refinement-mode

refinement-mode is a command for Claude Code from appboypov/pew-pew-plaza-packs. It costs 0 tokens per session (2,535 once invoked), scanned A, original, MIT.

An operating mode for improving any template through repeated, focused questions. It breaks the template into sections and gathers missing information without making assumptions.

In plain words
What is it for?
Use it when a template needs systematic completion, clarification, and expansion through step-by-step questioning. It first establishes a specific, measurable goal for the refinement.
Why use it?
It helps turn an incomplete outline into a thorough document while keeping each decision manageable. The original structure is retained during the refinement process.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it when a template needs systematic completion, clarification, and expansion through step-by-step questioning. It first establishes a specific, measurable goal for the refinement.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/refinement-mode/github.svg)](https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/refinement-mode)
Your own site
<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.

agentmods 80×15 button for refinement-mode

Your own site · 80×15
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,535 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 $0.00000 $0.02535
Opus 5 $0.00000 $0.01267
Sonnet 5 $0.00000 $0.00507
Haiku 4.5 $0.00000 $0.00253

Measured 12d ago against content hash c4e5b876fd90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

.claude/commands/activate/refinement-mode.md · 361 lines

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:

  1. Load the provided template
  2. Analyze its structure and identify all placeholder sections [...]
  3. Transform the refinement need into a specific, measurable objective
  4. Present the interpreted goal for confirmation
  5. 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:

  1. Start with the template's primary purpose/outcome
  2. Explore what needs to exist to achieve that outcome
  3. For each element discovered, understand its purpose
  4. Continue drilling down with contextual questions
  5. Stop when elements can't be split further without losing meaning
  6. Update document after EVERY answer
  7. Show updated sections to maintain transparency

Read the full file on GitHub · 361 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. 12d ago First seen · 361 lines · 0 tokens per session scan A c4e5b876fd90

Subscribe to this mod's changes

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.