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-prototype-plangit 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-prototype-plan)<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/figma-prototype-plan"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/figma-prototype-plan/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-prototype-plan"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/figma-prototype-plan.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 | $0.00071 | $0.00787 |
| Opus 5 | $0.00036 | $0.00394 |
| Sonnet 5 | $0.00014 | $0.00157 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
figma-prototype-plan 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Prototype Plan Skill
Plans what to prototype in Figma and how — scoping to what the user test needs, defining every interaction, and setting up the test scenarios. Prevents over-building and ensures the prototype answers the research question.
Required Inputs
- Research question (what are you trying to learn?)
- Feature or flow being prototyped
- Prototype fidelity (low wireframe / mid functional / high pixel-perfect)
- Testing method (moderated in-person / moderated remote / unmoderated)
- Number of test tasks
Output Structure
1. Prototype Scope
In scope: [Flows with real interactions — specific screens listed] Out of scope: [Screens to show as static — not worth building as interactive] Rationale: Prototypes should be the minimum needed to test the hypothesis.
2. Interaction Specification
Interaction N: [Description]
- Trigger: Tap/Swipe/Hover/Form submit
- Element: [Figma layer name]
- Destination: [Figma frame name]
- Animation: Instant/Dissolve/Push left/Push right/Slide up
- Timing: [ms]
- Reset after: Yes/No
3. Prototype Flow Diagram
[Start frame]
-> Tap "Action"
[Next frame]
-> Tap "Complete" -> [Success frame]
-> Tap "Cancel" -> [Back to start]
4. Test Task Scripts
Task N: [Title]
Scenario (read to participant): "[Realistic scenario giving context without directing the click path]"
Observing:
- [What to watch for]
Success when: [Specific trigger]
5. Figma Setup Guide
- Starting frame: [Name]
- Device preview: [Device]
- Prototype settings: background colour, show device, type
- Sharing: Can view link, reset process between participants
6. Build vs Fake Table
| Element | Build | Fake | Notes |
|---|---|---|---|
| Primary CTA flow | Yes | Core to research | |
| Secondary nav | Yes | Not being tested | |
| Error state | Yes | Testing recovery |
Quality Checks
- Scope limited to what the research question requires
- Every interaction has a named destination frame
- Task scripts are scenario-based (not "click on X")
- Success criteria defined for each task
- Reset process defined for between participants
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 · 92 lines · 71 tokens per session scan A af7851a348ed
figma-prototype-plan is a skill published in the GitHub repository cnfeat/top-pm-skills (48 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 787 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.