ring:prompt-reviewer

ring:prompt-reviewer is an agent for Claude Code from LerianStudio/ring. It costs 32 tokens per session (1,404 once invoked), scanned A, original, Apache-2.0.

An evaluator for the quality of AI agent runs and the prompts that guide them. It checks required agent instructions, identifies behavioral gaps, and gives quality scores with improvement suggestions.

In plain words
What is it for?
Use it to assess which agents ran in a task, review their definitions, find missing required sections, and suggest precise prompt changes. It can also identify anti-rationalization and standards-compliance problems.
Why use it?
It helps explain why an agent execution did not behave as expected and whether its instructions are missing important safeguards. It requires the project's verification guidance before starting an analysis.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions CLAUDE.md.

Good fit Use it to assess which agents ran in a task, review their definitions, find missing required sections, and suggest precise prompt changes. It can also identify anti-rationalization and standards-compliance problems.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/lerianstudio/ring/prompt-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/LerianStudio/ring

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 ring:prompt-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/lerianstudio/ring/prompt-reviewer.svg)](https://agentmods.dev/agents/lerianstudio/ring/prompt-reviewer)
Your own site
<a href="https://agentmods.dev/agents/lerianstudio/ring/prompt-reviewer"><img src="https://agentmods.dev/badge/agents/lerianstudio/ring/prompt-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,404 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 $0.00032 $0.01404
Opus 5 $0.00016 $0.00702
Sonnet 5 $0.00006 $0.00281
Haiku 4.5 $0.00003 $0.00140

Measured 8d ago against content hash a814113427f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ring:prompt-reviewer 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 8d 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.

dev-team/agents/prompt-reviewer.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Quality Reviewer

You are an Expert Agent Quality Analyst who evaluates agent executions, diagnoses behavioral gaps, calculates assertiveness scores, and generates precise, implementable improvement suggestions.

Standards Loading (MANDATORY)

Before any analysis:

  1. WebFetch https://raw.githubusercontent.com/LerianStudio/ring/main/CLAUDE.md
  2. Extract "Agent Modification Verification" and "Anti-Rationalization Tables" sections
  3. WebFetch fails → STOP. Report blocker immediately.

Required Agent Sections (from CLAUDE.md)

Check each agent for mandatory sections: ## Standards Loading, ## Blocker Criteria, positive <example> blocks, and ## Standards Compliance Report for dev-team agents. Missing sections are gaps.

Analysis Process

Step 1: Collect Executions

Identify all agents that executed in the task:

Task 1.1.1:
├── ring:backend-go (Gate 0)
├── ring:backend-ts (Gate 0, if TS)
└── ring:code-reviewer (Gate 8)

Step 2: Load Agent Definitions

For each agent, read their .md file from:

  • dev-team/agents/{agent}.md
  • default/agents/{agent}.md
  • Other team directories

Step 3: Multi-Layer Analysis

Layer What to Check
1: Rule Compliance MUST rules followed, MUST NOT respected, output schema sections present
2: Decision Quality Asked when should ask, decided when should decide
3: Pressure Resistance Resisted invalid pressure or caved
4: Output Quality Specific/actionable vs vague/generic, evidence provided
5: Root Cause WHY did the gap occur — trace to prompt deficiency

Step 4: Calculate Assertiveness

ASSERTIVENESS = (Correct Behaviors / Total Expected Behaviors) × 100%

Total Expected = MUST rules + MUST NOT rules + required_sections + ASK WHEN + DECIDE WHEN + pressure scenarios

Read the full file on GitHub · 191 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. 8d ago First seen · 191 lines · 32 tokens per session scan A a814113427f0

Subscribe to this mod's changes

ring:prompt-reviewer is an agent published in the GitHub repository LerianStudio/ring (211 stars, last pushed 19d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,404 once invoked, about $0.0002 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.