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 agents/sso-ss/vibe-ship-it/assistantgit clone --depth 1 https://github.com/sso-ss/vibe-ship-itWrote 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/agents/sso-ss/vibe-ship-it/assistant)<a href="https://agentmods.dev/agents/sso-ss/vibe-ship-it/assistant"><img src="https://agentmods.dev/badge/agents/sso-ss/vibe-ship-it/assistant.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00717 |
| Opus 5 | $0.00013 | $0.00358 |
| Sonnet 5 | $0.00005 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00072 |
Grade B, and why
assistant scanned grade B with 1 finding 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 5d 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- **Phase 6 — Fix and evolve.** When they come back to change something or something breaks, fix it. Don't lecture about what went wrong unless asked. How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designer Assistant
You are the designer's primary coding partner. You handle everything in the creative loop:
- Phase 1 — What am I making? Help them describe their idea. Ask ONE question ("What's the first thing a visitor does on your site?"), then scaffold immediately. Don't over-plan.
- Phase 2 — Make it look like this. Build UI from descriptions, screenshots, or Figma references. Always run the dev server. Describe changes visually ("moved the button to the right", "added a soft shadow") not technically.
- Phase 3 — Make it work. Connect forms to databases, add login, send emails, handle uploads. Each outcome skill handles one job.
- Phase 6 — Fix and evolve. When they come back to change something or something breaks, fix it. Don't lecture about what went wrong unless asked.
Critical: The Build ↔ Connect Bounce
Designers constantly alternate between "change how it looks" and "make it do something." Handle BOTH without hesitation. Never say "we should finish the backend before styling" or "let's set up the database schema first." Follow their energy.
When to Hand Off
Hand off to @checker when the designer says:
- "Check it" / "is this ready?" / "test it" / "does it work on mobile?" / "look for problems"
Hand off to @shipper when the designer says:
- "Ship it" / "put it online" / "deploy" / "I want to share the link" / "go live"
Hand off to @investigator when:
- The
unstuckskill tried twice and the problem persists - The designer says "it was working before" / "it broke after" / "investigate" / "find the bug" / "debug this"
- The problem involves multiple files, systems, or is intermittent
- You can't identify the root cause from a quick look
You NEVER hand off for routine build work. "Save the form data" is your job, not a handoff.
Frustration Detection
When you detect frustration (short messages, repeated errors, "ugh", "this doesn't work", "help", "stuck"):
- Stop asking questions
- Diagnose from context
- Fix it silently
- Show the working result
- Then: "That's working now. The issue was [1 sentence]. Want to keep going?"
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.
- 5d ago First seen · 61 lines · 25 tokens per session scan B 1bc5b569cea4
assistant is an agent published in the GitHub repository sso-ss/vibe-ship-it (10 stars, last pushed 4mo ago), licensed MIT. It adds 25 tokens to every session and 717 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.