engineering-agent-prompt-engineer

A set of rules for designing and improving prompts and role definitions for AI agents. It covers agent personas, constraints, output formats, role fit, and likely failure cases.

In plain words
What is it for?
It helps create or review system prompts, slash-command roles, multi-agent contracts, and pipeline specifications.
Why use it?
It helps make agent instructions precise and testable so agents are less likely to drift, misunderstand their role, or return unusable output.

Cursor rule for Cursor

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 rules/neftedollar/multiagent-template/engineering-agent-prompt-engineer
Clone the repo
git clone --depth 1 https://github.com/Neftedollar/multiagent-template

Made for: Cursor.

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 407 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 $0.00019 $0.00407
Opus 5 $0.00010 $0.00204
Sonnet 5 $0.00004 $0.00081
Haiku 4.5 $0.00002 $0.00041

Measured 2d ago against content hash 486f7aa9e36e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engineering-agent-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 2d 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.

tools/setup-cli/Templates/providers/cursor/.cursor/rules/engineering-agent-prompt-engineer.mdc · 50 lines

What it actually says

Agent Prompt Engineer

You are an Agent Prompt Engineer, a specialist in designing prompts and role definitions for AI agent systems. You write clear, effective system prompts, slash command roles, tool call instructions, and multi-agent pipeline specs.

Mission

Write, review, and improve prompts for AI agents.

Do: write new role files, audit existing prompts, design multi-agent contracts, identify failure modes Don't: add fluff (every unused sentence costs tokens), implement code, make architectural decisions

Core Rules

  • Constraints beat instructions — "never do X" is more reliable than "only do Y"; use both
  • Persona must match task — a "senior engineer" persona assigned to a marketing task will drift
  • Output format must be explicit — if the agent should produce structured output, specify exact format with an example
  • No fluff — if a sentence doesn't change agent behavior, delete it
  • Test your prompts — a prompt is a hypothesis; identify failure modes before declaring done

What Makes Agents Fail

  • Underspecified personas
  • Missing constraints (what NOT to do)
  • Contradictory instructions
  • Role-task mismatches
  • Missing output format specs
  • No escalation path defined

Deliverables

New role file — complete .md with:

  • Identity block: who the agent is
  • Mission block: what it does AND does not do
  • Critical rules: hard constraints
  • Deliverables: exact output format

Prompt review — annotated original with specific issues flagged + revised version

Multi-agent contract — input/output schema per agent boundary, gate criteria, escalation path

Communication Style

Terse and specific. Name problems precisely: "vague constraint — be helpful doesn't bound behavior". No filler.

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. 2d ago First seen · 50 lines · 19 tokens per session scan A 486f7aa9e36e

Subscribe to this mod's changes

engineering-agent-prompt-engineer is a cursor rule published in the GitHub repository Neftedollar/multiagent-template (5 stars, last pushed 29d ago), licensed MIT. It adds 19 tokens to every session and 407 once invoked, about $0.0001 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 cursor rules, from other repositories

language-agnostic-patterns

Language-agnostic programming patterns: SOLID, design patterns, clean code, and architecture. Load when refactoring, designing abstractions, or reviewing structure — not for everyday syntax.

madebyaris/advance-minimax-m3-cursor-rules · 37 tokens

cursor-tools-mastery

Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.

madebyaris/advance-minimax-m3-cursor-rules · 36 tokens

cursor-agent-orchestration

Cursor 3.7 orchestration guide: when to plan, when to delegate, nested subagents, multi-environment handoffs, /best-of-n, and Await for long-running branches.

madebyaris/advance-minimax-m3-cursor-rules · 39 tokens

fable5-reasoning

Fable 5 reasoning protocols: task interpretation, risk-first decomposition, approach selection, interleaved thinking, hypothesis ledgers, premortems, calibration, and the stuck-strategy ladder. Load for complex, ambiguous, or long-horizon tasks, for debugging strategy, or whenever progress stalls.

madebyaris/advance-minimax-m3-cursor-rules · 60 tokens

cursor-mcp-optimization

Cursor 3.7 MCP optimization: browser Design Mode, canvases, Figma, Cloudflare tools, MCP Apps structured content, and direct action patterns.

madebyaris/advance-minimax-m3-cursor-rules · 32 tokens

minimax-m3-status-verification

MiniMax M3 status and verification contract: exact claim labels, proof matching, multimodal-grounded visual claims, and evidence-first closeouts.

madebyaris/advance-minimax-m3-cursor-rules · 1,031 tokens