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/jircdev/crew-plugin/designnpx skills add jircdev/crew-plugin --skill designgit clone --depth 1 https://github.com/jircdev/crew-pluginWhat 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 | $0.00152 | $0.03047 |
| Opus 5 | $0.00076 | $0.01523 |
| Sonnet 5 | $0.00030 | $0.00609 |
| Haiku 4.5 | $0.00015 | $0.00305 |
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 yesterday.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design — the interface craft
The domain truth belongs to the owning role (informational spec to data-experience-architect, visual authority to ux-architect, implementation to frontend-architect, verdict to qa-test-architect). This skill governs how you get from a problem to a composition, and how you prove the composition is good.
The frontier this skill respects
The plugin carries method; the project carries capability and memory. What is beautiful here, which components exist, which references this product aspires to, which patterns it has rejected — none of that is in this file, and none of it may be invented. It is declared by the project in docs/design/ (memory) and crew.json (capabilities).
Test of the opposite aesthetic — apply it to every sentence you are about to write as if it were a rule: would this still be true in a project with the opposite aesthetic, another stack, and other form factors? If not, it is not method — it is taste, and taste belongs to the project. Never smuggle a value, a palette, a scale, a spacing rhythm, a named style, or a library into a recommendation as if it were craft.
Before anything: read the capability
Read crew.json and docs/design/. Each declared capability enables something and each absence forces a named admission. Never degrade silently.
| Declared | Enables | Absent → you must say |
|---|---|---|
design.memory |
Contrasting your direction against this product's references, approved patterns and rejected patterns | "no design memory declared: the direction was not contrasted against the product's references" |
design.baseline |
Falling back to an aesthetic baseline the project named — a skill or a document — when the memory is silent on the question at hand | "no memory and no baseline declared: the direction rests on the brief alone" |
design.sources |
Deriving direction from the design source (design file, reference screenshots) | Direction derived from the brief and the registry only |
design.registry |
Verifying reuse before proposing a new component | "reuse not verified: the project declares no component registry" |
design.runtime.url |
Connecting to and inspecting a running app without asking permission each turn | Ask, as before |
design.runtime.launch |
Running the declared launch profile without asking permission each turn | Ask, as before |
design.capture |
A verdict on visual quality | Code conformity only, labeled as such |
design.checks |
Asserting accessibility or performance as measured | Assert them as reasoned, labeled not measured |
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.
- yesterday First seen · 145 lines · 152 tokens per session scan A 56623886627c
design is a skill published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 152 tokens to every session and 3,047 once invoked, about $0.0008 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…