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 agentmods add skills/fergius-engineering/instincts/ux-designer-mindsetnpx skills add Fergius-Engineering/instincts --skill ux-designer-mindsetgit clone --depth 1 https://github.com/Fergius-Engineering/instinctsWrote 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/fergius-engineering/instincts/ux-designer-mindset)<a href="https://agentmods.dev/skills/fergius-engineering/instincts/ux-designer-mindset"><img src="https://agentmods.dev/badge/skills/fergius-engineering/instincts/ux-designer-mindset.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00443 |
| Opus 5 | $0.00014 | $0.00221 |
| Sonnet 5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
ux-designer-mindset 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.
What it actually says
The rule
A feature that compiles and returns the right value can still feel broken. Before you implement, walk the interaction the way the user lives it; after, check the states you didn't design for. A green build tells you the code runs — it tells you nothing about how the thing feels under a real hand.
Fires when
Building or changing any control, screen, or flow a user interacts with.
How to apply
Before coding, narrate the interaction: "user does X, sees Y, expects Z" — and flag every gap where Y or Z is missing. After coding, walk the edge states you didn't design for: empty, zero results, a hundred thousand results, rapid repeated clicks, first run versus returning, panel closed versus open. Every clickable control must give feedback (a hover state, a cursor change), and you verify that in the running app — in many UI frameworks a bad style name silently falls back to a default and the build stays green either way. Offer the small touches that show care, like a count on hover or a brief fade.
Worked example
A toolbar icon is wired to its action and compiles cleanly, but it's drawn with a borderless style — no hover highlight, no cursor change. It works when clicked, yet it reads as dead, and users stop trusting that it does anything. Switching to a real button style and checking the hover and cursor live in the running app fixes the feel. The green build had nothing to say about it, because nothing about feel shows up at compile time.
Red flags
| Thought | Reality |
|---|---|
| "It compiles and returns the right value" | Correct and broken-feeling are not exclusive. |
| "The button's wired up" | Wired up but dead-looking reads as broken. |
| "I'll just check it built" | A build proves the code runs, not how it feels. |
| "Nobody clicks twice" | Someone always clicks twice. Handle it. |
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 · 30 lines · 27 tokens per session scan A af062c6228fc
ux-designer-mindset is a skill published in the GitHub repository Fergius-Engineering/instincts (2 stars, last pushed 11d ago), licensed MIT. It adds 27 tokens to every session and 443 once invoked, about $0.0001 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
gitnexus
将 GitNexus 作为受控可选代码智能能力接入,用于 brownfield MCP 查询、影响面分析、 detectchanges、多仓分析和更深代码图谱证据。输出必须回落到 /team- 主链和 artifacts。.
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…