ux-flows

Rules for documenting how people complete tasks in an interface, including the screens, states, decisions, and error paths they encounter.

In plain words
What is it for?
Use them to analyse tasks, draw user-flow diagrams, define screen states and wireframes, or improve an interface's user experience.
Why use it?
They keep the written user flow aligned with the actual interface and make missing states or unclear recovery steps easier to find.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/ssheleg/super-ux/ux-flows
Clone the repo
git clone --depth 1 https://github.com/ssheleg/super-ux
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 966 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00042 $0.00966
Opus 5 $0.00021 $0.00483
Sonnet 5 $0.00008 $0.00193
Haiku 4.5 $0.00004 $0.00097

Measured 2d ago against content hash 3f5857c889cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ux-flows 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 2d 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.

cursor/rules/ux-flows.mdc · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ux-flows — Design HOW Users Move

docs/ux/flows.md is the HOW layer between foundation (stories) and scenarios: task analysis + mermaid user flows referencing screens by SCR-ID. The canonical per-screen spec lives in docs/ux/screens.md — the UI map: every screen and state with its Figma frame, wireframe, code coverage, scenarios, and resources. IDs FLW-NN/SCR-NN, sequential, never reused. Any interface change updates screens.md (and the Figma frame when enabled) in the same change — a screen whose code diverges from its record is drifted.

Flow entry (ux-contract v4)

Fields: Traces (story/job IDs), Goal (observable end state), Entry points (ALL of them), Success exit, Task analysis (numbered user-visible micro-steps), mermaid flowchart (screens as Screen: <name>, decisions as diamonds, *_err error nodes with labeled recovery edges), Screens traversed table (| Screen | States used here | — SCR-IDs only; the full per-screen spec lives once in screens.md).

Each screen entry in screens.md: Used by, Purpose, Elements (mark the ONE primary action), States table (| State | Trigger | Figma frame | Behavior | — a row per loading/empty/error/success that applies), Wireframe, Coverage (file:line), Scenarios, Resources, Status (designed|built|drifted|retired).

Design rules

  • One flow = one user goal. Task analysis first: cut/merge/default-away every step that doesn't serve the job; pull first value as early as possible; happy path ≤5 steps or justified.
  • Every decision an explicit branch; every error edge lands on recovery — dead ends are defects; all entry points enumerated.
  • Wireframes optional (docs/ux/wireframes/FLW-NN.md, ASCII hierarchy + primary action, not pixels); storyboard only when usage context drives design.
  • Visual identity BEFORE any frame: screens.md → Design system → Style pack. Empty and no design system in the project → pick a pack with the sheleg-design companion skill (workbench for product UI / dashboards / tools, instrument-console, editorial-luxury, or a new pack on its contract; cinematic scroll pages also take its motion methodology) and record the pack + token file. Missing → offer the one-time install once (npx sheleg-design-skill) and continue on platform defaults; recommend, don't force. The pack owns palette/type/motion and its bans; BP-079..090 stay the floors it must clear. Never invent a look per screen.
  • Figma mockups optional (default on): if the foundation's Design tooling enables Figma and a Figma MCP is available, mirror each screen into a frame built on the pack's tokens (they become the Figma variable collections) applying visual-craft practices (BP-079..090), and link every screen row to its frame; ask the user once at the start of design.
  • Backwards mode (existing product): reconstruct flows as they ARE from code with file:line evidence, tag inferred until confirmed; gaps between is/should become the improvement backlog.

Read the full file on GitHub · 74 lines

Changes

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.

  1. 2d ago First seen · 74 lines · 42 tokens per session scan A 3f5857c889cf

Subscribe to this mod's changes

ux-flows is a cursor rule published in the GitHub repository ssheleg/super-ux (2 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 966 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 2026-08-31.