Borrowing it
Nothing to install: this file belongs to wandb/vibes. 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/wandb/vibes/main/AGENTS.mdgit clone --depth 1 https://github.com/wandb/vibesWrote 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/instructions/wandb/vibes/agents-md)<a href="https://agentmods.dev/instructions/wandb/vibes/agents-md"><img src="https://agentmods.dev/badge/instructions/wandb/vibes/agents-md/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/instructions/wandb/vibes/agents-md"><img src="https://agentmods.dev/badge/instructions/wandb/vibes/agents-md.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 | $0.01389 | $0.01389 |
| Opus 5.5 | $0.00556 | $0.00556 |
| Sonnet 5.5 | $0.00278 | $0.00278 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade A, and why
vibes AGENTS.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 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.
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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Prompting Guide
General strategies for working effectively with AI coding assistants across all platforms (Claude, Gemini, GPT, etc.).
Core Principles
1. Treat AI as a Collaborative Partner
- Share your thought process and constraints
- Ask for alternatives and trade-offs
- Build on AI suggestions iteratively
2. Provide Rich Context
- Include relevant code, error messages, and project details
- Mention your experience level and learning goals
- Specify your environment (frameworks, tools, constraints)
3. Think in Systems
- Break complex problems into smaller components
- Consider interactions between different parts
- Plan for scalability and maintainability
Universal Prompting Patterns
The STAR Method
Situation - Task - Action - Result
Situation: I'm building a React app with TypeScript
Task: Need to implement user authentication
Action: Show me how to create a login form with validation
Result: Should handle success/error states and redirect users
The 5W+H Framework
Who, What, When, Where, Why, How
Who: Junior developer learning Node.js
What: Build a REST API for a blog
When: Need it working by end of week
Where: Using Express.js and MongoDB
Why: Portfolio project for job applications
How: Step-by-step implementation with explanations
Chain of Reasoning
Ask the AI to show its thinking process:
"Think through this step by step:
1. What are the main challenges with this approach?
2. What are 3 different solutions?
3. What are the pros/cons of each?
4. Which would you recommend and why?"
Advanced Agentic Techniques
1. Role Assignment
Give the AI specific expertise:
"Act as a DevOps engineer with 10 years of AWS experience.
How would you set up CI/CD for this Node.js application?"
2. Perspective Taking
Ask for multiple viewpoints:
"From a security perspective... From a performance perspective... From a maintainability perspective..."
3. Socratic Method
Let the AI guide your learning:
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 · 226 lines · 1,389 tokens per session scan A 648556194c69
vibes AGENTS.md is an instructions file published in the GitHub repository wandb/vibes (37 stars, last pushed 1y ago), licensed Apache-2.0. It adds 1,389 tokens to every session, about $0.0056 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 2026-09-02.
vibes AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vibes AGENTS.mdwandb/vibes | Instructions file | 37 | 1y ago | Apache-2.0 | A | 1,389 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |