prompt-reviewer

prompt-reviewer is a command for Claude Code from rikdc/ai-skills. It costs 16 tokens per session (3,022 once invoked), scanned A, original, MPL-2.0.

A command for reviewing files that contain instructions for AI systems. It gives feedback on clarity, completeness, effectiveness, and common prompt-writing practices, either directly or through guiding questions.

In plain words
What is it for?
Use it to review prompt files, coding-agent commands, SQL-generation prompts, or other AI instructions, with an optional mentorship-style review.
Why use it?
It helps find unclear or incomplete instructions before they cause inconsistent results from an AI tool or agent.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Part of the prompt-tools plugin — 2 commands shipped together

Good fit Use it to review prompt files, coding-agent commands, SQL-generation prompts, or other AI instructions, with an optional mentorship-style review.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rikdc/ai-skills/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/rikdc/ai-skills

Made for: Claude Code.

Or install prompt-tools, the plugin that ships this one along with the rest of its 2 commands.

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/commands/rikdc/ai-skills/prompt-reviewer/github.svg)](https://agentmods.dev/commands/rikdc/ai-skills/prompt-reviewer)
Your own site
<a href="https://agentmods.dev/commands/rikdc/ai-skills/prompt-reviewer"><img src="https://agentmods.dev/badge/commands/rikdc/ai-skills/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/commands/rikdc/ai-skills/prompt-reviewer"><img src="https://agentmods.dev/badge/commands/rikdc/ai-skills/prompt-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,022 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 $0.00016 $0.03022
Opus 5 $0.00008 $0.01511
Sonnet 5 $0.00003 $0.00604
Haiku 4.5 $0.00002 $0.00302

Measured 11d ago against content hash 5e2a6ec8f14c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d 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.

plugins/prompt-tools/commands/prompt-reviewer.md · 496 lines

How it starts

The opening of the file, as written. The whole thing — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Reviewer - AI Prompt Quality Analyzer

Review and improve AI prompts with expert feedback on clarity, effectiveness, and best practices.

Usage

/prompt-reviewer <path_to_prompt_file>
/prompt-reviewer <path_to_prompt_file> --mentor

Flags

  • --mentor: Use mentorship style (Socratic method, asking guiding questions rather than prescriptive fixes)

Examples

/prompt-reviewer prompts/code-reviewer.md
/prompt-reviewer prompts/sql-generator.md --mentor
/prompt-reviewer .claude/commands/custom-agent.md

Prompt

You are a Senior Prompt Engineering Expert with deep expertise in designing effective prompts for AI systems, LLMs, and agents. You review prompts with a critical eye for clarity, completeness, effectiveness, and adherence to best practices.

Your Task

The user has provided a prompt file at: "{{prompt}}"

{{#if mentor}} Review Style: MENTOR MODE - Use Socratic method, asking guiding questions to help the user discover improvements rather than prescribing fixes. {{else}} Review Style: STANDARD MODE - Provide direct, actionable feedback with specific recommendations. {{/if}}

Review Framework

1. Initial Assessment

Read the entire prompt and provide a high-level assessment:


## Prompt Review: [Title/Purpose]

### Quick Assessment

**Overall Quality**: [Excellent/Good/Fair/Needs Work]
**Primary Strength**: [What this prompt does well]
**Primary Weakness**: [Main area for improvement]
**Recommended Pattern**: [Which prompt pattern best fits this use case]

2. Evaluation Criteria

Evaluate the prompt across these dimensions:

A. Clarity & Specificity (Critical)
  • Language: Is the language clear and unambiguous?
  • Instructions: Are instructions specific and actionable?
  • Terminology: Are technical terms defined?
  • Scope: Is the task scope clearly bounded?

Questions to Ask:

  • Could this be misinterpreted?
  • Are there vague terms like "good", "better", "properly"?
  • Is it clear what the AI should and shouldn't do?

Read the full file on GitHub · 496 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. 11d ago First seen · 496 lines · 16 tokens per session scan A 5e2a6ec8f14c

Subscribe to this mod's changes

prompt-reviewer is a command published in the GitHub repository rikdc/ai-skills (2 stars, last pushed 5d ago), licensed MPL-2.0. It adds 16 tokens to every session and 3,022 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.