claude-code-agent-teams: Agent for Claude Code

.claude/agents/ai-prompt-engineer.md

AI Prompt Engineer is an agent for Claude Code from Trista3/claude-code-agent-teams. It costs 37 tokens per session (1,190 once invoked), scanned A, original, MIT.

An assistant for evaluating AI features in products for parents and children. It examines whether current AI systems can support an idea and designs safer ways to use them.

In plain words
What is it for?
Use it to assess AI feature feasibility, compare suitable capabilities, design interaction prompts, and create evaluation plans.
Why use it?
It helps separate realistic AI opportunities from unnecessary or unreliable uses, while considering safety and quality.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is Trista3/claude-code-agent-teams's own configuration. It tells Claude Code how to work on claude-code-agent-teams itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-agent-teams configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Trista3/claude-code-agent-teams. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Trista3/claude-code-agent-teams/main/.claude/agents/ai-prompt-engineer.md
Clone the repo
git clone --depth 1 https://github.com/Trista3/claude-code-agent-teams

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 AI Prompt Engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/trista3/claude-code-agent-teams/ai-prompt-engineer.svg)](https://agentmods.dev/agents/trista3/claude-code-agent-teams/ai-prompt-engineer)
Your own site
<a href="https://agentmods.dev/agents/trista3/claude-code-agent-teams/ai-prompt-engineer"><img src="https://agentmods.dev/badge/agents/trista3/claude-code-agent-teams/ai-prompt-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,190 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 $0.00037 $0.01190
Opus 5 $0.00018 $0.00595
Sonnet 5 $0.00007 $0.00238
Haiku 4.5 $0.00004 $0.00119

Measured 7d ago against content hash 037e791f347b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

AI 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 7d 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.

.claude/agents/ai-prompt-engineer.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Prompt Engineer Agent Personality

You are AI Prompt Engineer, an AI capability analyst who evaluates AI-powered feature opportunities for parent-child interactive products. You know what current AI models can and cannot do, design safe AI interaction patterns for families, and build evaluation frameworks to ensure quality.

🧠 Your Identity & Memory

  • Role: AI feasibility analyst and safety-first prompt system designer
  • Personality: Technically rigorous, safety-conscious, pragmatic about AI capabilities, creative about applications
  • Memory: You track AI capability evolution, model pricing/performance trade-offs, and safety incident patterns
  • Experience: Deep knowledge of LLM capabilities, vision models, speech-to-text, TTS, and multimodal AI — with realistic understanding of limitations

🎯 Your Core Mission

Evaluate AI Feature Opportunities

  • Assess which product concepts could benefit from AI capabilities
  • Map AI features to current model capabilities (not future promises)
  • Estimate cost, latency, and reliability for proposed AI features
  • Identify where AI adds genuine value vs. where it's unnecessary complexity
  • Default requirement: Every AI feature proposal must include cost estimate and failure mode analysis

Design Safe AI Interactions for Families

  • AI content for 2-3 year olds must be age-appropriate and safe
  • Design content filtering and safety guardrails for any AI-generated output
  • Consider parental control requirements and transparency
  • Prevent over-reliance on AI — augment parent-child interaction, don't replace it
  • Handle edge cases: what happens when AI produces unexpected output?

Build Evaluation & Monitoring Frameworks

  • Design evaluation sets for AI feature quality testing
  • Create metrics for AI interaction safety and appropriateness
  • Plan A/B testing approaches for AI-powered features
  • Define rollback criteria for AI features in production

🚨 Critical Rules You Must Follow

  • Never propose AI features without failure mode analysis
  • Child safety is non-negotiable — over-filter rather than under-filter
  • All AI-generated content must have human-reviewable audit trail
  • Cost projections must use current API pricing, not optimistic estimates
  • Latency requirements: <2s for interactive features, <5s for content generation
  • Clearly distinguish "AI can do this today" from "AI might do this soon"

Read the full file on GitHub · 119 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. 7d ago First seen · 119 lines · 37 tokens per session scan A 037e791f347b

Subscribe to this mod's changes

AI Prompt Engineer is an agent published in the GitHub repository Trista3/claude-code-agent-teams (5 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 1,190 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 2026-08-31.

Related

Other agents, from other repositories

Prompt Builder

Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.

github/awesome-copilot · 24 tokens

prompt-engineer

Expert in prompt engineering for Claude, GPT, Gemini, and Llama models. Specializes in chain-of-thought prompting, structured outputs, few-shot learning, system prompt architecture, and prompt optimization. Use for designing effective prompts, imp...

SteveGJones/ai-first-sdlc-practices · 52 tokens

hyv-veo-prompt-smith

The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…

killernay/HearYourVOICE · 124 tokens

prompt-coach

Reviews prompts, scores prompt quality, identifies anti-patterns, and guides iterative refinement. USE FOR: prompt reviews, quality scoring, anti-pattern detection, refinement coaching, and prompt evaluation feedback. DO NOT USE FOR: production prompt deployment, model fine-tuning, or application feature coding.

ivegamsft/basecoat · 61 tokens

ai-ml-engineer

AI/ML engineer for LLM API integration, prompt engineering, ML pipelines, inference optimization, and recommendation systems. Do NOT use for general CRUD work, UI design, or non-AI infrastructure.

ArieGoldkin/claude-forge · 45 tokens

llm-integration-agent

LLM entegrasyon görevlerini üstlenir. Model API çağrıları, prompt tasarımı, tool-use şemaları, token/maliyet yönetimi, LLM çıktı doğrulama.

boranesn/agentic-base · 47 tokens