ralph-loop-agent AGENTS.md

Repository instructions for ralph-loop-agent, an AI application built with the Vercel AI SDK and AI Gateway. They cover package versions, model naming, source-code references, and how to fetch additional source code.

In plain words
What is it for?
Use them when adding dependencies, configuring models, working with the AI Gateway, or locating source code for the agent.
Why use it?
They prevent dependency and model-configuration mistakes, such as installing outdated packages or using provider-specific integrations where the project expects AI Gateway model strings.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/vercel-labs/ralph-loop-agent/agents-md
Clone the repo
git clone --depth 1 https://github.com/vercel-labs/ralph-loop-agent

Made for: Codex, OpenCode.

Per session 532 This file is loaded in full into every session.
When invoked 532 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00532 $0.00532
Opus 5 $0.00266 $0.00266
Sonnet 5 $0.00106 $0.00106
Haiku 4.5 $0.00053 $0.00053

Measured 3d ago against content hash 625a5747375b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralph-loop-agent 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 3d 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.

AGENTS.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Package Management

Always check the latest version before installing a package.

Before adding or updating any dependency, verify the current latest version on npm:

npm view <package-name> version

Or check multiple packages at once:

npm view ai version
npm view @ai-sdk/provider-utils version
npm view zod version

This ensures we don't install outdated versions that may have incompatible types or missing features.

AI Gateway

Use AI Gateway string format for models, not provider packages.

Do NOT install or import from provider-specific packages like @ai-sdk/openai, @ai-sdk/anthropic, etc.

Instead, use the AI Gateway string format: {provider}/{model}

// CORRECT - Use AI Gateway strings
import { streamText } from 'ai';

const result = streamText({
  model: 'anthropic/claude-opus-4.5',
  prompt: 'Why is the sky blue?',
});

// INCORRECT - Don't use provider packages
import { anthropic } from '@ai-sdk/anthropic';  // DON'T DO THIS

const result = streamText({
  model: anthropic('claude-opus-4.5'),  // DON'T DO THIS
  prompt: 'Why is the sky blue?',
});

Default model: When examples need a model, default to anthropic/claude-opus-4.5.

Note: @ai-sdk/provider-utils is fine to use for types like ModelMessage, SystemModelMessage, etc.

Source Code Reference

Source code for dependencies is available in opensrc/ for deeper understanding of implementation details.

See opensrc/sources.json for the list of available packages and their versions.

Use this source code when you need to understand how a package works internally, not just its types/interface.

Fetching Additional Source Code

To fetch source code for a package or repository you need to understand, run:

npx opensrc <package>           # npm package (e.g., npx opensrc zod)
npx opensrc pypi:<package>      # Python package (e.g., npx opensrc pypi:requests)
npx opensrc crates:<package>    # Rust crate (e.g., npx opensrc crates:serde)
npx opensrc <owner>/<repo>      # GitHub repo (e.g., npx opensrc vercel/ai)

Read the full file on GitHub · 75 lines

Changes

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.

  1. 3d ago First seen · 75 lines · 532 tokens per session scan A 625a5747375b

Subscribe to this mod's changes

ralph-loop-agent AGENTS.md is an instructions file published in the GitHub repository vercel-labs/ralph-loop-agent (828 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 532 tokens to every session, about $0.0027 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 2026-08-30.