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 hoangatg/ai-agent-toolkit --skill prompt-engineeringgit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWrote 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/hoangatg/ai-agent-toolkit/prompt-engineering)<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/prompt-engineering"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/prompt-engineering/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/hoangatg/ai-agent-toolkit/prompt-engineering"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/prompt-engineering.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 | $0.00042 | $0.01032 |
| Opus 5 | $0.00021 | $0.00516 |
| Sonnet 5 | $0.00008 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
prompt-engineering 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 8d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Engineering
Design prompts that get reliable, high-quality results from LLMs.
1. Core Principles
| Principle | Description |
|---|---|
| Clarity | Unambiguous instructions, one interpretation |
| Specificity | Define format, length, tone, constraints |
| Context | Provide relevant background, not noise |
| Examples | Show desired output (few-shot) |
| Iteration | Test, measure, refine systematically |
2. Prompt Architecture
Anatomy of a Good Prompt
[System Role] → Who the AI is
[Context] → Background information
[Task] → What to do
[Format] → How to output
[Constraints] → What NOT to do
[Examples] → Few-shot demonstrations
System Prompt Design
| Component | Purpose |
|---|---|
| Persona | Define expertise and behavior |
| Scope | Boundaries of what to handle |
| Style | Tone, formality, verbosity |
| Rules | Hard constraints and guardrails |
3. Prompting Strategies
Strategy Selection
| Strategy | When to Use |
|---|---|
| Zero-shot | Simple, well-defined tasks |
| Few-shot | Need consistent format/style |
| Chain-of-Thought | Complex reasoning, math, logic |
| Self-Consistency | High-stakes decisions (multiple runs) |
| Tree-of-Thought | Exploration, creative problem-solving |
| ReAct | Tool use, multi-step tasks |
Chain-of-Thought Principles
- Ask model to "think step by step"
- Break complex problems into sub-problems
- Request reasoning before final answer
- Validate intermediate steps
4. Few-Shot Patterns
Design Principles
| Principle | Application |
|---|---|
| Representative examples | Cover edge cases |
| Consistent format | Same structure each example |
| Diverse difficulty | Easy → Hard progression |
| Minimal examples | 2-5 usually sufficient |
Anti-Patterns
| ❌ Don't | ✅ Do |
|---|---|
| 20+ examples (context waste) | 3-5 well-chosen examples |
| All similar examples | Diverse representative cases |
| Examples without labels | Clear input → output mapping |
| Ambiguous formatting | Explicit delimiters |
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.
- 8d ago First seen · 163 lines · 42 tokens per session scan A c91514e3cd6d
prompt-engineering is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 1,032 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
skill-meta-prompt
Craft better prompts using proven optimization techniques — use when your prompt needs refinement.
cost-aware-llm-pipeline
A planning guide for choosing language models and managing the amount of conversation context used by an AI coding workflow. It groups tasks by complexity and gives rules for avoiding context overflow during long sessions.
llm-patterns
AI-first application patterns, LLM testing, prompt management.
coding-agents-prompt-authoring
To author, adapt, review, and validate prompts (skills, agents, workflows, rules, etc.) with brief, contracts, and a validation pack.
prompt-engineering
Use when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt blocks, or the inline cases you run while tuning. NOT the agent loop, tools, or retrieval (that is building-agents), NOT a standing CI eval…
prompt-enhancer
Transform poor or overly simple prompts with expert-level framing. Use when the user explicitly asks to improve, refine, or rewrite a prompt, or wants help framing a request for another AI system. Do NOT use for authoring, reviewing, or migrating system prompts or skills targeting a specific Claude model…