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-userflow/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-userflow)<a href="https://agentmods.dev/skills/hoangpm96/reqwise-figma-mcp/figma-userflow"><img src="https://agentmods.dev/badge/skills/hoangpm96/reqwise-figma-mcp/figma-userflow/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-userflow"><img src="https://agentmods.dev/badge/skills/hoangpm96/reqwise-figma-mcp/figma-userflow.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 | $0.00051 | $0.02532 |
| Opus 5.5 | $0.00020 | $0.01013 |
| Sonnet 5.5 | $0.00010 | $0.00506 |
| Haiku 4.5 | $0.00005 | $0.00253 |
Grade A, and why
figma-userflow 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 1mo 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/figma-userflow — What the user sees next
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
userflow.
The tool is figma_diagram with type: "userflow". One thing is different from the
other five kinds: the compact form here is mermaid (a flowchart TD source), not
text. Passing text to a userflow is an INVALID_PARAMS it cannot explain to you.
Goal
Map the screens and the paths between them — including the ones nobody wants to think about: the validation error, the cancel, the back button, the timeout. Drawn before the screens, this is the cheapest place to discover that three error states have no screen and one screen has no way out.
Output: one Figma frame Userflow · <title>, plus the flow holes it exposed.
Constraints
Hard rules — never violate
- Draw the flow before drawing screens, or at least offer to. A screen designed without its flow gets designed twice.
- Every
decisionneeds at least two outgoing edges, each with alabelthat is the condition ("yes" / "no", "còn lượt thử" / "hết lượt"). A question with one answer is not a question; the tool reports it. - Every path ends — at a
terminal, anexternal, or by looping back. A screen with no way out is a finding. kind: "return"on the edge for cancel / back / retry. It is drawn dashed in an outer gutter and kept out of the rank maths, which is what stops a long flow becoming a spider's web.- Never invent a screen. If the spec has no "email already registered" screen, the diagram shows the gap. That gap is the deliverable.
Write it in the compact form — here that is mermaid
The five figma_diagram kinds take a text line-form. A userflow does not — its compact
form is mermaid, a flowchart TD source passed as the mermaid field instead of
nodes+edges. Same idea, different notation, because a flowchart already has one everybody
knows and every model writes fluently.
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.
- 1mo ago First seen · 192 lines · 51 tokens per session scan A 012ca303e33d
figma-userflow is a skill published in the GitHub repository hoangpm96/reqwise-figma-mcp (106 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 2,532 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 2026-09-18.
figma-userflow compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| figma-userflowhoangpm96/reqwise-figma-mcp | Skill | 106 | 1mo ago | MIT | A | 51 | Claude Code |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | yesterday | 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 |