prompt-engineer

prompt-engineer is an agent for Claude Code from khanh-vu/claude-force. It costs 0 tokens per session (3,612 once invoked), scanned A, original, MIT.

An agent for writing, improving, and testing instructions given to large language models, the systems behind tools such as chat assistants. It covers prompt structure, examples, output formats, and different ways to guide model responses.

In plain words
What is it for?
Use it to design system and user prompts, add examples, guide tool use, compare prompting approaches, and evaluate response quality across models.
Why use it?
It helps when model answers are inconsistent, incomplete, or in the wrong format, by making the instructions clearer and testing how well they work.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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.

agentmods
npx agentmods add agents/khanh-vu/claude-force/prompt-engineer
Clone the repo
git clone --depth 1 https://github.com/khanh-vu/claude-force

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/khanh-vu/claude-force/prompt-engineer.svg)](https://agentmods.dev/agents/khanh-vu/claude-force/prompt-engineer)
Your own site
<a href="https://agentmods.dev/agents/khanh-vu/claude-force/prompt-engineer"><img src="https://agentmods.dev/badge/agents/khanh-vu/claude-force/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 3,612 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.03612
Opus 5 $0.00000 $0.01806
Sonnet 5 $0.00000 $0.00722
Haiku 4.5 $0.00000 $0.00361

Measured 6d ago against content hash 8508945ae96b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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/prompt-engineer.md · 532 lines

How it starts

The opening of the file, as written. The whole thing — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Engineering Expert Agent

Role

Prompt Engineering Expert - specialized in designing, optimizing, and testing prompts for Large Language Models to maximize output quality, consistency, and reliability.

Domain Expertise

  • Prompt Design & Optimization
  • Chain-of-Thought (CoT) Prompting
  • Few-Shot & Zero-Shot Learning
  • System Prompt Engineering
  • Function Calling & Tool Use
  • Prompt Evaluation & Testing
  • Multi-Model Prompt Strategies

Skills & Specializations

Core Prompt Engineering

Prompt Design Patterns
  • Zero-Shot Prompting: Clear instructions without examples
  • Few-Shot Prompting: Learning from examples, in-context learning
  • Chain-of-Thought (CoT): Step-by-step reasoning, think-aloud
  • Tree of Thoughts: Multiple reasoning paths, backtracking
  • ReAct (Reasoning + Acting): Thought-action-observation loops
  • Self-Consistency: Multiple reasoning paths, voting
  • Least-to-Most: Breaking complex problems into sub-problems
Prompt Structure
  • System Prompts: Role definition, context, constraints, output format
  • User Prompts: Task description, input data, examples
  • Assistant Prefills: Guiding response format, JSON structure
  • Multi-Turn Conversations: Context management, memory
  • Structured Outputs: JSON mode, function calling, constrained generation

LLM-Specific Techniques

Claude (Anthropic)
  • Extended Context: Working with 200K+ token windows
  • XML Tags: Using for structure and clarity
  • Function Calling: Tools, tool_choice, structured outputs
  • Thinking Blocks: Internal reasoning with
  • Constitutional AI: Harmlessness, helpfulness, honesty
  • Prompt Caching: Reducing cost for repeated context
OpenAI (GPT-4, GPT-3.5)
  • System Messages: Role and behavior definition
  • Function Calling: JSON schemas, parameters, required fields
  • JSON Mode: Guaranteed JSON output
  • Temperature Control: Creativity vs. consistency
  • Top-P (Nucleus) Sampling: Response diversity
  • Seed Parameter: Deterministic outputs

Read the full file on GitHub · 532 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. 6d ago First seen · 532 lines · 0 tokens per session scan A 8508945ae96b

Subscribe to this mod's changes

prompt-engineer is an agent published in the GitHub repository khanh-vu/claude-force (5 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,612 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 2026-08-31.

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

prompting

Agent "prompting" from bestdeejay-design/awesome-ai-handbook, covering prompting for ai agents, 1. how agent prompting differs, 2. system prompt structure, role and tools.

bestdeejay-design/awesome-ai-handbook · 0 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

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