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 valsecchi75/project-scaffolder --skill persona-labgit clone --depth 1 https://github.com/valsecchi75/project-scaffolderWrote 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/valsecchi75/project-scaffolder/persona-lab)<a href="https://agentmods.dev/skills/valsecchi75/project-scaffolder/persona-lab"><img src="https://agentmods.dev/badge/skills/valsecchi75/project-scaffolder/persona-lab/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/valsecchi75/project-scaffolder/persona-lab"><img src="https://agentmods.dev/badge/skills/valsecchi75/project-scaffolder/persona-lab.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 | $0.00066 | $0.01403 |
| Opus 5 | $0.00033 | $0.00701 |
| Sonnet 5 | $0.00013 | $0.00281 |
| Haiku 4.5 | $0.00007 | $0.00140 |
Grade A, and why
persona-lab 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 10d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona-Lab — The Simulated Focus Group
Overview
Persona-Lab simulates diverse end-user profiles testing the implemented feature, catching UX problems that code review misses. It operates at code-level understanding — reading widget/component code, evaluating text labels, tracing navigation flows — not rendered pixels.
Core principle: If a low-tech user can't complete the flow, the implementation isn't done.
Important limitation: Persona-Lab cannot see rendered UI. It evaluates UX through code structure, text content, and flow logic. Visual issues (alignment, color contrast, spacing) belong to QA or manual review.
Context Budget (v3)
Persona subagents receive ≤5k tokens of injected context (same cap as the Cortex specialist): task description, the UI/flow under test, relevant excerpt of wiki/ux pages if present, persona profile. Never inject full wiki pages — excerpts only.
When to Run
| Task type | Run Persona-Lab? |
|---|---|
| UI feature (new screen, flow) | Yes — full 3-persona test |
| UI modification (copy, layout) | Yes — 2 personas (low-tech + high-tech) |
| Backend/API (no UI) | No |
| Infrastructure/devops | No |
| Bug fix (UX-related) | Yes — 1 persona matching bug reporter profile |
--skip-persona flag |
No |
Inputs from Cortex
Persona-Lab receives this context:
| Input | Source | Purpose |
|---|---|---|
| Task description | /task command |
What was implemented |
| Files changed (list) | Specialist output | Scope of change |
| Feature description | wiki/product/features.md excerpt (if present) |
Feature context |
| UI flow context | wiki/ux/ui-decisions.md excerpt (if present) |
Navigation patterns |
| Brand/tone rules | wiki/branding.md excerpt (if present) |
Language expectations |
| Relevant widget code | Changed UI files | Actual implementation |
Profile Generation
Read project context to generate relevant personas:
wiki/overview.md— target user descriptionwiki/ux/ui-decisions.md(if present) — UX principleswiki/branding.md(if present) — tone and visual identitywiki/product/features.md(if present) — feature context
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.
- 10d ago First seen · 137 lines · 66 tokens per session scan A 179acc5be77b
persona-lab is a skill published in the GitHub repository valsecchi75/project-scaffolder (9 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,403 once invoked, about $0.0003 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.
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.