agent-best-practices

agent-best-practices is a command for Claude Code from appboypov/pew-pew-plaza-packs. It costs 20 tokens per session (1,288 once invoked), scanned A, original, MIT.

A set of guidelines for designing reusable software agents, with each agent focused on one clear responsibility.

In plain words
What is it for?
Planning agent roles, prompts, boundaries, dependencies, and reusable architecture for coding-agent workflows.
Why use it?
It helps keep agents understandable, independent, and useful across different projects.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Good fit Planning agent roles, prompts, boundaries, dependencies, and reusable architecture for coding-agent workflows.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/appboypov/pew-pew-plaza-packs/agent-best-practices
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.

Clone the repo
git clone --depth 1 https://github.com/appboypov/pew-pew-plaza-packs

Made for: Claude Code.

Wrote 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.

agentmods badge for agent-best-practices

README.md
[![agentmods](https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/agent-best-practices/github.svg)](https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/agent-best-practices)
Your own site
<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/agent-best-practices"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/agent-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.

agentmods 80×15 button for agent-best-practices

Your own site · 80×15
<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/agent-best-practices"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/agent-best-practices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,288 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00020 $0.01288
Opus 5 $0.00010 $0.00644
Sonnet 5 $0.00004 $0.00258
Haiku 4.5 $0.00002 $0.00129

Measured 9d ago against content hash 3c96e136ea3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-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.

.claude/commands/apply/agent-best-practices.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 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.


⭐ Agent Best Practices

💡 Proven approaches and techniques for creating high-quality agents.

Design Principles

WHEN designing agent architecture

Single Responsibility Principle:

  • Focus each agent on one clear, well-defined purpose
  • Resist the temptation to combine multiple functions
  • Create separate agents rather than multi-purpose ones
  • Ensure the agent name reflects its single purpose

Autonomy Within Scope:

  • Design agents to operate independently within their domain
  • Provide all necessary context and instructions
  • Minimize dependencies on external clarification
  • Enable decision-making within defined boundaries

Reusability Focus:

  • Create agents that work across different projects
  • Avoid project-specific hardcoding
  • Use wikilinks for configuration and templates
  • Design for composition with other agents

Prompt Engineering

WHEN writing agent system prompts

Clarity and Specificity:

  • Be explicit about requirements and constraints
  • Use concrete examples to illustrate concepts
  • Define technical terms and acronyms
  • Avoid ambiguous language

Structured Thinking:

  • Use XML tags for complex input processing
  • Apply chain-of-thought reasoning for complex tasks
  • Break down multi-step processes clearly
  • Include decision trees for branching logic

Positive Framing:

  • Frame instructions as "what to do" rather than "what not to do"
  • Use ALWAYS for required actions before NEVER for prohibitions
  • Focus on desired outcomes and behaviors
  • Reserve NEVER rules for critical prohibitions only

Progressive Disclosure:

  • Start with high-level purpose and role
  • Add detail progressively through sections
  • Use subsections for complex topics
  • Maintain logical flow from general to specific

Component Composition

WHEN combining agents with other components

WikiLink Strategy:

  • Reference existing workflows with [[workflow-name]]
  • Embed reusable instructions with ![[instruction-name-wl-example]]
  • Link to templates for output formats
  • Connect to related agents for orchestration

Read the full file on GitHub · 230 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. 9d ago First seen · 230 lines · 20 tokens per session scan A 3c96e136ea3b

Subscribe to this mod's changes

agent-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 20 tokens to every session and 1,288 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.