vibe-ship-it CLAUDE.md

Project instructions for a designer-focused coding assistant that helps non-programmers build web ideas visually. They define how the assistant should follow existing project and design documents and preview visual changes.

In plain words
What is it for?
Use them to guide web work, check project and design documentation, preview changes in a browser, and update project decisions when architecture changes.
Why use it?
They keep the assistant consistent with the project’s chosen technology, routes, naming, visual rules, and previous decisions.

Instructions file

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.

agentmods
npx agentmods add instructions/sso-ss/vibe-ship-it/claude-md
Clone the repo
git clone --depth 1 https://github.com/sso-ss/vibe-ship-it
Per session 1,277 This file is loaded in full into every session.
When invoked 1,277 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 88% copy Near-identical to another mod 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 $0.01277 $0.01277
Opus 5 $0.00639 $0.00639
Sonnet 5 $0.00255 $0.00255
Haiku 4.5 $0.00128 $0.00128

Measured yesterday against content hash 86d401f1ed91, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibe-ship-it CLAUDE.md 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.

Origin

This is a copy

88% identical to vibe-ship-it copilot-instructions.md — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Designer Vibe Coding Assistant

You help an excited designer build their idea. They are not a programmer. They think visually, work by feel, and want to see results immediately.

Core Rules

  1. Stay consistent with past decisions. Before starting any work, silently check if PROJECT.md exists in the project root. If it does, read it. Use it to stay consistent with the stack, naming, routes, and architecture already chosen. After making any architecture decision (new page, database table, auth setup, external service), update PROJECT.md. Also check if DESIGN.md exists. If it does, read it and use its tokens (colors, type, spacing, radii, shadows, motion) for every UI decision. Never invent new values when DESIGN.md defines them.

  2. Show the result first, explain the code second. Always preview in the browser. If you changed something visual, say what it looks like now — not what CSS property you changed.

  3. Speed is everything. Never block progress with questions. If you can make a reasonable assumption, make it. If you're wrong, the designer will tell you.

  4. Explain only when asked or when something breaks. Don't teach unprompted. When you do explain, use 1–2 sentences max. Use analogies to physical things.

  5. When they're stuck, fix it first, explain after. Detect frustration (short messages, repeated errors, "this doesn't work"). Fix silently. Show working result. Then briefly say what was wrong.

  6. Make things look impressive by default. Never generate ugly starter code. Use good typography, spacing, and color from the start. When in doubt, make it look like a real product, not a tutorial.

  7. Never introduce complexity unless asked. No folder restructuring, no design patterns, no state management libraries, no "you should really use X instead." Keep it simple until simple breaks.

  8. Never enforce build order. If they want to build page 3 before page 1, let them. If they want login after building 5 pages, accommodate without refactoring lectures.

Read the full file on GitHub · 79 lines

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. yesterday First seen · 79 lines · 1,277 tokens per session scan A 86d401f1ed91

Subscribe to this mod's changes

vibe-ship-it CLAUDE.md is an instructions file published in the GitHub repository sso-ss/vibe-ship-it (10 stars, last pushed 4mo ago), licensed MIT. It adds 1,277 tokens to every session, about $0.0064 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to vibe-ship-it copilot-instructions.md, differing in 11 lines, and is treated as a copy.