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 LanSynergy/mobbin-mcp --skill mobbin-flow-architectgit clone --depth 1 https://github.com/LanSynergy/mobbin-mcpWrote 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/lansynergy/mobbin-mcp/mobbin-flow-architect)<a href="https://agentmods.dev/skills/lansynergy/mobbin-mcp/mobbin-flow-architect"><img src="https://agentmods.dev/badge/skills/lansynergy/mobbin-mcp/mobbin-flow-architect/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/lansynergy/mobbin-mcp/mobbin-flow-architect"><img src="https://agentmods.dev/badge/skills/lansynergy/mobbin-mcp/mobbin-flow-architect.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 | $0.00244 | $0.03196 |
| Opus 5 | $0.00122 | $0.01598 |
| Sonnet 5 | $0.00049 | $0.00639 |
| Haiku 4.5 | $0.00024 | $0.00320 |
Grade A, and why
mobbin-flow-architect 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 9d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobbin Flow Architect
Turn a great flow you can see on Mobbin into a great flow inside this project.
The job is not to photocopy screens. A reference app's flow is a teacher: it shows how an experienced team sequenced steps, removed friction, and built momentum toward a goal. Your work is to extract that transferable structure, leave the incidental brand/domain/visual identity behind, and re-instantiate the structure inside the current project's own domain, design system, and constraints — enhancing it where the project has an advantage the reference lacked. Copying produces a costume; adapting produces a flow that genuinely belongs to the product.
How everything is invoked
Every Mobbin capability is reachable through one CLI. Prefer it for deterministic orchestration:
npx -y @aos-engineer/mobbin-mcp skill <action> '<json-payload>'
The four sibling skills (mobbin-search, mobbin-capture, mobbin-prompts,
mobbin-visuals) wrap the same actions; invoke them when you want their extra
guidance, but the CLI above is enough to drive the whole pipeline. Run
npx -y @aos-engineer/mobbin-mcp skill --help to see every action.
Before anything else, confirm live access. doctor only reads local files, so
it passes even when the token is expired — never trust it alone. Verify with one real
call:
npx -y @aos-engineer/mobbin-mcp skill doctor '{}'
npx -y @aos-engineer/mobbin-mcp skill quick-search '{"query":"onboarding","platform":"ios"}'
Run that first authenticated call on its own, before firing any others. Mobbin's
refresh token is single-use, so several skill calls launched in parallel while the
token is expired will race to rotate it and all fail. Once one call succeeds, the rest
are safe to batch.
If Mobbin is unreachable (auth expired, refresh_token_already_used, or API
errors), do not silently invent a flow and do not bury the result in empty stub files.
Instead:
- Surface the one-command fix prominently — tell the user to run
npx -y @aos-engineer/mobbin-mcp auth. It is interactive (browser login), so they run it, not you; in this CLI they can prefix it with!. - Then offer a choice: wait for re-auth and run the real pipeline, or let you draft a provisional spec now from general product knowledge of the reference, to be verified against real captures once auth is restored.
- If they pick provisional, switch to Provisional mode (see below) and label it unmistakably. Never present recalled-from-memory structure as if it were captured from Mobbin — that exact confusion is what this skill exists to prevent.
What ships with it
4 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.
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.
- 9d ago First seen · 244 lines · 244 tokens per session scan A 810fbdfa6d0b
mobbin-flow-architect is a skill published in the GitHub repository LanSynergy/mobbin-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 244 tokens to every session and 3,196 once invoked, about $0.0012 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.