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/tomzx/agents/create-mockupsnpx skills add tomzx/agents --skill create-mockupsgit clone --depth 1 https://github.com/tomzx/agentsWhat 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 | $0.00034 | $0.01757 |
| Opus 5 | $0.00017 | $0.00879 |
| Sonnet 5 | $0.00007 | $0.00351 |
| Haiku 4.5 | $0.00003 | $0.00176 |
Grade A, and why
create-mockups scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Mockups
Produces UI mockups and wireframes for a feature from its requirements and specification, settling the visual layout, component breakdown, interaction states, and flows before a line of UI code is written.
Without this step, UI work starts with no shared picture of what to build, so layout, states, and accessibility are improvised during implementation and reworked in review.
For features with no user interface (a pure API, a background job, a CLI), skip this phase and state the skip explicitly.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - If no argument is provided, locate the feature directory under
.sdlc/features/whose frontmatterissuefield references$ISSUE_NUMBER. .sdlc/features/N-<slug>/requirements.md(must have passed review with findings verdictapproved), or a requirements document provided in context or as a file path ($1).sdlc/features/N-<slug>/specification.md(must have passed review with findings verdictapproved, if produced): reuse the data models, API contracts, and flows it defines so the mockups stay faithful to what the system can actually deliver.sdlc/features/N-<slug>/lifecycle.md(optional, if a lifecycle document was produced): reflect resource states and transitions in the UI states (e.g., show different views or disabled actions based on the resource's current state).sdlc/features/N-<slug>/codebase-analysis.md(optional, if existing code was analyzed): reuse existing UI components and patterns it inventoried, and honor any "must not change" constraints on shared components
Steps
- Read the requirements, the specification if present, and the codebase analysis if present.
- Decide whether the feature has a UI surface. If it does not, emit
verdict: skipped(do not writemockups.md). Theskippedverdict routes the pipeline straight to the next phase, bypassing/review-mockups. - Inventory every screen, view, or dialog the feature needs, cross-referenced against the requirements and the spec's flows.
- For each screen, draw an ASCII wireframe inside a fenced block, annotated with the regions, primary action, and data shown.
- Break the UI down into components, marking which already exist in the codebase (reuse), which must be extended, and which are new.
- For each key component and screen, enumerate its interaction states: empty, loading, populated, error, and disabled or read-only where relevant.
- Map the navigation between screens as a flow, including entry points, exits, and the back path.
- Specify responsive behavior across the viewports the feature targets (mobile, tablet, desktop), noting what collapses, reorders, or hides.
- Call out accessibility requirements: keyboard reachability, focus order and visible focus, screen-reader labels, color-contrast targets, and minimum touch-target sizes.
- Note copy and content as placeholders so writers can fill them without changing layout.
- Flag where high-fidelity mockups (Figma, HTML/CSS, a prototype) are warranted and cannot be conveyed by ASCII, and record a pointer or a request for them.
- Write the output to
.sdlc/features/N-<slug>/mockups.md.
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 · 161 lines · 34 tokens per session scan A e12a8d2da57c
create-mockups is a skill published in the GitHub repository tomzx/agents (5 stars, last pushed 6d ago), licensed MIT. It adds 34 tokens to every session and 1,757 once invoked, about $0.0002 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…