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.
git clone --depth 1 https://github.com/PhAlves23/prompt-engineering-skillWrote 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/rules/phalves23/prompt-engineering-skill/prompt-engineering)<a href="https://agentmods.dev/rules/phalves23/prompt-engineering-skill/prompt-engineering"><img src="https://agentmods.dev/badge/rules/phalves23/prompt-engineering-skill/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/rules/phalves23/prompt-engineering-skill/prompt-engineering"><img src="https://agentmods.dev/badge/rules/phalves23/prompt-engineering-skill/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 | $0.00037 | $0.01063 |
| Opus 5.5 | $0.00015 | $0.00425 |
| Sonnet 5.5 | $0.00007 | $0.00213 |
| Haiku 4.5 | $0.00004 | $0.00106 |
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 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 Engineering
Turn a raw draft into a production-grade prompt. Improve the prompt, don't run it — return a rewritten version + a short changelog. Only execute the task the prompt describes if the user explicitly asks.
Operating principle
- Calibrate effort to complexity. Simple prompt → lean structural rewrite. Complex prompt (reasoning, classification, generation with criteria, agentic) → full structure. Don't over-engineer.
- If the draft is already good, say so and do the minimum. Don't invent changes to justify a rewrite.
- Default target model is Claude 4.x. If the user names another (GPT/o-series, Gemini), adjust accordingly (reasoning models do NOT want "think step by step").
- Preserve every
{{variable}}from the original. Convert negative instructions into positive ones. Add motivation to non-obvious instructions.
Workflow
- Diagnose — real intent, task type, target model, audience, output format, constraints, dynamic variables, draft weaknesses.
- Select techniques — only those that add value (see decision table).
- Rewrite in the canonical structure.
- Self-review — could a colleague with no context run this without doubt? Fix what fails.
- Deliver — optimized prompt + changelog.
Canonical structure (omit sections that don't add value)
- Role/persona — one line: who the model is + domain.
- Task + objective — what to produce + success criterion (outcome-oriented).
- Context + motivation — background + why it matters.
- Data/inputs — in XML tags. Long-context (20k+ tokens): long data at the TOP, question at the END (+up to 30% quality).
- Instructions — numbered when order matters, positive, explicit scope ("apply to ALL sections, not just the first").
- Reasoning —
<thinking>block for analytical tasks; NOT for reasoning models. - Examples (few-shot) — 3–5 diverse, in
<example>tags. Strongest lever for format/tone. - Output contract — exact format (JSON schema, XML, "result only, no preamble"). Say what to do, not what to avoid.
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 · 37 tokens per session scan A 1a6da38eb0c2
prompt-engineering is a cursor rule published in the GitHub repository PhAlves23/prompt-engineering-skill (9 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 1,063 once invoked, about $0.0001 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 2026-08-31.
Other cursor rules, from other repositories
python-app
Here's how the python application is organized.
react-router
Cursor rule "react-router" from iloveitaly/llm-ide-rules, covering react router, loading mock data, how to use clientloader and loading backend data.
react
Cursor rule "react" from iloveitaly/llm-ide-rules, covering react, mock data, react hook form and styling.
python
Cursor rule "python" from iloveitaly/llm-ide-rules, covering python, package management, typing, data manipulation and date & datetime.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.