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/donald-ada/workinggenius/designernpx skills add donald-ada/workinggenius --skill designergit clone --depth 1 https://github.com/donald-ada/workinggeniusWrote 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/donald-ada/workinggenius/designer)<a href="https://agentmods.dev/skills/donald-ada/workinggenius/designer"><img src="https://agentmods.dev/badge/skills/donald-ada/workinggenius/designer.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 | $0.00069 | $0.02197 |
| Opus 5 | $0.00034 | $0.01099 |
| Sonnet 5 | $0.00014 | $0.00439 |
| Haiku 4.5 | $0.00007 | $0.00220 |
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 today.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designer
UI built without a style conversation wears the model's default aesthetic — the look it would produce for any product, which means it was chosen for none. That default is momentum, not design. And taste is the fork that belongs most completely to the user's world, yet it's the one the momentum of building never stops to ask about.
The concept: know who is looking and where; name the base and the delta; settle the delta by looking; commit one language as tokens. A design language is a contract between every screen this product will ever have — which is why it is written once, as named values with roles, and not re-decided per screen.
The discipline
-
Audience and context come before taste. Who uses this, on what, for how long, and in what state of mind — a nurse glancing at a phone between patients, an analyst at a desk for eight hours, a buyer deciding in thirty seconds — decides density, type size, motion budget and contrast before anyone has an opinion about colors. Ask it first, in one exchange, because a delta chosen against the wrong audience is a beautiful mistake: the dense dashboard the analyst wanted is unreadable at a glance, and the airy landing page is useless at a desk all day. DESIGN.md records the answer as the first thing a later screen reads.
-
The first question after that is the base — and how much of it survives. An existing surface, a brand guide, a shipped base (13 curated templates live in this skill's
bases/folder — minimal, editorial, neobrutalism, glassmorphism, neumorphism, bento, mono, retro, neon, paper, premium, corporate, claymorphism — vendored MIT from awesome-design-skills, whose full 67-template catalog stays one pull upstream), a famous style, or nothing. Delta zero is adopting: a successful outcome, one exchange, no research. A named delta is a remix: the base survives except where the user has their own understanding. No base is crafting from the problem itself. Cost follows the delta — research only ever covers the part no base answers. A shipped base is a starting token set; its generic rule lists are not this product's rules, and the language is the delta written down.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- bases/bento.md 4.0 KB
- bases/claymorphism.md 4.1 KB
- bases/corporate.md 4.5 KB
- bases/editorial.md 4.2 KB
- bases/glassmorphism.md 4.4 KB
- bases/minimal.md 3.9 KB
- bases/mono.md 4.3 KB
- bases/neobrutalism.md 3.9 KB
- bases/neon.md 3.9 KB
- bases/neumorphism.md 4.3 KB
- bases/paper.md 3.9 KB
- bases/premium.md 3.9 KB
- bases/retro.md 3.9 KB
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.
- today Changed · +59 lines · +17 tokens per session d34a39aeac21
- 6d ago First seen · 21 lines · 52 tokens per session scan A cdda03370b1f
designer is a skill published in the GitHub repository donald-ada/workinggenius (6 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 2,197 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
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.
grill
Interrogate a plan or decision one question at a time before capture, keeping a decision-plus-rationale ledger, then route to the right capture skill.
dw-doctor
Read-only environment diagnostic for a solo-lane repo: whether the tools the hooks and skills assume are installed and whether the repo's guardrails will really fire, each gap reported with a copy-paste fix.
dw-handoff
Compact the live session into .ai/work/ /HANDOFF.md — how far into the current task you are, what is applied but uncommitted, and which dead ends are already ruled out, so the next context window resumes mid-task. Explicit-invoke only.
dw-next
The solo lane's build step and its resume point in one skill: report where the active .ai/work/ /CHANGE.md stands — read from disk, so it survives a /clear — then build every remaining unticked task, one commit each.