agent-rules

agent-rules is a command for Claude Code from appboypov/pew-pew-plaza-packs. It costs 19 tokens per session (1,230 once invoked), scanned A, original, MIT.

A set of mandatory rules for creating software agents, covering their scope, metadata, file placement, links, and output instructions.

In plain words
What is it for?
Use it as a checklist when creating agents, writing delegation descriptions, adding required sections, and checking referenced files.
Why use it?
It prevents agents from being incomplete, inconsistent, or difficult for other people and tools to discover and use.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it as a checklist when creating agents, writing delegation descriptions, adding required sections, and checking referenced files.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/agent-rules"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/agent-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,230 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 $0.00019 $0.01230
Opus 5 $0.00010 $0.00615
Sonnet 5 $0.00004 $0.00246
Haiku 4.5 $0.00002 $0.00123

Measured 9d ago against content hash bff3b1838384, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-rules 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-rules.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 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 Rules

💡 Non-negotiable rules that ensure agent quality, security, and consistency.

👍 Always

WHEN creating new agents

  • ALWAYS include all required sections from @templates/agents/agent-template.md
  • ALWAYS start with single, focused purpose
  • ALWAYS include YAML frontmatter with name, description, and color
  • ALWAYS verify all wikilinks resolve to actual files
  • ALWAYS follow kebab-case naming convention
  • ALWAYS place agents in appropriate subdirectory

WHEN writing agent descriptions

  • ALWAYS include expertise statement first
  • ALWAYS use "Use when..." pattern for delegation
  • ALWAYS wrap description in double quotes
  • ALWAYS keep descriptions action-oriented
  • ALWAYS make delegation triggers specific

WHEN structuring agent content

  • ALWAYS include instruction 0 for scope analysis
  • ALWAYS use exact section headers and emojis from template
  • ALWAYS maintain section order from template
  • ALWAYS provide clear output format specification
  • ALWAYS include quality standards table

WHEN defining tool access

  • ALWAYS consider security implications
  • ALWAYS document tool requirements in Purpose section
  • ALWAYS apply principle of least privilege
  • ALWAYS justify any broad tool access
  • ALWAYS review MCP tool implications

WHEN using wikilinks

  • ALWAYS verify referenced files exist
  • ALWAYS place embedded wikilinks on separate lines
  • ALWAYS use standard wikilink format without backticks
  • ALWAYS end example wikilinks with "-wl-example"
  • ALWAYS check for circular dependencies

WHEN writing instructions

  • ALWAYS make instructions actionable and specific
  • ALWAYS use numbered format starting with 0
  • ALWAYS bold action names in instructions
  • ALWAYS include error handling guidance
  • ALWAYS provide success criteria

WHEN documenting context

  • ALWAYS include Project Files & Code section
  • ALWAYS include Documentation & External Resources section
  • ALWAYS provide relevance notes for each reference
  • ALWAYS organize references by category
  • ALWAYS verify external links are accessible

Read the full file on GitHub · 191 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 · 191 lines · 19 tokens per session scan A bff3b1838384

Subscribe to this mod's changes

agent-rules is a command published in the GitHub repository appboypov/pew-pew-plaza-packs (85 stars, last pushed 8mo ago), licensed MIT. It adds 19 tokens to every session and 1,230 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.