Borrowing it
Nothing to install: this file belongs to alfonsograziano/auto-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alfonsograziano/auto-agent/master/.claude/skills/prompt-engineering/SKILL.mdgit clone --depth 1 https://github.com/alfonsograziano/auto-agentWrote 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/alfonsograziano/auto-agent/prompt-engineering)<a href="https://agentmods.dev/skills/alfonsograziano/auto-agent/prompt-engineering"><img src="https://agentmods.dev/badge/skills/alfonsograziano/auto-agent/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/alfonsograziano/auto-agent/prompt-engineering"><img src="https://agentmods.dev/badge/skills/alfonsograziano/auto-agent/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 | $0.00109 | $0.01284 |
| Opus 5 | $0.00055 | $0.00642 |
| Sonnet 5 | $0.00022 | $0.00257 |
| Haiku 4.5 | $0.00011 | $0.00128 |
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 9d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Engineering
Reference for writing and reviewing LLM system prompts. Based on Harada et al. (2024) — Curse of Instructions, EARS syntax, and ARQ pattern.
1. Minimize the Rule Count (Curse of Instructions)
The probability of the model following all rules simultaneously is approximately P = p^N, where N is the number of independently verifiable instructions and p is the per-rule adherence rate.
| N rules | p = 0.95 | p = 0.90 |
|---|---|---|
| 5 | 77% | 59% |
| 10 | 60% | 35% |
| 20 | 36% | 12% |
| 30 | 21% | 4% |
Target: 10 or fewer distinct rules in the system prompt.
The math is unforgiving — every additional rule multiplicatively reduces the chance the model follows all of them. This is why minimizing rule count matters more than perfecting any single rule.
- Move procedural/structural rules (e.g., parameter formatting, count constraints) into tool descriptions, not the system prompt.
- Merge rules that protect the same invariant into one EARS statement.
- Delete rules already enforced by the tool schema or the agent framework.
2. Write Rules in EARS Syntax
Easy Approach to Requirements Syntax produces unambiguous, testable rules. Free-form instructions invite misinterpretation because the model has to guess the scope and trigger condition. EARS removes that ambiguity.
Four forms:
| Form | Template | Use when |
|---|---|---|
| Ubiquitous | The system shall [action]. | Rule always applies |
| Event-driven | When [trigger], the system shall [action]. | Rule fires on a condition |
| State-driven | While [condition], the system shall [action]. | Rule applies during a state |
| Unwanted behavior | If [situation], the system shall [response]. | Error / boundary case |
Before (free-form): "NEVER output a URL that contains {product_name} as a literal string. Always make sure the product name is properly substituted before including any link."
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.
- 9d ago First seen · 94 lines · 109 tokens per session scan A 85e5f4aee34d
prompt-engineering is a skill published in the GitHub repository alfonsograziano/auto-agent (56 stars, last pushed 5mo ago), licensed MIT. It adds 109 tokens to every session and 1,284 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
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.
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…
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.
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…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
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…