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/agent-conventions)<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.
<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>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 | $0.00019 | $0.06107 |
| Opus 5 | $0.00010 | $0.03053 |
| Sonnet 5 | $0.00004 | $0.01221 |
| Haiku 4.5 | $0.00002 | $0.00611 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- create-agent — 92% identical, 568 lines differ
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.mdnotprompt-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.mdorassistant.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
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 · 679 lines · 19 tokens per session scan A 0f4c9f76b315
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.
Other commands, from other repositories
worktree-cleanup
A command for removing a Git worktree, which is a separate working folder linked to the same repository, after its pull request is merged.
costs
Open ccboard costs analysis tab.
mobile
Mobile project management command. React Native/Flutter/Expo/Swift/Kotlin scaffolding, version sync, build and release guides.
env-check
.env file validation. Detects missing, extra, empty, and placeholder values + .gitignore check.
callee-create-agent
Create a Callee agent or deterministic workflow.
ship
Ship command. Runs the pre-flight gate, decides the version bump, assembles the changelog, and opens the PR via the release-manager agent. Nothing ships unless the gate is green.