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 cnfeat/top-pm-skills --skill figma-user-flow-plannergit clone --depth 1 https://github.com/cnfeat/top-pm-skillsWrote 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/cnfeat/top-pm-skills/figma-user-flow-planner)<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/figma-user-flow-planner"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/figma-user-flow-planner/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/cnfeat/top-pm-skills/figma-user-flow-planner"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/figma-user-flow-planner.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 | $0.00088 | $0.00769 |
| Opus 5 | $0.00044 | $0.00385 |
| Sonnet 5 | $0.00018 | $0.00154 |
| Haiku 4.5 | $0.00009 | $0.00077 |
Grade A, and why
figma-user-flow-planner 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 7d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma User Flow Planner Skill
Plans what needs to be designed before a pixel is touched — mapping all screens, states, entry points, and edge cases so designers do not discover missing states mid-build.
Required Inputs
- Feature or task being designed
- User type (who performs this flow?)
- Platform (iOS / Android / Web / Multi-platform)
- Starting point (where does the user begin?)
- Known edge cases (optional)
Output Structure
1. Flow Overview
Feature, user, goal, entry points, success exit, failure exits.
2. Screen Map
| # | Screen name | Type | Triggered by | Notes |
|---|---|---|---|---|
| 1 | [Screen] | New/Modal/Drawer/Toast | [What triggers] | [Considerations] |
Screen types to cover: entry, happy path, loading, success, error (network/validation/permission), empty, first-time/onboarding, edge cases.
3. State Matrix
[Screen name]
| State | Trigger | Visual change | Action available |
|---|---|---|---|
| Default | Page load | [Description] | [What user can do] |
| Loading | User taps action | Skeleton/spinner | None |
| Error | API failure | Error message | Retry/Go back |
| Empty | No data | Empty state | [CTA] |
4. Decision Points
Decision: [Name]
- If yes: [Screen N]
- If no: [Screen X]
5. Suggested Figma File Structure
Feature name/
- Cover
- Flow Map
- Happy Path
- Error States
- Empty States
- Edge Cases
- Handoff
6. What Not to Design Yet
[Explicit out-of-scope items — prevents scope creep]
Quality Checks
- All three state types covered: loading, error, empty
- All decision points mapped with both branches
- Entry points include all realistic user paths
- Out-of-scope section is explicit
- Figma file structure matches screen map
Anti-Patterns
- Do not plan only the happy path — all error states, empty states, and edge cases must be mapped before designing starts
- Do not produce a flow map that doesn't match the Figma file structure — the page structure must reflect the flow map
- Do not define screens without specifying all required states — a screen without its variants is an incomplete design scope
- Do not start designing before entry and exit points are fully documented — unclear boundaries cause scope creep
- Do not plan user flows without tying each step back to a user goal — every screen must justify its existence
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.
- 7d ago First seen · 84 lines · 88 tokens per session scan A 521bc43f2fca
figma-user-flow-planner is a skill published in the GitHub repository cnfeat/top-pm-skills (48 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 769 once invoked, about $0.0004 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 2026-09-03.
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 $ralph 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.