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 parhamb/design-skills --skill ux-safety-privacygit clone --depth 1 https://github.com/parhamb/design-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/parhamb/design-skills/ux-safety-privacy)<a href="https://agentmods.dev/skills/parhamb/design-skills/ux-safety-privacy"><img src="https://agentmods.dev/badge/skills/parhamb/design-skills/ux-safety-privacy/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/parhamb/design-skills/ux-safety-privacy"><img src="https://agentmods.dev/badge/skills/parhamb/design-skills/ux-safety-privacy.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 | $0.00053 | $0.00902 |
| Opus 5.5 | $0.00021 | $0.00361 |
| Sonnet 5.5 | $0.00011 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
ux-safety-privacy 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 2mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Safety and Privacy UX
Privacy is a user right. Security is a promise. Both must be designed for explicitly — users should not have to choose between convenience and protection.
Checklist
| Item | Guidance |
|---|---|
| Biometric authentication | Face ID and fingerprint are available for app re-entry and sensitive actions. |
| Storage permission prompt | Asked at the moment of use, not on launch. Explains why access is needed. |
| Location permission prompt | Request "While Using" first. Upgrade to "Always" only when strictly necessary. |
| Permissions listed | All required permissions are explained before the system dialog appears. |
| Data protection | Data is encrypted at rest and in transit. Sensitive fields are masked. |
| Multi-device management | User can view all signed-in devices and revoke access remotely from Settings. |
| Notification management | Per-type notification toggles (transactional, promotional, security). See ux-notifications. |
| Two-factor authentication | TOTP (authenticator app) available with SMS as fallback and backup codes for recovery. |
| Privacy policy link | Accessible from Settings > About and during account creation. A link, not a buried PDF. |
| GDPR compliance | Data export, data deletion, and consent management are implemented. |
| Analytics disclosure | Analytics providers are listed in the privacy policy. |
Permission Best Practices
Ask for permissions in context, not on launch. Requesting camera access when the user first opens the app feels invasive. Asking when the user taps the camera icon feels natural and logical.
Before the system permission dialog appears, show a pre-permission screen that explains what you are asking for and why. This dramatically improves the acceptance rate and reduces the chance the user denies and never comes back.
If a user denies a permission, always provide a recovery path. Show a message like "Enable in Settings > [App] > Camera" rather than silently disabling the feature.
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.
- 2mo ago First seen · 95 lines · 53 tokens per session scan A 01c7527772c0
ux-safety-privacy is a skill published in the GitHub repository parhamb/design-skills (25 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 902 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 2026-08-30.
ux-safety-privacy compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ux-safety-privacyparhamb/design-skills | Skill | 25 | 4mo ago | MIT | A | 53 | Claude Code, Codex |
| 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 | 4d 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 |