mobbin-prompts

mobbin-prompts is a skill for Claude Code from LanSynergy/mobbin-mcp. It costs 67 tokens per session (583 once invoked), scanned A, original, MIT.

A prompt-writing tool that turns saved Mobbin references into structured instructions for coding agents and design reviews.

In plain words
What is it for?
Use it to create implementation briefs, analysis reports, onboarding notes, pull-request references, feature reviews, and context for Codex, Claude Code, Pi, or Mem Palace.
Why use it?
It gives an agent useful context from captured screens and flows instead of requiring you to explain every reference manually.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code; mentions Codex.

Good fit Use it to create implementation briefs, analysis reports, onboarding notes, pull-request references, feature reviews, and context for Codex, Claude Code, Pi, or Mem Palace.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lansynergy/mobbin-mcp/mobbin-prompts
Install

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.

Any agent
npx skills add LanSynergy/mobbin-mcp --skill mobbin-prompts
Clone the repo
git clone --depth 1 https://github.com/LanSynergy/mobbin-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for mobbin-prompts

README.md
[![agentmods](https://agentmods.dev/badge/skills/lansynergy/mobbin-mcp/mobbin-prompts/github.svg)](https://agentmods.dev/skills/lansynergy/mobbin-mcp/mobbin-prompts)
Your own site
<a href="https://agentmods.dev/skills/lansynergy/mobbin-mcp/mobbin-prompts"><img src="https://agentmods.dev/badge/skills/lansynergy/mobbin-mcp/mobbin-prompts/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.

agentmods 80×15 button for mobbin-prompts

Your own site · 80×15
<a href="https://agentmods.dev/skills/lansynergy/mobbin-mcp/mobbin-prompts"><img src="https://agentmods.dev/badge/skills/lansynergy/mobbin-mcp/mobbin-prompts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 583 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.00583
Opus 5 $0.00034 $0.00292
Sonnet 5 $0.00013 $0.00117
Haiku 4.5 $0.00007 $0.00058

Measured 9d ago against content hash 620396355a90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mobbin-prompts 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/mobbin-prompts.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

source/skills/mobbin-prompts/SKILL.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mobbin Prompts

Generate prompt-ready context from captured artifacts.

Use:

node scripts/mobbin-prompts.mjs <action> '<json>'

Selectors

All actions can select artifacts with artifact_ids, query, tags, type, app_name, feature_area, limit, and project_path.

Prefer selecting by feature_area, tags, or explicit artifact_ids when a prompt should stay tied to a specific captured flow. Direct Mobbin capture actions store flow steps, patterns, elements, source URLs, and visual hashes, so prompt output is strongest after capture-flow, capture-screen, or capture-site-sections has been used.

Actions

  • feature-prompt: unified MCP-equivalent prompt generator; mode is implementation, analysis, or onboarding
  • implementation-prompt: implementation brief from references; requires or benefits from objective
  • analysis-prompt: intended-vs-current analysis brief
  • onboarding-prompt: teammate onboarding brief
  • agent-context: target-specific context; target is codex, claude_code, pi, or mem_palace
  • pr-reference: PR-ready markdown; accepts title and objective
  • feature-review: diff-style review using intended_artifact_ids or intended_query, plus actual_artifact_ids or actual_query

Examples

node scripts/mobbin-prompts.mjs feature-prompt '{"mode":"implementation","objective":"Build checkout confirmation","feature_area":"checkout","limit":6}'
node scripts/mobbin-prompts.mjs implementation-prompt '{"objective":"Build checkout confirmation","feature_area":"checkout","limit":6}'
node scripts/mobbin-prompts.mjs analysis-prompt '{"objective":"Compare shipped checkout against saved Mobbin references","feature_area":"checkout","type":"flow","limit":4}'
node scripts/mobbin-prompts.mjs agent-context '{"target":"mem_palace","query":"onboarding","limit":10}'
node scripts/mobbin-prompts.mjs pr-reference '{"title":"Checkout reference pack","objective":"Implement the confirmation step","tags":["checkout"]}'
node scripts/mobbin-prompts.mjs feature-review '{"title":"Checkout review","intended_query":"checkout references","actual_query":"checkout shipped"}'

Read the full file on GitHub · 45 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 9d ago First seen · 45 lines · 67 tokens per session scan A 620396355a90

Subscribe to this mod's changes

mobbin-prompts is a skill published in the GitHub repository LanSynergy/mobbin-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 67 tokens to every session and 583 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

google-labs-code/stitch-skills · 41 tokens

stitch-ued-guide

Visual vocabulary, design terminology, and prompt engineering strategy for Stitch. Reference this when you need layout pattern names, aesthetic style terms, color structure formulas, or device guidelines.

gabelul/stitch-kit · 40 tokens

ai-interaction-patterns

AI UX patterns — prompt UX, wayfinding, HITL, trust, disclosure, memory, generative UI.

terrene-foundation/kailash-coc-claude-py · 29 tokens

stitch-ui-prompt-architect

Builds Stitch-ready prompts via two paths — Path A enhances vague ideas into polished prompts, Path B merges a Design Spec JSON + user request into a structured [Context] [Layout] [Components] prompt.

gabelul/stitch-kit · 50 tokens

ai-product-design

Design or improve an AI-assisted feature, copilot, agent, recommendation, generation, or automation workflow with explicit capability boundaries, user control, recovery, trust, and evaluation. Trigger on "design this AI feature", "improve this copilot", or "plan this agent workflow". Do not default every AI product to…

aditya-ariosity/ux-ui-skills · 70 tokens

ai-feedback-loops

Design feedback mechanisms that help AI systems learn from users - thumbs up/down, preference ranking, corrections, and human-in-the-loop escalation. Use when: RLHF UX, user feedback for AI, thumbs up down design, AI correction flow, human in the loop, feedback signal design, AI improvement loops.

varunk130/ai-ux-skill-library · 66 tokens