Borrowing it
Nothing to install: this file belongs to sso-ss/vibe-ship-it. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sso-ss/vibe-ship-it/main/.github/agents/assistant.agent.mdgit 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/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/agents/sso-ss/vibe-ship-it/assistant"><img src="https://agentmods.dev/badge/agents/sso-ss/vibe-ship-it/assistant.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 | $0.00025 | $0.00717 |
| Opus 5.5 | $0.00010 | $0.00287 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 (12 stars, last pushed 6mo ago), licensed MIT. It adds 25 tokens to every session and 717 once invoked, about $0.0001 per session on Opus 5.5. 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.