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/appboypov/pew-pew-plaza-packsWrote 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/commands/appboypov/pew-pew-plaza-packs/prompt-best-practices)<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/prompt-best-practices"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/prompt-best-practices/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/commands/appboypov/pew-pew-plaza-packs/prompt-best-practices"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/prompt-best-practices.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 | $0.00018 | $0.01622 |
| Opus 5 | $0.00009 | $0.00811 |
| Sonnet 5 | $0.00004 | $0.00324 |
| Haiku 4.5 | $0.00002 | $0.00162 |
Grade A, and why
prompt-best-practices 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instruction Command
When this command is used, acknowledge that you understand these instructions and will follow them throughout the conversation. Then await the user's request.
🌟 Prompt Best Practices
💡 Industry standards and proven approaches for creating high-quality, maintainable prompts.
Start with End Goal
Define Success First
The End Goal is your north star - it determines whether any other section should exist. Write it as:
- Specific and measurable
- Outcome-focused, not process-focused
- Clear enough that success is unambiguous
- Concise but complete
Example End Goals
- ✅ "Generate production-ready Flutter widget tests with 100% coverage"
- ✅ "Transform user stories into technical implementation plans"
- ❌ "Help with testing" (too vague)
- ❌ "Follow the testing process" (process, not outcome)
WHEN defining End Goals
- ALWAYS make them measurable
- ALWAYS focus on the outcome
- ALWAYS keep them concise
- NEVER include process steps
- NEVER leave ambiguity
Apply Ruthless Modularity
Include Only What Contributes
Each section must pass the contribution test:
- Does this section help achieve the End Goal?
- Would the prompt fail without it?
- Does it add more value than complexity?
If any answer is "no", exclude the section.
Component Decision Framework
Persona:
- ✅ Include if: Specialized expertise improves outcome
- ❌ Exclude if: General knowledge suffices
Workflow:
- ✅ Include if: Multi-step process with dependencies
- ❌ Exclude if: Single action or simple task
Instructions:
- ✅ Include if: Specific rules prevent common failures
- ❌ Exclude if: Obvious or redundant with Request
Output Format:
- ✅ Include if: Specific structure required
- ❌ Exclude if: Standard text response works
WHEN evaluating components
- ALWAYS test against End Goal
- ALWAYS document inclusion rationale
- ALWAYS prefer exclusion when uncertain
- NEVER include components by default
- NEVER add sections "just in case"
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 · 285 lines · 18 tokens per session scan A 431262a8fcab
prompt-best-practices is a command published in the GitHub repository appboypov/pew-pew-plaza-packs (85 stars, last pushed 8mo ago), licensed MIT. It adds 18 tokens to every session and 1,622 once invoked, about $0.0001 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 commands, from other repositories
devkit.prompt-optimize
Provides expert prompt optimization using advanced techniques (CoT, few-shot, constitutional AI) for LLM performance enhancement. Use when you need to improve prompt quality or optimize LLM interactions.
cloud-sdk-ai-python-chat-template
Generate or review a Python chat template for SAP Cloud SDK for AI with environment-based configuration.
cloud-sdk-ai-chat-template
Generate or review a JavaScript or TypeScript chat template for SAP Cloud SDK for AI with safe configuration boundaries.
meta-prompt
Turn a rough request or the preceding conversation into a grounded, ready-to-run prompt for another agent. Use when the user asks to write a prompt, meta-prompt, or briefing for a separate agent session — "write a prompt for another instance", "brief another agent", "prepare a prompt I can copy-paste", "write this up…
prompt
Transform the user message into a professional, precise Cursor-ready prompt. Never execute the requested task. Output only the optimized prompt package.
prompt-eval-debug
Debug any prompt with a tiny eval suite (control, edge, boundary), failure diagnosis, and smallest next change, no blind rewrite.