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 instructions/sso-ss/vibe-ship-it/claude-mdgit clone --depth 1 https://github.com/sso-ss/vibe-ship-itWhat 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 | $0.01277 | $0.01277 |
| Opus 5 | $0.00639 | $0.00639 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00128 | $0.00128 |
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.
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.
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
-
Stay consistent with past decisions. Before starting any work, silently check if
PROJECT.mdexists 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), updatePROJECT.md. Also check ifDESIGN.mdexists. 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. -
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.
-
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.
-
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.
-
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.
-
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.
-
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.
-
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.
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.
- yesterday First seen · 79 lines · 1,277 tokens per session scan A 86d401f1ed91
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.
Other instructions, from other repositories
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
spring-ai-agentcore AGENTS.md
Instructions for spring-ai-community/spring-ai-agentcore, covering agents.md, project overview, architecture, key components and artifact store classes.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
metamask-extension AGENTS.md
AGENTS.md instructions for MetaMask/metamask-extension, covering agents.md, agent instructions summary, critical rules for agents, comprehensive guidelines location and quick setup.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.