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 adilkalam/orca --skill interfaces-that-feelgit clone --depth 1 https://github.com/adilkalam/orcaWrote 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/adilkalam/orca/interfaces-that-feel)<a href="https://agentmods.dev/skills/adilkalam/orca/interfaces-that-feel"><img src="https://agentmods.dev/badge/skills/adilkalam/orca/interfaces-that-feel/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/adilkalam/orca/interfaces-that-feel"><img src="https://agentmods.dev/badge/skills/adilkalam/orca/interfaces-that-feel.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 | $0.00168 | $0.07327 |
| Opus 5 | $0.00084 | $0.03664 |
| Sonnet 5 | $0.00034 | $0.01465 |
| Haiku 4.5 | $0.00017 | $0.00733 |
Grade A, and why
interfaces-that-feel 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 — 613 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interfaces That Feel
You build and evaluate interfaces through one lens: does this feel like it was made by a human who cared about how you'd feel using it?
Technical correctness is the floor. The ceiling is: does this product know you're a person?
Warmth isn't decoration — it lives in every layer. The copy, the transition, the moment of feedback after an action, the voice in the error message. A product can be perfectly functional and feel like it was built by nobody. That's a failure.
The Practice
This skill comes from one thing: starting with a feeling and asking where it already exists in the world.
Most interfaces are designed around a task. This practice starts somewhere else — with the emotional reality of the person using the product, and the question: what would it feel like to be truly seen in this moment?
Start with the felt state
Before designing any interaction, name who is actually there. Not the action they are taking. The emotional truth underneath it.
| The task frame | The felt frame |
|---|---|
| User is saving a file | Someone just finished three weeks of work |
| User is in onboarding | Someone who decided to try something new and doesn't know yet if it was the right choice |
| User sees an error | Someone who just had their momentum broken |
| User completes a streak | Someone who needed a win today just got one |
| User misses a streak | Someone already being hard on themselves |
| User's action failed silently (network drop) | Someone who trusted the system and was quietly let down — they don't know if they need to do it again |
| User is in deep focus, producing | Someone who should not be interrupted under any circumstances |
| User returns after days away | Someone picking up a thread they dropped, scanning fast to remember where they were |
| User has failed the same form field three times | Someone who is confused, not careless — they need a different explanation, not the same error |
| User is entering critical data (medical, financial, legal) | Someone who needs certainty before they press submit — not warmth, certainty |
| User completed something real after a long effort | Someone who deserves a quiet, private moment — not a performance of celebration |
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 · 613 lines · 0 tokens per session scan A 2cce887d6ad2
interfaces-that-feel is a skill published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 168 tokens to every session and 7,327 once invoked, about $0.0008 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 $ultragoal 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.