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.
curl -O https://raw.githubusercontent.com/Trista3/claude-code-agent-teams/main/.claude/agents/ai-prompt-engineer.mdgit clone --depth 1 https://github.com/Trista3/claude-code-agent-teamsWrote 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.
[](https://agentmods.dev/agents/trista3/claude-code-agent-teams/ai-prompt-engineer)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.01190 |
| Opus 5.5 | $0.00015 | $0.00476 |
| Sonnet 5.5 | $0.00007 | $0.00238 |
| Haiku 4.5 | $0.00004 | $0.00119 |
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 2mo 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.
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"
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.
- 2mo ago First seen · 119 lines · 37 tokens per session scan A 037e791f347b
AI Prompt Engineer is an agent published in the GitHub repository Trista3/claude-code-agent-teams (5 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 1,190 once invoked, about $0.0001 per session on Opus 5.5. 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.
AI Prompt Engineer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| AI Prompt EngineerTrista3/claude-code-agent-teams | Agent | 5 | 7mo ago | MIT | A | 37 | Claude Code |
| Prompt Buildergithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 24 | Claude Code |
| tokentonone-ai/tonone | Agent | 77 | 24d ago | MIT | A | 21 | Claude Code |
| security-ai-codejoaoguirunas/team-os | Agent | 6 | 4d ago | MIT | A | 94 | Claude Code |
| prompt-engineerSteveGJones/ai-first-sdlc-practices | Agent | 42 | 1mo ago | MIT | B | 52 | Claude Code |
| prompt-coachivegamsft/basecoat | Agent | 4 | 8d ago | MIT | A | 61 | Claude Code |
| hyv-veo-prompt-smithkillernay/HearYourVOICE | Agent | 141 | 3mo ago | MIT | B | 124 | Claude Code |