Borrowing it
Nothing to install: this file belongs to hoangpm96/reqwise-figma-mcp. 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/hoangpm96/reqwise-figma-mcp/main/.claude/skills/figma-state/SKILL.mdgit clone --depth 1 https://github.com/hoangpm96/reqwise-figma-mcpWrote 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/hoangpm96/reqwise-figma-mcp/figma-state)<a href="https://agentmods.dev/skills/hoangpm96/reqwise-figma-mcp/figma-state"><img src="https://agentmods.dev/badge/skills/hoangpm96/reqwise-figma-mcp/figma-state/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/hoangpm96/reqwise-figma-mcp/figma-state"><img src="https://agentmods.dev/badge/skills/hoangpm96/reqwise-figma-mcp/figma-state.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 | $0.00049 | $0.02469 |
| Opus 5 | $0.00024 | $0.01234 |
| Sonnet 5 | $0.00010 | $0.00494 |
| Haiku 4.5 | $0.00005 | $0.00247 |
Grade A, and why
figma-state 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 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.
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 — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/figma-state — What a record is allowed to be
Read ../reqwise-diagram-rules.md first — connection gate, the four levels of correct, the
findings loop, frame placement, verification. This file carries only what is specific to a
state machine.
Goal
Turn a status field into a contract. A spec says status: draft | pending | approved | rejected and stops; the questions it never answers are which change is allowed from which,
what triggers it, and what has to be true first. That is what a developer needs to write the
guard clause and a tester needs to know what to try.
Output: one Figma frame State · <title> for one entity, plus the transition questions the
diagram exposed.
Constraints
Hard rules — never violate
- One entity per diagram. Two lifecycles on one canvas is two diagrams sharing a frame, and every reader loses track of which state belongs to which. Draw the second one separately.
- Exactly one
kind: "initial", and at least onekind: "final"unless the entity genuinely never ends (a session, a switch). The tool reports both. - Every transition needs a reason — see the table below. This is the rule the tool checks hardest, and the one specs leave out most often.
- Use the states the SYSTEM uses. If the DB stores
pending_review, theidispending_reviewand thelabelis what a human calls it ("Chờ duyệt"). A diagram whose state names do not match the data is a diagram nobody can implement against. - Never invent a transition to connect an orphan. A state nothing can reach is a finding about the spec, not a missing arrow.
Write it in the compact form
text is one line per thing, and the transition line is the UML sentence — which is what
keeps event, guard and action three separate things instead of one string with the guard
missing.
held "Seats held"
entry hold_expires_at = now() + 10 min
detail booking_seats rows written
paying "Awaiting payment"
do wait for the payment gateway
paid "Paid" final ok # kind + class on the state line
void "Released" final err
[*] -> held: Reserve the seats / insert bookings
held -> paying: Confirm the order [payment method chosen] / insert payments
held -> held: Change seats # a self-transition is normal, not odd
paying ~> held: Gateway declined [attempts < 3] !err # ~> is a way BACK
paying -> paid: Gateway confirmed
paying -> void: [attempts = 3] # guard only, no event
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 · 183 lines · 49 tokens per session scan A 8dbae7e9266e
figma-state is a skill published in the GitHub repository hoangpm96/reqwise-figma-mcp (65 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 2,469 once invoked, about $0.0002 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 2026-09-18.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.