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.
git clone --depth 1 https://github.com/tercumantanumut/seleneWrote 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/commands/tercumantanumut/selene/mockup)<a href="https://agentmods.dev/commands/tercumantanumut/selene/mockup"><img src="https://agentmods.dev/badge/commands/tercumantanumut/selene/mockup/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/commands/tercumantanumut/selene/mockup"><img src="https://agentmods.dev/badge/commands/tercumantanumut/selene/mockup.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 | $0.00019 | $0.00270 |
| Opus 5.5 | $0.00008 | $0.00108 |
| Sonnet 5.5 | $0.00004 | $0.00054 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
mockup 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 1mo 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.
What it actually says
Use this command when a user already has one or more real screenshots and wants a framed app mockup without ML image generation.
Preferred flow:
- Confirm or infer the source screenshot path.
- Pick the closest preset for the request.
- Run:
npm --prefix selene-plugins/app-mockup-kit run render -- --input <path-or-url> --output <output.svg> --preset <preset> - Return the output path plus the preset used.
Common presets:
browser-chromebrowser-safariiphone-14-propixel-6-proipad-promacbook-prowindowplain
Useful flags:
--title "Launch Week"--subtitle "New analytics dashboard"--url "selene.sh/pricing"--background "gradient:#0f172a,#2563eb"--padding 72--shadow lifted
If the source is a webpage URL rather than an image, capture a screenshot first with the host agent's browser tooling, then pass the saved screenshot into the renderer.
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.
- 1mo ago First seen · 34 lines · 19 tokens per session scan A 92ecbd571cd1
mockup is a command published in the GitHub repository tercumantanumut/selene (172 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 270 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
agentlas-local
Staff a task only from Agentlas agents registered on this machine.
Checkpoint Commit
Commit changes at meaningful checkpoints throughout the workflow.
speckit.review.errors
Error handling review — silent failure detection, catch block analysis, error logging.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.