mcp-skillset: Agent for Claude Code

.claude/agents/prompt-engineer.md

prompt-engineer is an agent for Claude Code from bobmatnyc/mcp-skillset. It costs 143 tokens per session (5,712 once invoked), scanned A, a copy of engineer, MIT.

A prompt-engineering agent for improving instructions given to AI models, especially Claude 4.5.

In plain words
What is it for?
Use it to select models, refine prompts, design tool workflows, structure outputs, manage context, and reduce common prompt problems.
Why use it?
It helps make prompts clearer and more efficient while choosing how much reasoning, context, and tool use a task needs.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is bobmatnyc/mcp-skillset's own configuration. It tells Claude Code how to work on mcp-skillset 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 mcp-skillset configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bobmatnyc/mcp-skillset. 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/bobmatnyc/mcp-skillset/main/.claude/agents/prompt-engineer.md
Clone the repo
git clone --depth 1 https://github.com/bobmatnyc/mcp-skillset

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/bobmatnyc/mcp-skillset/prompt-engineer/github.svg)](https://agentmods.dev/agents/bobmatnyc/mcp-skillset/prompt-engineer)
Your own site
<a href="https://agentmods.dev/agents/bobmatnyc/mcp-skillset/prompt-engineer"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-skillset/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.

agentmods 80×15 button for prompt-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/bobmatnyc/mcp-skillset/prompt-engineer"><img src="https://agentmods.dev/badge/agents/bobmatnyc/mcp-skillset/prompt-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,712 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 86% copy Near-identical to another mod 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 $0.00143 $0.05712
Opus 5 $0.00072 $0.02856
Sonnet 5 $0.00029 $0.01142
Haiku 4.5 $0.00014 $0.00571

Measured 10d ago against content hash 243ba4554873, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

Origin

This is a copy

86% identical to engineer — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/prompt-engineer.md · 745 lines

How it starts

The opening of the file, as written. The whole thing — 745 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{'base_instructions': 'See BASE_PROMPT_ENGINEER.md for comprehensive Claude 4.5 best practices', 'base_precedence': 'BASE_PROMPT_ENGINEER.md contains the complete knowledge base and overrides all instruction fields below', 'primary_role': 'Expert prompt engineer specializing in Claude 4.5 optimization and meta-level instruction refactoring', 'core_focus': ['Apply model selection decision matrix (Sonnet for coding/analysis, Opus for strategic planning)', 'Configure extended thinking strategically (16k-64k budgets, cache-aware design)', 'Design tool orchestration patterns (parallel execution, error handling)', 'Enforce structured output methods (tool-based schemas preferred)', 'Optimize context management (caching 90% savings, sliding windows, progressive summarization)', 'Detect and eliminate anti-patterns (over-specification, cache invalidation, generic prompts)', 'Refactor instructions to demonstrate Claude 4 best practices: high-level guidance over prescriptive steps'], 'unique_capability': 'Meta-level analysis - analyze and optimize system prompts, agent templates, and instruction documents for Claude 4.5 alignment, token efficiency, and cost/performance optimization', 'delegation_patterns': ['Research agent: For codebase pattern analysis and benchmark data collection', 'Engineer agent: For implementation of optimized prompt templates', 'Use extended thinking for deep instruction analysis and refactoring strategy']}


Base Engineer Instructions

Appended to all engineering agents (frontend, backend, mobile, data, specialized).

Engineering Core Principles

Code Reduction First

  • Target: Zero net new lines per feature when possible
  • Search for existing solutions before implementing
  • Consolidate duplicate code aggressively
  • Delete more than you add

Search-Before-Implement Protocol

  1. Use MCP Vector Search (if available):
    • mcp__mcp-vector-search__search_code - Find existing implementations
    • mcp__mcp-vector-search__search_similar - Find reusable patterns
    • mcp__mcp-vector-search__search_context - Understand domain patterns

Read the full file on GitHub · 745 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. 10d ago First seen · 745 lines · 143 tokens per session scan A 243ba4554873

Subscribe to this mod's changes

prompt-engineer is an agent published in the GitHub repository bobmatnyc/mcp-skillset (20 stars, last pushed 6mo ago), licensed MIT. It adds 143 tokens to every session and 5,712 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to engineer, differing in 11 lines, and is treated as a copy.

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

graph-reviewer

Validates knowledge graphs for correctness, completeness, and quality. Runs systematic checks and renders approval or rejection decisions.

Egonex-AI/Understand-Anything · 26 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-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

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

ai-product-designer

The AI Product Designer designs LLM-, agent-, and ML-powered features inside the app: prompt UX, guardrails, latency UX (streaming, skeletons, cancellation), error recovery, and evaluation framing. Use this agent when an app feature uses an LLM or agent under the hood — chat, generation, summarization, semantic…

cenconq25/claude-code-app-studio · 92 tokens