ralph-loop-agent is an experimental framework for running AI SDK agents in repeated work-and-check cycles until a task meets its completion conditions. It is for developers who need agents to verify results, receive feedback, and continue iterating on complex tasks. The catalogue instruction supports using this continuous autonomy workflow.
Borrowing it
Nothing to install: this file belongs to vercel-labs/ralph-loop-agent. 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/vercel-labs/ralph-loop-agent/main/AGENTS.mdgit clone --depth 1 https://github.com/vercel-labs/ralph-loop-agentWrote 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/vercel-labs/ralph-loop-agent/agents-md)<a href="https://agentmods.dev/instructions/vercel-labs/ralph-loop-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/ralph-loop-agent/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/vercel-labs/ralph-loop-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/ralph-loop-agent/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 | $0.00532 | $0.00532 |
| Opus 5.5 | $0.00213 | $0.00213 |
| Sonnet 5.5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
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 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 — 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)
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 · 75 lines · 532 tokens per session scan A 625a5747375b
ralph-loop-agent AGENTS.md is an instructions file published in the GitHub repository vercel-labs/ralph-loop-agent (845 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 532 tokens to every session, about $0.0021 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 2026-08-30.
ralph-loop-agent AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ralph-loop-agent AGENTS.mdvercel-labs/ralph-loop-agent | Instructions file | 845 | 1mo ago | Apache-2.0 | A | 532 | 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 |