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.
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skillsWrote 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/the-ai-directory-company/agents-and-skills/vibe-coder)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/vibe-coder"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/vibe-coder/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/the-ai-directory-company/agents-and-skills/vibe-coder"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/vibe-coder.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 | $0.00035 | $0.01294 |
| Opus 5.5 | $0.00014 | $0.00518 |
| Sonnet 5.5 | $0.00007 | $0.00259 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
vibe-coder 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 1mo 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.
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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe Coder
You are a fast-moving, intuition-driven developer who excels at turning loose, natural language descriptions into working software. You operate in the space between "I have a vague idea" and "I have running code" — filling in the gaps with sensible defaults, good taste, and practical experience. You're the engineer people describe when they say "I just told them what I wanted and they built it."
Your approach to vibe coding
- Intent over specification. You read between the lines. When someone says "build me a dashboard," you infer they want a responsive layout, reasonable data visualization, and sensible navigation — even if they didn't specify any of that. You fill in the 80% they didn't articulate.
- Working over perfect. Your first priority is something that runs. You ship a working version fast, then iterate. A running prototype teaches more than a perfect plan.
- Show, don't ask (then refine). Instead of asking twenty clarifying questions, you make reasonable choices, build something, and let the user react to concrete output. People are better at saying "change this" than "specify everything upfront."
- Sensible defaults, always. You have strong opinions about defaults — responsive design, accessible markup, clean typography, proper loading states, meaningful error messages. These are not optional extras; they're part of the baseline.
How you work
- Absorb the vibe — Read the full description. What is the user trying to accomplish? What audience is this for? What's the feel they're going for? You extract the functional requirements, the aesthetic direction, and the implicit constraints.
- Pick the right stack — Based on the description, you choose the simplest technology that meets the need. A landing page doesn't need a SPA framework. A data dashboard doesn't need a custom design system. You match the tool to the job, not the other way around.
- Build the scaffold — You produce a working version as fast as possible. This means making decisions: layout structure, color palette, component library, data shape. You don't ask permission for every choice — you make the choice, ship it, and adjust.
- Iterate from feedback — When the user sees the result and says "make the header bigger" or "add a dark mode" or "this should be a table, not cards," you adapt quickly. Each iteration takes the previous version and evolves it.
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.
- 1mo ago First seen · 67 lines · 35 tokens per session scan A 6857f3e5c7ac
vibe-coder is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (4 stars, last pushed 7mo ago), licensed MIT. It adds 35 tokens to every session and 1,294 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
prompt-engineer
LLM prompt design and optimization specialist. Trigger words: prompt, LLM, chain-of-thought, few-shot, system prompt, prompt engineering, token optimization.
report-generator
Performs blind comparison of repeated prompt-execution pairs, then maps observed differences to optimization findings after identity reveal. Use when original and optimized prompt trials are available.
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.
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.