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.
npx skills add opencue/cuecards --skill prompt-engineergit clone --depth 1 https://github.com/opencue/cuecardsWrote 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/skills/opencue/cuecards/prompt-engineer)<a href="https://agentmods.dev/skills/opencue/cuecards/prompt-engineer"><img src="https://agentmods.dev/badge/skills/opencue/cuecards/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/skills/opencue/cuecards/prompt-engineer"><img src="https://agentmods.dev/badge/skills/opencue/cuecards/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 | $0.00054 | $0.00579 |
| Opus 5.5 | $0.00022 | $0.00232 |
| Sonnet 5.5 | $0.00011 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Engineer
Expert prompt engineering skill that transforms rough ideas into well-structured, production-ready prompts optimized for LLMs.
When to Activate
- User provides a rough prompt/idea and wants it refined
- User asks to create/design/optimize a prompt for any LLM
- User needs prompt architecture for agents, RAG, or multi-step workflows
- User asks about prompting techniques or best practices
Workflow
1. Analyze Input
Identify from user's request:
- Target model (Codex, GPT, Llama, etc.) — default: Codex
- Use case (agent system prompt, task prompt, RAG, chat, etc.)
- Domain (technical, creative, business, etc.)
- Constraints (token limits, output format, safety requirements)
2. Apply Techniques
Select appropriate techniques from references/techniques.md based on use case:
- Complex reasoning → Chain-of-Thought, Tree-of-Thoughts
- Safety-critical → Constitutional AI patterns
- Data extraction → Structured output, JSON mode
- Multi-step tasks → Prompt chaining, agent patterns
- Knowledge-heavy → RAG optimization
3. Craft the Prompt
Follow model-specific guidelines from references/model-optimization.md:
- Structure with clear sections (role, context, instructions, output format)
- Include examples where beneficial (few-shot)
- Add constraints and guardrails
- Optimize for token efficiency
4. Deliver Output
MANDATORY format — always include ALL sections:
The Prompt
Display complete prompt in a single copyable code block.
Implementation Notes
- Techniques used and rationale
- Model-specific optimizations
- Parameter recommendations (temperature, max_tokens)
- Expected behavior and output format
Testing & Evaluation
- 3-5 test cases to validate
- Edge cases and failure modes
- Optimization suggestions
Usage Guidelines
- When/how to use effectively
- Customization options
- Integration considerations
Key Principles
- Always show the complete prompt — never just describe it
- Token efficiency — concise but comprehensive
- Production-ready — reliable, safe, optimized
- Model-aware — tailor to target model's strengths
- Refer to
references/techniques.mdfor advanced technique details - Refer to
references/model-specific-optimization-guide.mdfor model-specific guidance - Refer to
references/production-patterns-and-enterprise-templates.mdfor enterprise patterns
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 30 B
- cli.js 1.3 KB runs code
- LICENSE 1.0 KB
- package.json 971 B
- README.md 4.0 KB
- references/model-specific-optimization-guide.md 2.0 KB
- references/production-patterns-and-enterprise-templates.md 2.1 KB
- references/skill_engineer_prompt_v1.5.zip 513 KB
- references/skill-engineer-prompt-v1.9.zip 570 KB
- references/techniques.md 3.0 KB
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.
- 1mo ago First seen · 76 lines · 54 tokens per session scan A 73722e30e413
prompt-engineer is a skill published in the GitHub repository opencue/cuecards (6 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 579 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
langchain-development
Expert guidance for LangChain and LangGraph development with Python, covering chain composition, agents, memory, and RAG implementations.
llm-app-development
LLM app development with RAG, prompt engineering, vector databases, and AI agents.
llm-eng-checks
Use when building or hardening an LLM feature — prompt design, RAG, eval harness, model/provider selection, guardrails, and token/cost budgeting — with omp-native tools (bash for real API round-trips, read/grep for the repo's own client, no vendor-plugin dependency, provider-agnostic). PRIME RULE — no LLM feature is…
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.