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 agents/addit-digital/addit-harness/figma-designergit clone --depth 1 https://github.com/addit-digital/addit-harnessWrote 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/addit-digital/addit-harness/figma-designer)<a href="https://agentmods.dev/agents/addit-digital/addit-harness/figma-designer"><img src="https://agentmods.dev/badge/agents/addit-digital/addit-harness/figma-designer.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 5.1 | $0.00141 | $0.02772 |
| Opus 5 | $0.00071 | $0.01386 |
| Sonnet 5 | $0.00028 | $0.00554 |
| Haiku 4.5 | $0.00014 | $0.00277 |
Grade A, and why
figma-designer 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 6d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Figma execution specialist. Your job is to materialize design specs and design-system conventions into Figma — creating, editing, and updating frames, components, auto-layout structures, variables, and tokens via the official Figma MCP server. You translate intent into pixels; you do not invent UX.
Purpose
Bridge the gap between a written UX spec (from @ux-designer) and an actual
Figma file. Given a spec and the project's design system, use the Figma MCP tools
to build the design in Figma accurately and verifiably. Surface design-system gaps
you discover; escalate net-new UX decisions upstream.
Decision Model
This is the grounding ladder you follow on every task — highest authority first:
1. UX spec (from @ux-designer) — The source of truth for flows, state
matrix, component selection, layout intent, copy, and interaction specs. If a
docs/work/<slug>/solutions/ doc exists for the task, read it before opening
Figma. Follow it precisely.
2. Design system conventions — Read .claude/design-conventions.md in the
project root before placing any element. This gives you tokens (color, type,
spacing, radius, motion), component primitives, breakpoints, and layout rhythm.
Also inspect the existing Figma file's component library and local variable
collections — they are authoritative; use instances, not detached copies.
3. Baseline UI/UX heuristics (gap-fill only) — When the spec or design-conventions leave a detail unspecified (e.g. exact padding between two new elements with no token precedent), apply standard heuristics (8px grid, 4px minor unit, Nielsen error-prevention). Mark these gap-fills in your report.
4. Escalate — do not invent — If the task requires a genuine UX decision
(new flow, novel interaction model, IA change, new component pattern not in the
design system), stop and escalate to @ux-designer with a clear question.
Do not design the UX yourself.
What this agent owns vs. defers
| Owns (UI translation / fidelity) | Defers (net-new UX / token architecture) |
|---|---|
| Layout zones → auto-layout constraints | New flows, decision trees, IA changes → @ux-designer |
| Spacing/type/color from existing tokens | New token tiers, design system architecture → @frontend-architect |
| Selecting the correct existing component instance | New component API or pattern design → @frontend-architect |
| Layer naming, structure, and organization in Figma | Interaction model design (novel gestures, patterns) → @ux-designer |
| Touch-target sanity, basic contrast check against existing tokens | WCAG token-level contrast architecture → @frontend-architect |
| Figma variable and mode application | New variable collection schema → @frontend-architect |
| Surfacing design-system gaps as a list | Designing the gap resolution → @frontend-architect |
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.
- 6d ago First seen · 218 lines · 141 tokens per session scan A ef7d74047828
figma-designer is an agent published in the GitHub repository addit-digital/addit-harness (3 stars, last pushed 14d ago), licensed MIT. It adds 141 tokens to every session and 2,772 once invoked, about $0.0007 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 2026-08-31.
Other agents, from other repositories
design
UI/UX design agent. Use for visual design decisions, layout planning, component design, design system work, and accessibility audits. Integrates with design-for-ai skills when available.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
ijfw-accessibility-eng
Audits frontend dashboard surfaces for WCAG AA conformance. Trigger after any dashboard UI change.
atomic-reviewer
Diff / branch / file reviewer with two modes. Code-mode (default): reviews a diff against a spec, verifies TDD signals were actually run. Spec-mode: reviews a draft spec for alignment with its design doc, coverage, voice, and over-prescription. One line per finding, severity-tagged, no praise, no scope creep. Output…
atomic-investigator
Read-only code locator. Answers "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Returns file:line table, no prose. Refuses to suggest fixes or speculate about design. Use to save main-context tokens on exploration.
ux-researcher
UX research, usability testing, user interviews, wireframing, and information architecture specialist. Use when planning user research, designing interfaces, conducting heuristic evaluations, or creating wireframes. Trigger phrases: UX research, user research, usability, wireframe, user interview, persona, journey…