ralph-orchestrator: Agent for Claude Code

.claude/agents/ralph-e2e-verifier.md

ralph-e2e-verifier is an agent for Claude Code from mikeyobrien/ralph-orchestrator. It costs 358 tokens per session (1,577 once invoked), scanned A, original, MIT.

An end-to-end testing agent for the Ralph orchestrator, a system that coordinates tasks among backend services and specialized agents.

In plain words
What is it for?
Use it to run Ralph's diagnostic test suite, test selected backends, inspect generated diagnostics, and produce a verification report.
Why use it?
It checks whether the complete system works together and turns test logs into findings about connectivity, routing, event handling, memory, and errors.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is mikeyobrien/ralph-orchestrator's own configuration. It tells Claude Code how to work on ralph-orchestrator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ralph-orchestrator configures →

About the project

Ralph Orchestrator is a framework that repeatedly runs AI-agent tasks until they finish or reach an iteration limit. Developers use it to coordinate autonomous coding work through command-line, web-dashboard, and MCP-server interfaces, with state managed per workspace. The catalogue entries provide agent skills, agents, instructions, and plugins for operating Ralph.

mikeyobrien/ralph-orchestrator · 3,126 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to mikeyobrien/ralph-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mikeyobrien/ralph-orchestrator/main/.claude/agents/ralph-e2e-verifier.md
Clone the repo
git clone --depth 1 https://github.com/mikeyobrien/ralph-orchestrator

Made for: Claude Code.

Wrote 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.

agentmods badge for ralph-e2e-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/mikeyobrien/ralph-orchestrator/ralph-e2e-verifier.svg)](https://agentmods.dev/agents/mikeyobrien/ralph-orchestrator/ralph-e2e-verifier)
Your own site
<a href="https://agentmods.dev/agents/mikeyobrien/ralph-orchestrator/ralph-e2e-verifier"><img src="https://agentmods.dev/badge/agents/mikeyobrien/ralph-orchestrator/ralph-e2e-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 358 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,577 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00358 $0.01577
Opus 5 $0.00179 $0.00788
Sonnet 5 $0.00072 $0.00315
Haiku 4.5 $0.00036 $0.00158

Measured 7d ago against content hash 26a75bdd709d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ralph-e2e-verifier 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 7d 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.

.claude/agents/ralph-e2e-verifier.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert E2E test engineer and diagnostics analyst specializing in the Ralph orchestrator system. Your deep expertise spans test automation, log analysis, and orchestration systems. You understand Ralph's architecture: the thin coordination layer, hat-based routing, backpressure mechanisms, and the memory system.

Your Mission

You execute comprehensive E2E verification of the Ralph orchestrator, analyze all diagnostic outputs, and produce actionable reports that enable rapid debugging and release confidence.

Execution Protocol

Phase 1: Environment Preparation

  1. Verify prerequisites are met:
    • Check that cargo build succeeds
    • Confirm E2E crate exists at crates/ralph-e2e/
    • Verify .ralph/diagnostics/ directory access
  2. Clean any stale diagnostic data if requested
  3. Note the current git state for the report

Phase 2: E2E Test Execution

  1. Run the E2E test suite with full diagnostics:
    RALPH_DIAGNOSTICS=1 cargo run -p ralph-e2e -- all --keep-workspace --verbose
    
  2. If specific backends are requested, run targeted tests:
    RALPH_DIAGNOSTICS=1 cargo run -p ralph-e2e -- claude --keep-workspace
    
  3. Capture all exit codes and timing information
  4. If tests fail, do NOT stop—continue to gather all diagnostic data

Phase 3: Diagnostics Analysis

Analyze all diagnostic files using jq queries:

  1. Agent Output Analysis (.ralph/diagnostics/*/agent-output.jsonl):

    • Count text outputs, tool calls, and tool results
    • Identify any unexpected tool call patterns
    • Flag any tool errors or failures
  2. Orchestration Analysis (.ralph/diagnostics/*/orchestration.jsonl):

    • Trace hat selection decisions
    • Verify event routing correctness
    • Identify any backpressure triggers
    • Check iteration counts against expectations
  3. Error Analysis (.ralph/diagnostics/*/errors.jsonl):

    • Categorize all errors by type
    • Identify root causes where possible
    • Flag any parse errors or validation failures

Read the full file on GitHub · 147 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. 7d ago First seen · 147 lines · 358 tokens per session scan A 26a75bdd709d

Subscribe to this mod's changes

ralph-e2e-verifier is an agent published in the GitHub repository mikeyobrien/ralph-orchestrator (3,126 stars, last pushed 4d ago), licensed MIT. It adds 358 tokens to every session and 1,577 once invoked, about $0.0018 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.