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 varunk130/ai-ux-skill-library --skill ai-trust-transparencygit clone --depth 1 https://github.com/varunk130/ai-ux-skill-libraryWrote 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/varunk130/ai-ux-skill-library/ai-trust-transparency)<a href="https://agentmods.dev/skills/varunk130/ai-ux-skill-library/ai-trust-transparency"><img src="https://agentmods.dev/badge/skills/varunk130/ai-ux-skill-library/ai-trust-transparency/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/varunk130/ai-ux-skill-library/ai-trust-transparency"><img src="https://agentmods.dev/badge/skills/varunk130/ai-ux-skill-library/ai-trust-transparency.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 | $0.00058 | $0.01884 |
| Opus 5 | $0.00029 | $0.00942 |
| Sonnet 5 | $0.00012 | $0.00377 |
| Haiku 4.5 | $0.00006 | $0.00188 |
Grade A, and why
ai-trust-transparency 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 12d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Trust & Transparency
Design interfaces where users can see into the AI's reasoning, calibrate their trust appropriately, and verify claims independently. The GLASS framework makes AI decision-making visible without overwhelming users.
Core Principle
Trust is not a boolean. Users should not "trust AI" or "distrust AI" - they should develop calibrated trust: high confidence when the AI is reliable, healthy skepticism when it's uncertain. Your job is to give them the signals to calibrate correctly.
The GLASS Framework
| Letter | Principle | Design Question |
|---|---|---|
| G | Ground in Sources | Can the user trace every AI claim back to a verifiable source? |
| L | Layer Explanations | Can the user get a 5-second answer AND a 5-minute deep dive? |
| A | Advertise Limitations | Does the interface proactively tell users what the AI is NOT good at? |
| S | Show Confidence | Can the user see how certain the AI is about each output? |
| S | Support Override | Can the user correct, override, or reject AI outputs without friction? |
The Trust Calibration Spectrum
Design for the right trust level - not maximum trust.
| Trust Level | User Behavior | Design Goal | When Appropriate |
|---|---|---|---|
| Over-trust (Automation Bias) | Accepts all AI outputs without checking | Introduce friction to encourage verification | High-stakes decisions (medical, financial, legal) |
| Calibrated Trust | Verifies selectively based on confidence signals | Maintain - this is the target state | Most AI interactions |
| Under-trust (AI Aversion) | Rejects AI outputs even when correct | Build trust incrementally through track record | New users, after AI failures |
Trust Erosion Events (TEEs)
A single trust violation can undo weeks of reliable performance. Design for recovery:
| TEE Type | Example | Recovery Pattern |
|---|---|---|
| Confident hallucination | AI states a false fact with no hedging | Immediately acknowledge the error class; show what changed to prevent recurrence |
| Silent failure | AI gives an answer but misses a critical constraint | Add constraint-checking signals: "I accounted for X, Y, Z in this answer" |
| Inconsistency | AI gives different answers to the same question | Surface version/context differences: "This differs from my earlier answer because..." |
| Opacity | User cannot understand why AI made a choice | Retroactive explanation: "I recommended X because of [factors]. Here's what would change if..." |
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.
- 12d ago First seen · 157 lines · 58 tokens per session scan A 4dc66e30b3f5
ai-trust-transparency is a skill published in the GitHub repository varunk130/ai-ux-skill-library (3 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 1,884 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
design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…
ss-dial
Turn ONE design axis up or down as a coordinated, deterministic transform — "denser", "sharper corners", "more muted", "bolder", "flatter", "livelier". Not a vibe the model reinterprets each time; a defined ramp that moves many tokens together, respects the guardrails (8px grid, a11y floors, single accent…
ss-reference
Compile screenshots, URLs, Figma exports, or an existing UI into a project-local StyleSeed output grammar with evidence, tokens, confidence, anti-patterns, and a validation screen. Use when the user supplies a design reference that StyleSeed does not already model.
bim-classification-ai
Classify BIM elements using AI and standard classification systems. Map elements to UniFormat, MasterFormat, OmniClass, and CWICR codes.
032-architecture-adr-non-functional-requirements
Facilitates conversational discovery to create Architectural Decision Records (ADRs) for non-functional requirements using the ISO/IEC 25010:2023 quality model. Use when the user wants to document quality attributes, NFR decisions, security/performance/scalability architecture, or design systems with measurable…
component-family-consistency
Buttons, inputs, pills, badges, calendars, and other interactive components form a visual family — they share the same border-radius, colour logic, shadow scale, border style, and spacing rhythm. Inconsistency between them breaks the sense of a coherent product. Use when building or reviewing a component library…