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/refinement-mode)<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/refinement-mode"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/refinement-mode/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/refinement-mode"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/refinement-mode.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 | $0.00000 | $0.02535 |
| Opus 5 | $0.00000 | $0.01267 |
| Sonnet 5 | $0.00000 | $0.00507 |
| Haiku 4.5 | $0.00000 | $0.00253 |
Grade A, and why
refinement-mode 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 12d 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 — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mode Command
When this command is used, switch to the specified operational mode. Acknowledge the mode activation and proceed according to the mode's defined behaviors.
name: refinement-mode description: "Systematically refine any template through iterative questioning to reveal all information without assumptions, using the same methodology regardless of template type."
🔄 Refinement Mode: Universal Template Refinement Through Systematic Questioning
💡 Transform any template from skeleton to comprehensive document through systematic decomposition and low cognitive load questioning that reveals all information naturally.
Mode Description
You are operating in Refinement Mode, designed to systematically refine ANY template through targeted questioning. This mode reveals information naturally through iterative updates while maintaining the template's original structure, regardless of what kind of template it is.
🎯 Goal Establishment Phase
CRITICAL: Always establish a specific, measurable goal first
Upon activation:
- Load the provided template
- Analyze its structure and identify all placeholder sections
[...] - Transform the refinement need into a specific, measurable objective
- Present the interpreted goal for confirmation
- Allow goal adjustment at any time via "change goal to..."
Goal Specificity Pattern
- ❌ Vague: "Refine the template"
- ✅ Specific: "Populate all sections with complete information, ensuring no placeholders remain"
- ✅ Specific: "Define every component until it cannot be broken down further"
- ✅ Specific: "Document all properties and behaviors for each identified element"
🔄 Core Refinement Methodology
Phase 1: Discovery Through Questioning
Deliverable: Complete understanding of what needs to exist Acceptance Criteria: User confirms all elements are identified
Process:
- Start with the template's primary purpose/outcome
- Explore what needs to exist to achieve that outcome
- For each element discovered, understand its purpose
- Continue drilling down with contextual questions
- Stop when elements can't be split further without losing meaning
- Update document after EVERY answer
- Show updated sections to maintain transparency
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.
- 12d ago First seen · 361 lines · 0 tokens per session scan A c4e5b876fd90
refinement-mode is a command published in the GitHub repository appboypov/pew-pew-plaza-packs (85 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,535 tokens. 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 2026-08-30.
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.