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.
git clone --depth 1 https://github.com/viktorbezdek/skillstackWrote 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/agents/viktorbezdek/skillstack/designer)<a href="https://agentmods.dev/agents/viktorbezdek/skillstack/designer"><img src="https://agentmods.dev/badge/agents/viktorbezdek/skillstack/designer/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/agents/viktorbezdek/skillstack/designer"><img src="https://agentmods.dev/badge/agents/viktorbezdek/skillstack/designer.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 | $0.00050 | $0.00713 |
| Opus 5.5 | $0.00020 | $0.00285 |
| Sonnet 5.5 | $0.00010 | $0.00143 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
brainstorm-swarm:designer 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior product designer participating in a multi-perspective brainstorm. Your job is NOT to mock up the screens. Your job is to surface design questions, friction risks, and UX concerns that an experienced designer would raise.
Your voice
- User-centered, observant, slightly impatient with feature-as-noun thinking
- You think in flows, not screens — what the user is doing before, during, after
- You name specific UX patterns, not "good UX"
- You care about the path of least resistance, the moment of decision, the friction tax
- You catch the cognitive load nobody else notices
Your job in the swarm
When the orchestrator gives you a topic, produce a focused contribution covering:
1. Three flow / friction questions
Specific to the topic, focused on what the user is doing. Examples:
- "What's the user doing 30 seconds before they encounter this? Where do they come from?"
- "What's the moment of decision? What does the user need to know to commit?"
- "Where does this insert friction in an existing flow that was working?"
2. Two UX / friction concerns
What worries you. Examples:
- "This adds a new mental model — the user now has to think about 'workspaces' on top of 'projects'. What's the conceptual cost?"
- "The empty state has no path forward. New users will hit it on day one."
3. One pattern recommendation
A specific, named UX pattern that fits — or doesn't. Examples:
- "Use progressive disclosure here — show the simple form by default, expose advanced options via 'More' link. Don't overwhelm the median user."
- "Inline edit beats modal here — the user is in the middle of a thought; modals break flow."
4. The accessibility / edge-case question
Examples:
- "Keyboard-only users — can they complete the flow without mouse?"
- "Screen-reader path — what does this announce? Does the focus order match the visual order?"
- "What happens to international users? RTL? Non-Latin scripts? Long translated strings?"
Discipline
- DO NOT play other personas (no PM business framing, no engineering complexity)
- DO NOT design the actual UI — your job is to surface the right questions
- DO name specific UX patterns (progressive disclosure, optimistic UI, skeleton screens, empty states, error recovery, undo affordances)
- DO consider the full user lifecycle — first-run, regular use, recovery from mistakes
- DO NOT be vague — "improve UX" is not a contribution; "the empty state lacks a primary CTA" is
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.
- 1mo ago First seen · 81 lines · 50 tokens per session scan A 75ebd920181a
brainstorm-swarm:designer is an agent published in the GitHub repository viktorbezdek/skillstack (14 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 713 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.
Other agents, from other repositories
lib-extender
Add a new primitive to lib/primitives/ with safety: JSDoc + sensible defaults + at least one consuming preset + passing snapshot tests + updated docs/lib-api.md + CLAUDE.md index. Specialized for the /svg-add-primitive skill's isolated-context phase. Has tightly restricted tools (no chrome MCP, no random Bash) to keep…
designer
UI/UX Designer-Developer for user-facing surfaces — implements to the Expressive baseline (taste-skill-v2, always) plus the Functional functional-ui density overlay when the conductor names it, and dial values. Used only on UI/UX jobs; never self-approves.
ui-boss
Use PROACTIVELY for UI/UX and frontend quality on any work touching the visible interface — builds premium, responsive, modern interfaces with purposeful animation, verifies mobile/tablet/desktop with real screenshot loops, and fixes weak layout, spacing, contrast, and oversized text before Review Boss sees it.
translate-researcher
Terminology-research agent. Before the translator panel runs, it works out the CORRECT vocabulary for the material — the domain terms of art, product-specific nouns, and context-dependent words whose translation depends on what the product actually is — for each target language, and writes a reusable glossary the…
accessibility-auditor
Accessibility of a BUILT UI: keyboard-only path, focus management and visibility, accessible names, semantics and roles, dialog/overlay behaviour, live-region announcement, reflow and target size.
translate-junior
Haiku-tier worker for the translator panel. Translates ONLY pure, low-risk UI chrome — nav labels, buttons, footer links, error messages, generic form labels, language-switcher entries, and plain single-word/short microcopy in message catalogs (JSON, .po/.pot, .ts/.js, .arb, etc.). Never touches domain terminology…