references/annotation-properties.md.
- Comments (file-level discussion threads, not node specs) are out of scope — use Figma's comments REST API instead.
Workflow
- Get the node ID. Use the current selection or a node ID the user gives you. Annotations only apply to nodes whose type supports them (frames, components, instances, shapes, text — not pages).
- List categories first when writing categorized annotations. Run the categories snippet so you
can pass a real
categoryId(category names are per-file and not guessable). See the script. - Read with
scripts/get-annotations.js— setINCLUDE_CHILDRENto walk a component tree for full-component documentation. - Write with
scripts/set-annotations.js. ChooseMODE:'replace'(default — overwrites all annotations on the node) or'append'(keeps existing). PassANNOTATIONS = []with'replace'to clear all annotations. - Validate. Re-run the read script and confirm the annotation count and labels match what you set.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 42 lines · 145 tokens per session scan A fb0ca47cfe48
annotations-figma is a skill published in the GitHub repository southleft/skills-for-figma (14 stars, last pushed 3mo ago), licensed MIT. It adds 145 tokens to every session and 871 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to figma-annotations, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
system-pitch
Write a design system investment pitch with a business case and ROI framing. Trigger when someone says: pitch the design system, make the case for the system, sell this to leadership, justify the investment, business case for design systems, why should we invest in a design system, or anything about building an…
stakeholder-brief
Write a one-page stakeholder brief translating design system health or status into business language. Trigger when someone says: stakeholder update, exec brief, leadership summary, status report for leadership, system status for non-designers, write a brief for the business, or anything about communicating design…
token-audit
Audit a design system's token definitions for naming violations, missing semantic tiers, and structural debt. This audits how tokens are defined and organised, NOT how they are consumed in code. Trigger when someone says: audit my tokens, token naming review, are my tokens consistent, token health check, review my…
accessibility-per-component
Run an accessibility audit on a specific design system component. Trigger when someone says: accessibility check, a11y audit, WCAG compliance, is this accessible, check accessibility, does this meet WCAG, screen reader support, keyboard navigation check, or anything about auditing the accessibility of a specific…
ai-component-description
Generate AI-optimised text descriptions for components, formatted for Figma's MCP server and LLM consumption. This produces prose descriptions in a six-section format (purpose, props, anti-patterns, composition, accessibility, examples), NOT JSON schemas or structured data files. Trigger when someone says: write…
context-engine-builder
Generate a context engine — seven structured blueprint files (UX, UI, content, accessibility, ethical, technical, business intelligence) that encode everything an AI agent needs to work with a design system. This produces YAML infrastructure in .ai/context-engine/, NOT a health score or quality assessment. Trigger…