Borrowing it
Nothing to install: this file belongs to argile-ai/claude-ralph-mode. 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/argile-ai/claude-ralph-mode/main/CLAUDE.mdgit clone --depth 1 https://github.com/argile-ai/claude-ralph-modeWrote 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/argile-ai/claude-ralph-mode/claude-md)<a href="https://agentmods.dev/instructions/argile-ai/claude-ralph-mode/claude-md"><img src="https://agentmods.dev/badge/instructions/argile-ai/claude-ralph-mode/claude-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/argile-ai/claude-ralph-mode/claude-md"><img src="https://agentmods.dev/badge/instructions/argile-ai/claude-ralph-mode/claude-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 | $0.00428 | $0.00428 |
| Opus 5 | $0.00214 | $0.00214 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
claude-ralph-mode 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 9d 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.
What it actually says
Ralph - Claude Code CLI
Overview
Ralph is an autonomous AI agent loop that runs Claude Code repeatedly until all PRD items are complete. Each iteration is a fresh Claude Code instance with clean context.
Installation
npm install -g claude-ralph
Commands
| Command | Description |
|---|---|
ralph init |
Initialize configuration in current directory |
ralph plan <feature> |
Generate a structured implementation plan |
ralph prd |
Convert plan.md into prd.json |
ralph run |
Run the autonomous execution loop |
ralph status |
Show current progress and status |
Key Files
| File | Purpose |
|---|---|
ralph.config.json |
Project configuration (repos, checks) |
plan.md |
Generated plan (from ralph plan) |
prd.json |
Executable PRD (from ralph prd) |
progress.txt |
Accumulated learnings |
Workflow
- User runs
ralph initto create configuration - User runs
ralph plan <feature>to generate a plan - User reviews/edits
plan.md - User runs
ralph prdto convert to JSON - User runs
ralph runto execute autonomously
Configuration
Edit ralph.config.json to define:
- Repository paths
- Quality checks per repository
- Max iterations
Configuration can also be stored in:
.ralphrc.ralphrc.json.ralphrc.yamlpackage.jsonunder"ralph"key
Patterns
- Each iteration spawns a fresh Claude Code instance
- Memory persists via git history,
progress.txt, andprd.json - Stories should be small enough to complete in one context window
- Backend stories should come before frontend stories
- Always update CLAUDE.md in target repos with discovered patterns
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.
- 9d ago First seen · 60 lines · 428 tokens per session scan A efcb41c1132f
claude-ralph-mode CLAUDE.md is an instructions file published in the GitHub repository argile-ai/claude-ralph-mode (11 stars, last pushed 7mo ago), licensed MIT. It adds 428 tokens to every session, about $0.0021 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.