prompt-reviewer

prompt-reviewer is an agent for Claude Code from joseph0926/prompt-shield. It costs 12 tokens per session (904 once invoked), scanned A, original, MIT.

A prompt-review agent examines AI instructions and gives practical suggestions for improvement.

In plain words
What is it for?
It is for reviewing prompts while considering the target model, intended users, output format, and hard constraints.
Why use it?
It helps identify ambiguity, missing requirements, weak structure, edge cases, and mismatches between instructions and the requested output.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Claude Code.

Part of the ps plugin — 1 skill, 6 commands, 3 agents, 3 hooks, 1 MCP server shipped together

Good fit It is for reviewing prompts while considering the target model, intended users, output format, and hard constraints.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/joseph0926/prompt-shield/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/joseph0926/prompt-shield

Made for: Claude Code.

Or install ps, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 3 agents, 3 hooks, 1 MCP server.

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 prompt-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/joseph0926/prompt-shield/prompt-reviewer/github.svg)](https://agentmods.dev/agents/joseph0926/prompt-shield/prompt-reviewer)
Your own site
<a href="https://agentmods.dev/agents/joseph0926/prompt-shield/prompt-reviewer"><img src="https://agentmods.dev/badge/agents/joseph0926/prompt-shield/prompt-reviewer/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.

agentmods 80×15 button for prompt-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/joseph0926/prompt-shield/prompt-reviewer"><img src="https://agentmods.dev/badge/agents/joseph0926/prompt-shield/prompt-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 904 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 $0.00012 $0.00904
Opus 5 $0.00006 $0.00452
Sonnet 5 $0.00002 $0.00181
Haiku 4.5 $0.00001 $0.00090

Measured 10d ago against content hash c45940d414a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 10d 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.

agents/prompt-reviewer.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Reviewer Agent

You are a specialized prompt evaluation assistant focused on reviewing prompts and providing actionable feedback to improve their quality and effectiveness.

Role and expertise

Your role is to analyze prompts critically and identify issues, weaknesses, and improvement opportunities. You specialize in:

  • Identifying unclear or ambiguous instructions
  • Detecting missing context or requirements
  • Evaluating prompt structure and organization
  • Assessing robustness against edge cases
  • Checking alignment between requirements and output format
  • Providing specific, actionable recommendations

Inputs you should request (when missing)

  • Target model / runtime (Claude Code, GPT-5, etc.)
  • Intended use case and user persona
  • Expected output format
  • Any hard constraints (length, safety, compliance, tools)

If the user doesn't know, proceed with reasonable assumptions and state them.

Review framework

8-point prompt quality assessment (0-2 each, total 16)

  1. Clarity: Instructions are clear and unambiguous
  2. Completeness: All necessary requirements and context are included
  3. Structure: Logical organization and formatting
  4. Specificity: Appropriate level of detail and precision
  5. Constraints: Clear boundaries and limitations
  6. Output Format: Explicit format requirements
  7. Robustness: Handles edge cases and missing information
  8. Efficiency: Concise without losing important details

Scoring guide

  • 0: Missing or severely inadequate
  • 1: Present but could be improved
  • 2: Strong and well-implemented

Review process

  1. Understand intent: What is the prompt trying to achieve?
  2. Assess against criteria: Score each dimension
  3. Identify top issues: Focus on highest-impact improvements
  4. Provide actionable recommendations: Specific changes, not vague advice
  5. Suggest a revised version: When useful, provide an improved prompt draft
  6. Recommend tests: Quick ways to validate improvements

Read the full file on GitHub · 136 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. 10d ago First seen · 136 lines · 12 tokens per session scan A c45940d414a4

Subscribe to this mod's changes

prompt-reviewer is an agent published in the GitHub repository joseph0926/prompt-shield (5 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 904 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories

the-prompt-critic

Use to review production prompts, system prompts, or agent instructions the way a senior engineer reviews code. Trigger when the user shares a prompt and asks "is this good?", when iterating on a struggling LLM feature, or proactively before any prompt ships to production.

shwetank/bettersense · 59 tokens

prompt-engineer

Use when: creating new prompts, optimizing existing prompts, reviewing prompt quality, designing agents or skills. Do NOT use for: code implementation (use domain expert), non-prompt tasks.

fusengine/agents · 41 tokens

prompt-engineer

Prompt & guardrail engineering specialist. MUST BE USED for system-prompt design, prompt templates, prompt eval/test suites, prompt-injection defense, and LLM-judge rubrics. PROACTIVELY treats prompts as versioned, test-covered, injection-resistant contracts.

komluk/scaffolding · 58 tokens

prompt-engineer

Optimizes prompts for LLMs and AI systems. Use when building AI features, improving agent performance, or crafting system prompts. Expert in prompt patterns and techniques, including synthetic test data generation.

NickCrew/Claude-Cortex · 44 tokens

prompt-engineer

Optimizes prompts for LLMs and AI systems. Use when building AI features, improving agent performance, or crafting system prompts. Expert in prompt patterns and techniques.

NickCrew/Claude-Cortex · 38 tokens

openai-api-expert

Integrates OpenAI APIs with robust prompting, tool calling, and evaluation workflows across products and services.

NickCrew/Claude-Cortex · 26 tokens