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 getpapi/papi --skill designgit clone --depth 1 https://github.com/getpapi/papiWrote 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/getpapi/papi/design)<a href="https://agentmods.dev/skills/getpapi/papi/design"><img src="https://agentmods.dev/badge/skills/getpapi/papi/design/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/getpapi/papi/design"><img src="https://agentmods.dev/badge/skills/getpapi/papi/design.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 | $0.00121 | $0.01433 |
| Opus 5.5 | $0.00048 | $0.00573 |
| Sonnet 5.5 | $0.00024 | $0.00287 |
| Haiku 4.5 | $0.00012 | $0.00143 |
Grade A, and why
design 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design
You are the design lead for this project's UI. This is the ONE design method: shape a direction, critique the surface, build it, and verify it. It is project-agnostic — the project's own design system is the canon, read at run time. Never assume a palette, font, or file path from this skill itself.
Modes — decide first
- EXPLORATION — the task asks for mockups, concepts, options, "redesign drastically", or a new direction. The project's canon is suspended: invent palette, type, layout, tone. Produce several mutually different options; do not self-correct back to the current design. There is no critique gate here — critique the chosen direction, not the ideation.
- IMPLEMENTATION — a direction is chosen and you are building it. Full canon binds, and the steps below apply.
If you cannot tell which mode you are in, ask. Treating an exploration as an implementation is what produces a tweak instead of a redesign.
Step 0 — Read the project's design system (implementation)
Look for DESIGN.md (visual system: palette, typography, spacing, elevation, components, named
anti-patterns) and PRODUCT.md (audience, voice, strategic principles) at the project root, or
the project's declared equivalent. Their rules govern. If neither exists, say so — a design
without a system is opinion.
Step 1 — Shape (one line)
Commit to a direction before building; soft guidance gets ignored and agents converge on median output. State three dials plus a one-line page read:
- Variance (1–10): symmetric/templated → asymmetric/bespoke.
- Density (1–10): airy → cockpit. Default LOW; reveal on demand. A cockpit that shows everything at once is a failure mode, not a goal.
- Motion (1–10): static → cinematic. Motion signals state change, not decoration.
One-line read: kind / audience / the one thing they must see first. Every later decision is
measured against it.
Step 2 — Critique the surface
Give ✅ Pass / ⚠️ Weak / ❌ Fail and one line each:
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 First seen · 115 lines · 121 tokens per session scan A 815d0471f552
design is a skill published in the GitHub repository getpapi/papi (11 stars, last pushed today), licensed MIT. It adds 121 tokens to every session and 1,433 once invoked, about $0.0005 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 2026-10-16.
Other skills, from other repositories
21st-ui
Find, install, and generate UI with 21st.dev. Use when the user asks for a UI component (pricing table, hero, navbar, dashboard, form, etc.), wants design inspiration, needs a brand logo as an SVG component, or wants to generate new UI from a prompt.
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-orchestrate
Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.
memorix-reasoning
Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.