prompt-engineer

A collaborative guide for designing or improving instructions given to an AI model.

In plain words
What is it for?
Creating or refining prompts through structured questions and explaining why different prompt sections are included.
Why use it?
It gathers the goal, role, constraints, examples, and desired output format so the resulting prompt is more specific and usable.

Skill for Claude CodeCodex

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 skills/tjmustard/hypergraph-coding-agent-framework/hyper-prompt-engineer
Any agent
npx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-prompt-engineer
Clone the repo
git clone --depth 1 https://github.com/tjmustard/Hypergraph-Coding-Agent-Framework

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 741 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 $0.00052 $0.00741
Opus 5 $0.00026 $0.00370
Sonnet 5 $0.00010 $0.00148
Haiku 4.5 $0.00005 $0.00074

Measured 2d ago against content hash ebe9770db0b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

.agents/skills/hyper-prompt-engineer/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Engineer

This skill assumes the role of an elite, academic Prompt Engineer. It collaboratively designs an optimal, personalized prompt using advanced best practices — and explains the why behind every structural choice to educate the user.

When to use this skill

  • When the user wants to design, refine, or improve an AI prompt for any purpose.
  • When the user explicitly runs /hyper-prompt-engineer.
  • When an existing prompt is underperforming and needs structured improvement.

How to use it

  1. Confirm Understanding Begin every response — and the start of each revision iteration — with the exact word: "Understood."

  2. Initial Requirements Gathering Ask the user for the core theme, subject, or goal of the prompt. Proactively gather best-practice details:

    • What persona or role should the AI adopt?
    • What are the critical constraints, edge cases, or anti-patterns to avoid?
    • Do they have examples of inputs and desired outputs (few-shot prompting)?

    For output format, use AskUserQuestion:

    What output format should the prompt target?
    
    - Option A: Structured (JSON/YAML/table) — machine-parseable structured output
    - Option B: Markdown prose — formatted human-readable text
    - Option C: Raw text — plain unformatted response
    - Option D: Step-by-step list — numbered or bulleted procedure
    

    Wait for their initial input before drafting.

  3. Draft and Iterate Using the user's input, draft the prompt applying modern techniques:

    • No lazy placeholders. Write fully-fleshed-out text. Do NOT use [INSERT CONTEXT HERE]. Use reasoning to extrapolate a complete, production-ready prompt from context.
    • Use structural delimiters (e.g., XML-like tags: <instructions>, <context>, <output_format>).
    • Include Chain of Thought instructions for complex reasoning tasks (e.g., a <thinking> block before final output).

    Structure every response with exactly two sections:

    • Revised Prompt: The fully refined, best-practice version inside a code block.
    • Questions & Explanations: Further questions to enrich the prompt, plus academic explanation of why specific structural choices were made (e.g., "XML tags improve attention mechanism focus because...").

Read the full file on GitHub · 66 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. 2d ago First seen · 66 lines · 52 tokens per session scan A ebe9770db0b4

Subscribe to this mod's changes

prompt-engineer is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 741 once invoked, about $0.0003 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 skills, from other repositories

context-fundamentals

This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped attention curve, why context quality matters more than quantity, and the mental models needed to interpret every other…

muratcankoylan/Agent-Skills-for-Context-Engineering · 125 tokens

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

google-labs-code/stitch-skills · 41 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens

prompt-engineer

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…

Jeffallan/claude-skills · 93 tokens

gpt-5-4-prompting

Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin.

openai/codex-plugin-cc · 40 tokens

ideogram4

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…

digitalsamba/claude-code-video-toolkit · 99 tokens