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/template-rules)<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/template-rules"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/template-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.
<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/template-rules"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/template-rules.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 | $0.01252 |
| Opus 5 | $0.00009 | $0.00626 |
| Sonnet 5 | $0.00004 | $0.00250 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
template-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.
How it starts
The opening of the file, as written. The whole thing — 167 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.
📏 Rules
💡 Specific ALWAYS and NEVER rules that must be followed without exception.
👍 Always
- WHEN placing instruction placeholders ALWAYS use single square brackets for placeholder instructions.
- Example: [Replace this with actual content]
- WHEN creating template variables ALWAYS use double curly brackets WITH backticks to indicate template variables.
- Example:
{{variable-name}}
- Example:
- WHEN referencing parts of the document ALWAYS use template variables.
- Example: Follow instruction in
{{variable-name}}when [some condition].
- Example: Follow instruction in
- WHEN demonstrating examples ALWAYS put them inside an example tag inside a codeblock.
- Example: See
{{example}}
- Example: See
- WHEN creating examples ALWAYS describe the example types instead of actual examples.
- Example: See
{{example}}
- Example: See
- WHEN creating examples that need multiple items ALWAYS describe ALL types on ONE line (e.g., "architectural decisions, limitations, dependencies, performance considerations").
- Example: See
{{multiple-items-example}}
- Example: See
- WHEN examples require specific structure (like steps with substeps) ALWAYS show the exact structure with inline [placeholder] instructions while keeping type descriptions on single lines.
- Example: See
{{structured-example}}
- Example: See
- WHEN creating examples for structured content (like nested lists, hierarchies, or multi-level content) NEVER show the structure - ONLY describe what types go there in a single line.
- WHEN an example has complex formatting IGNORE the formatting and ONLY list the content types.
👎 Never
- WHEN creating examples NEVER use actual content, only describe the types of examples.
- WHEN creating examples NEVER use multiple lines for the example types.
🚫 Example Structure Rule
NEVER recreate the structure of what you're documenting in the example. The example should ONLY contain:
- First line: [Description of all the types that go in this section]
- Second line: [Additional items if needed]
- Third line: [...]
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 · 167 lines · 18 tokens per session scan A 2f1c6a88110e
template-rules 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 1,252 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
security
Rapid security assessment focused on OWASP Top 10 vulnerabilities.
costs
Open ccboard costs analysis tab.
content-idea
Content idea generation command. Creates a structured idea list for a topic, theme, or platform.
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.