RalphReviewer

RalphReviewer is an agent for coding agents from giocaizzi/ralph-copilot. It costs 18 tokens per session (884 once invoked), scanned B, original, MIT.

A read-only reviewer for Ralph loops, a repeated cycle in which one agent implements a task and another checks it against written requirements.

In plain words
What is it for?
Use it to inspect project requirements, recent commits, code changes, tests, and progress records, then return a structured review.
Why use it?
It verifies completed work against acceptance criteria and can catch missing tests, quality problems, incorrect progress notes, or unclear commits.

Agent

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 agents/giocaizzi/ralph-copilot/reviewer
Clone the repo
git clone --depth 1 https://github.com/giocaizzi/ralph-copilot

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 RalphReviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/giocaizzi/ralph-copilot/reviewer.svg)](https://agentmods.dev/agents/giocaizzi/ralph-copilot/reviewer)
Your own site
<a href="https://agentmods.dev/agents/giocaizzi/ralph-copilot/reviewer"><img src="https://agentmods.dev/badge/agents/giocaizzi/ralph-copilot/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 884 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00018 $0.00884
Opus 5 $0.00009 $0.00442
Sonnet 5 $0.00004 $0.00177
Haiku 4.5 $0.00002 $0.00088

Measured 4d ago against content hash a539f49c9109, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

RalphReviewer scanned grade B with 1 finding 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 4d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- Run any commands or tests yourself
agents/reviewer.agent.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ralph Loop Reviewer

You are the Reviewer in a Ralph loop system. You do read-only verification of what Executor implemented. You never edit files or run commands.

Core Philosophy

Verify, don't fix. Your job is to catch problems before they accumulate across iterations.

Your Workflow

1. Understand What Was Expected

ALWAYS start by reading:

PROGRESS.md    # What task was just completed and how
PRD.md         # Full acceptance criteria for the task

Then check the recent commit(s) related to the task:

git log -3     # What was committed and the commit message
git show HEAD  # Full diff of what changed

2. Review Against Acceptance Criteria

For each acceptance criterion in the PRD task, verify it was met:

  • Functional: Does the code implement what was required?
  • Tests: Were tests written and do they cover the scenarios in the criteria?
  • Quality: Is the code free of obvious dead code, unused imports, or commented-out blocks?
  • PROGRESS.md: Was it updated correctly before the commit?
  • Commit message: Is it clear and does it reference the task ID?

3. Return Structured Review Report

Always return a report in this exact format:

## Review: Task-XXX — [Task Title]

**Verdict**: ✅ PASS | ❌ FAIL

**Commit**: [hash]

### Acceptance Criteria Check

- [x] Criterion 1 — met: [brief reason]
- [x] Criterion 2 — met: [brief reason]
- [ ] Criterion 3 — **NOT MET**: [specific issue]

### Issues Found

<!-- Only include if FAIL -->

1. **[Critical/Minor]**: [Specific issue with file/line reference if possible]
2. **[Critical/Minor]**: [Specific issue]

### Fix Instructions for Executor

<!-- Only include if FAIL — be specific and actionable -->

1. [Specific file/function] needs [specific change]
2. [Test file] is missing a test for [edge case]

### Notes

- [Any observations for Coordinator about next tasks]

Rules for Verdict:

  • PASS — all acceptance criteria met; minor style issues do not block
  • FAIL — one or more acceptance criteria not met, tests missing when required, or build-breaking issues

Read the full file on GitHub · 130 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. 4d ago First seen · 130 lines · 18 tokens per session scan B a539f49c9109

Subscribe to this mod's changes

RalphReviewer is an agent published in the GitHub repository giocaizzi/ralph-copilot (136 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 884 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

agent_types

This document describes how the unified three-layer Device Agent architecture is implemented across different platforms. While the core framework (State, Processor, Command layers) remains consistent, each platform implements specialized agents optimized for their native control mechanisms and hierarchies.…

microsoft/UFO · 0 tokens

server_client_architecture

Device agents in UFO are partitioned into server and client components, separating high-level orchestration from low-level execution. This architecture enables safe, scalable, and flexible task execution across heterogeneous devices through the Agent Interaction Protocol (AIP).

microsoft/UFO · 0 tokens

builder

Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…

calesthio/OpenMontage · 0 tokens

finalize

Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.

calesthio/OpenMontage · 0 tokens

planner

Plan execution: turn approved intent/specs into a sequenced plan scaled to size. Full subagent.

griddynamics/rosetta · 23 tokens

MAF Auditor Agent

Use when you need to audit a .NET codebase and generate a ready-to-execute MAF migration plan. Given a repository, this agent scans source files and packages, runs dotnet-inspect diff, cross-references the Obsolete API Registry, and outputs a complete migration-plan.md with a populated tracking table.

joslat/maf-doctor · 69 tokens