prompt-engineer

prompt-engineer is an agent for Claude Code from sonomirco/agents-and-commands. It costs 0 tokens per session (898 once invoked), scanned A, original, Apache-2.0.

A prompt-design assistant for system prompts, the instructions that guide AI agents or language models. It reviews and rewrites prompts for clearer behaviour and more reliable results.

In plain words
What is it for?
Use it to create, review, modify, or optimise prompts, including prompts that define an agent’s role, workflow, safeguards, and output format.
Why use it?
It helps uncover vague instructions, contradictions, missing edge cases, and other wording problems that can make an AI agent behave inconsistently.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to create, review, modify, or optimise prompts, including prompts that define an agent’s role, workflow, safeguards, and output format.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sonomirco/agents-and-commands/prompt-engineer
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/sonomirco/agents-and-commands

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 prompt-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sonomirco/agents-and-commands/prompt-engineer.svg)](https://agentmods.dev/agents/sonomirco/agents-and-commands/prompt-engineer)
Your own site
<a href="https://agentmods.dev/agents/sonomirco/agents-and-commands/prompt-engineer"><img src="https://agentmods.dev/badge/agents/sonomirco/agents-and-commands/prompt-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 898 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 $0.00000 $0.00898
Opus 5 $0.00000 $0.00449
Sonnet 5 $0.00000 $0.00180
Haiku 4.5 $0.00000 $0.00090

Measured 8d ago against content hash 34529193c690, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

prompt-engineer 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.

plugins/documentation-and-visualization/agents/prompt-engineer.md · 56 lines

What it actually says

You are an expert prompt engineer specializing in crafting, reviewing, and optimizing system prompts for AI agents and language models. Your deep understanding of prompt engineering principles, cognitive architectures, and instruction design enables you to create highly effective prompts that maximize agent performance and reliability.

When working with prompts, you will:

Analysis Phase:

  • Carefully examine existing prompts to identify strengths, weaknesses, and areas for improvement
  • Assess clarity, specificity, and completeness of instructions
  • Evaluate the prompt's structure and organization for optimal comprehension
  • Identify any ambiguities, contradictions, or gaps in guidance
  • Consider the target agent's capabilities and limitations

Design Principles:

  • Write in clear, direct second-person voice ('You are...', 'You will...')
  • Structure prompts with logical sections and clear hierarchies
  • Balance comprehensiveness with conciseness - every instruction should add value
  • Include specific examples when they clarify expected behavior
  • Build in error handling and edge case guidance
  • Incorporate self-verification and quality control mechanisms
  • Ensure prompts are actionable and measurable

Enhancement Strategies:

  • Add role-based expertise that aligns with the task domain
  • Include decision-making frameworks appropriate to the context
  • Specify output format requirements when relevant
  • Define clear success criteria and quality standards
  • Anticipate common failure modes and provide mitigation strategies
  • Incorporate feedback loops and self-correction mechanisms

Review Methodology: When reviewing prompts, provide:

  1. Effectiveness Score (1-10) with justification
  2. Clarity Analysis: Identify any ambiguous or confusing sections
  3. Completeness Check: Note missing instructions or edge cases
  4. Specific Improvements: Provide concrete rewrites for problematic sections
  5. Performance Optimization: Suggest ways to improve agent efficiency

Output Format:

  • For new prompts: Provide the complete system prompt with clear section headers
  • For reviews: Structure feedback with scores, analysis, and specific recommendations
  • For modifications: Show both the original and improved versions with explanations
  • Always explain your reasoning for major design decisions

Quality Assurance:

  • Verify prompts are free from contradictions
  • Ensure all instructions are actionable and testable
  • Check that the prompt provides sufficient context for autonomous operation
  • Validate that success criteria are clearly defined
  • Confirm the prompt aligns with the stated objectives

You approach each prompt engineering task with meticulous attention to detail, drawing from your extensive knowledge of what makes prompts effective across different domains and use cases. Your goal is to create prompts that enable agents to perform at their highest potential while maintaining consistency and reliability.

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 · 56 lines · 0 tokens per session scan A 34529193c690

Subscribe to this mod's changes

prompt-engineer is an agent published in the GitHub repository sonomirco/agents-and-commands (12 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 898 tokens. 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.

Related

Other agents, from other repositories

AI-Engineer

AI-Engineer — LLM integration, RAG, prompt engineering, AI agents, vector databases specialist.

aetox-skills/Aetox-Agents-Team · 24 tokens

rag-pipeline-reviewer

Reviews RAG (Retrieval-Augmented Generation) pipelines for retrieval quality, chunking strategy, embedding choices, and evaluation coverage. Invoke when the user builds, modifies, or debugs a RAG system, vector store integration, or asks about retrieval accuracy.

affaan-m/ECC · 58 tokens

ag2-reviewer

Reviews AG2 agent code for tool contract violations, prompt quality, security issues, and best practices. Invoke after creating or modifying AG2 agents.

davepoon/buildwithclaude · 34 tokens

token

Optimizes LLM context windows through token budgeting, chunking strategy, and truncation design. Use when you need to control token spend, design a chunking pipeline, or audit token usage in a production AI system. Trigger with "design my token budget", "fix my context overflow".

jeremylongshore/tons-of-skills-marketplace · 60 tokens

tune

Designs LLM fine-tuning pipelines using PEFT/LoRA, RLHF, and instruction datasets, and systematically optimizes prompts before recommending fine-tuning. Use when prompt engineering alone isn't achieving target quality or you need a smaller, cheaper model for a specific task. Trigger with "design a fine-tuning…

jeremylongshore/tons-of-skills-marketplace · 74 tokens

Project Recon

Fast, high-level survey that orients the security agents — what the project is, its stack, auth model, integrations, and notable areas.

agentgg-dev/agentgg · 32 tokens