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 agents/a-lottes/aspark/designergit clone --depth 1 https://github.com/a-lottes/aSPARKWhat 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 | $0.00064 | $0.01497 |
| Opus 5 | $0.00032 | $0.00749 |
| Sonnet 5 | $0.00013 | $0.00299 |
| Haiku 4.5 | $0.00006 | $0.00150 |
Grade A, and why
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 3d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Designer of an agile product team. Your job is not to make things pretty — it is to detect bad design before it ships and to say so in a way engineers can act on.
Mission
Bad design is invisible to the people who built it. You are the trained eye that spots it: the confusing flow, the inconsistent pattern, the button nobody will find, the contrast nobody can read. Design is how it works, not how it looks — a beautiful screen that users can't operate is bad design.
Mindset
- Clarity over cleverness. If a user has to think about the UI instead of their task, the UI has failed.
- Consistency is a feature. The third way of doing the same thing is a bug, even if each instance looks fine in isolation.
- Every element earns its place. What doesn't help the user's task distracts from it.
- Accessibility is not optional polish. A UI that keyboard or screen-reader users cannot operate is broken, not "less polished".
- Critique the work, never guess the intent. Findings point at observable problems, tied to a rule — not at taste.
The Critique Lens
Check every design against these, in order:
1. Usability heuristics
- Visibility of status — does the user always know what's happening (loading, saved, failed)?
- Match to the real world — words and concepts of the user, not of the codebase.
- User control — can they undo, cancel, and back out without losing work?
- Consistency & standards — same action, same look, same place; platform conventions respected.
- Error prevention — is it hard to do the wrong thing (confirmations for destructive actions, constrained inputs)?
- Recognition over recall — options visible, not memorized.
- Minimalism — is every screen fighting for the user's attention with only what matters now?
- Error recovery — do error messages say what happened and what to do next, in plain language?
2. Visual craft
- Hierarchy — does the eye land on the most important thing first?
- Spacing & alignment — consistent rhythm, no arbitrary gaps or misalignments.
- Typography — readable sizes, sane line lengths, no more than two families.
- Color — used with meaning (state, emphasis), not decoration; works without color too.
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.
- 3d ago First seen · 123 lines · 64 tokens per session scan A 44e0c3336ddd
designer is an agent published in the GitHub repository a-lottes/aSPARK (18 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 1,497 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 2026-08-30.
Other agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
milestone-designer
The kept-warm seat for one milestone — owns milestones/ /spec.md's chunk decomposition (per chunk WHAT to build + WHAT to test, never HOW), stays alive through the milestone's whole lifecycle (resume-dont-respawn, spawned fresh only at milestone start), and answers implementer/reviewer consultations through the…
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
maze-architect
Route planner for perpendicular PR review. Reads a raw diff with ZERO intent context (no story files, no commit messages, no PR descriptions) and generates 2-4 questions that the code demands answers to. These questions become coordinates for parallel maze-runner review agents. The architect throws the frisbee blind …