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/wandb/vibes/claude-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/claude-md)<a href="https://agentmods.dev/instructions/wandb/vibes/claude-md"><img src="https://agentmods.dev/badge/instructions/wandb/vibes/claude-md.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 | $0.01047 | $0.01047 |
| Opus 5 | $0.00524 | $0.00524 |
| Sonnet 5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
vibes 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 2d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Prompting Guide
Basic Usage
claude
claude "Your prompt here"
Claude Code Specific Features
Slash Commands
Claude Code supports custom slash commands. Create them in your project root:
# Example: Add to your project's .claude/commands/
/slides - Regenerate presentation slides
Memory Management
Claude Code maintains context across conversations. Use CLAUDE.md files to provide persistent context.
Agentic Prompting Techniques
1. Multi-Step Planning
Claude excels at breaking down complex tasks:
claude "I need to implement user authentication. First, create a plan with all the necessary steps."
2. Code Analysis and Refactoring
Leverage Claude's code understanding:
claude "Analyze this codebase structure and suggest architectural improvements: [paste code or file paths]"
3. Interactive Development
Build solutions iteratively:
claude "Start building a React component for user profiles. Begin with the basic structure."
# Then: "Add form validation to the profile component"
# Then: "Add state management with useReducer"
4. Documentation Generation
Claude is excellent at creating comprehensive docs:
claude "Generate API documentation for this Express.js router: [code]"
5. Test-Driven Development
Use Claude to guide TDD workflows:
claude "Write failing tests for a user authentication service, then implement the service to make them pass"
Advanced Techniques
System Thinking
claude "Think like a system architect. How would you design a scalable microservices architecture for an e-commerce platform?"
Code Review Partner
claude "Act as a senior code reviewer. What potential issues do you see in this implementation? Consider security, performance, and maintainability."
Debugging Assistant
claude "I'm getting this error: [error message]. Here's my code: [code]. Walk me through debugging this step by step."
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.
- 2d ago First seen · 175 lines · 1,047 tokens per session scan A d042cb8e6b73
vibes CLAUDE.md is an instructions file published in the GitHub repository wandb/vibes (37 stars, last pushed 1y ago), licensed Apache-2.0. It adds 1,047 tokens to every session, about $0.0052 per session on Opus 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.