agent-conventions

agent-conventions is a command for Claude Code from appboypov/pew-pew-plaza-packs. It costs 19 tokens per session (6,107 once invoked), scanned A, original, MIT.

A set of naming and file-structure rules for creating software agents that fit consistently into a larger framework.

In plain words
What is it for?
Use it when naming agent files, writing their descriptions, defining required metadata, and organizing agent folders.
Why use it?
It reduces confusion caused by inconsistent names, missing metadata, and agents placed in the wrong locations.

Command for Claude Code

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

Good fit Use it when naming agent files, writing their descriptions, defining required metadata, and organizing agent folders.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/agent-conventions"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/agent-conventions.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 6,107 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 $0.06107
Opus 5 $0.00010 $0.03053
Sonnet 5 $0.00004 $0.01221
Haiku 4.5 $0.00002 $0.00611

Measured 9d ago against content hash 0f4c9f76b315, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-conventions 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/apply/agent-conventions.md · 679 lines

How it starts

The opening of the file, as written. The whole thing — 679 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 Conventions

💡 Established patterns and standards for creating consistent, discoverable agents.

Naming Conventions

WHEN naming agent files

Patterns:

  • Use kebab-case exclusively: flutter-developer.md, code-reviewer.md
  • Be descriptive and specific: meta-prompt-engineer.md not prompt-helper.md
  • Include domain prefix when appropriate: meta-, flutter-, maestro-
  • Match the purpose clearly: name should indicate what the agent does

Rules:

  • ALWAYS use lowercase letters and hyphens only
  • ALWAYS make names self-documenting
  • NEVER use underscores, spaces, or special characters
  • NEVER use generic names like helper.md or assistant.md

Frontmatter Structure

WHEN creating agent frontmatter

Required Fields:

---
name: agent-name-here
description: "Expert description. Use when specific conditions."
color: ColorName
---

Conventions:

  • ALWAYS include all three fields: name, description, color
  • ALWAYS wrap description in double quotes
  • ALWAYS use action-oriented descriptions starting with expertise
  • ALWAYS include "Use when..." pattern in description
  • NEVER omit any required field
  • NEVER use single quotes for description

Color Selection Guidelines:

  • Choose colors that haven't been used by related agents
  • Consider the domain: Blue for meta, Green for dev, Purple for review
  • Maintain visual distinction in Claude Code interface

Directory Organization

WHEN organizing agents in the filesystem

Structure Pattern:

agents/
├── meta/         # Meta-level agents for framework tasks
├── dev/          # Development and coding agents
├── plan/         # Planning and organization agents
├── review/       # Review and quality agents
├── claude/       # Claude Code specific agents
└── [domain]/     # Domain-specific directories as needed

Read the full file on GitHub · 679 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 · 679 lines · 19 tokens per session scan A 0f4c9f76b315

Subscribe to this mod's changes

agent-conventions 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 6,107 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.