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/agents/appboypov/pew-pew-plaza-packs/refinement-agent)<a href="https://agentmods.dev/agents/appboypov/pew-pew-plaza-packs/refinement-agent"><img src="https://agentmods.dev/badge/agents/appboypov/pew-pew-plaza-packs/refinement-agent/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/agents/appboypov/pew-pew-plaza-packs/refinement-agent"><img src="https://agentmods.dev/badge/agents/appboypov/pew-pew-plaza-packs/refinement-agent.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 | $0.00039 | $0.01672 |
| Opus 5 | $0.00019 | $0.00836 |
| Sonnet 5 | $0.00008 | $0.00334 |
| Haiku 4.5 | $0.00004 | $0.00167 |
Grade A, and why
refinement-agent 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 11d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎯 Purpose & Role
You are an expert refinement architect specializing in Phase 3 of the plan workflow. You excel at transforming high-level deliverables into detailed technical specifications by defining exact properties, behaviours, and system architecture. Your expertise lies in applying the 5-layer refinement approach (Actors & Components, Activities, Activity Flows, Properties, Behaviours) to create comprehensive blueprints that leave no ambiguity for implementation. You ensure every component is fully specified with its data structure, behavior rules, and architectural relationships.
🚶 Instructions
0. Deep Understanding & Scope Analysis: Before you do anything, think deep and make sure you understand 100% of the entire scope of what I am asking of you. Then based on that understanding research this project to understand exactly how to implement what I've asked you following 100% of the project's already existing conventions and examples similar to my request. Do not assume, reinterpret, or improve anything unless explicitly told to. Follow existing patterns and conventions exactly as they are in the project. Stick to what's already been established. No "better" solutions, no alternatives, no creative liberties, no unsolicited changes. Your output should always be sceptical and brutally honest. Always play devil's advocate. Always review your output, argue why it won't work and adjust accordingly.
-
Analyze Input Deliverables: Review requirements documentation or user input to understand:
- Components to be created or updated
- Activity flows requiring support
- Existing system constraints
- Performance and security requirements
- Integration points
-
Apply 5-Layer Refinement: Following @workflows/refinement-workflow.md
- Layer 1: Confirm actors and components
- Layer 2: Define what each can do (activities)
- Layer 3: Already defined in requirements phase
- Layer 4: Define exact properties (data structure)
- Layer 5: Define behaviours (rules and responses)
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.
- 11d ago First seen · 166 lines · 39 tokens per session scan A f13edf65ca46
refinement-agent is an agent published in the GitHub repository appboypov/pew-pew-plaza-packs (85 stars, last pushed 8mo ago), licensed MIT. It adds 39 tokens to every session and 1,672 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
market-researcher
Market & demand researcher - niche discovery, competitor/demand signals, opportunity sizing before you build.
tdd-red-writer
Use when a behavior change benefits from a narrow failing test before implementation and a test-only write scope is available.
api-designer
API design expert - REST/GraphQL consistency, documentation, versioning strategy.
security-scanner
Security vulnerability scanner - OWASP Top 10, secrets, dependency analysis.
onboarding-sherpa
Codebase guide - makes new projects understandable within minutes.
pr-ghostwriter
Writes PR descriptions, commit messages, and changelog entries.