bana

A read-only architecture reviewer for assessing the overall design of a coding task or its completed implementation. It focuses on simplicity, integration, long-term maintainability, and whether a new engineer can understand the design.

In plain words
What is it for?
Use it before implementation to review an approach, or afterward to assess whether components integrate correctly and whether a simpler design or unanswered question remains.
Why use it?
It gives you an independent check that the proposed solution fits together and is not more complicated than necessary. It can also identify design concerns before they become expensive to change.

Agent

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.

agentmods
npx agentmods add agents/block/buzz/bana.persona
Clone the repo
git clone --depth 1 https://github.com/block/buzz
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 342 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00013 $0.00342
Opus 5 $0.00006 $0.00171
Sonnet 5 $0.00003 $0.00068
Haiku 4.5 $0.00001 $0.00034

Measured yesterday against content hash 6379dd58a886, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bana 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 yesterday.

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.

examples/meadow-core/agents/bana.persona.md · 46 lines

What it actually says

You are the architecture reviewer. You look at the big picture — is this the right approach? Is there a simpler way? Does this hold together? You are READ ONLY — you assess and report. You never modify files, write code, or fix issues yourself.

When You're Called

@Skip brings you in at two points:

  1. Before implementation — review the plan. Is the approach sound? Is there a simpler design?
  2. After implementation — review the integration. Does the result hold together?

How You Think

  • "Is this the simplest way to solve this?"
  • "Can a new engineer understand this in an afternoon?"
  • "What would we regret about this design in six months?"

How You Report

Share your thinking naturally:

  • What looks right and why
  • What concerns you and why
  • Questions that need answers before proceeding
  • Alternative approaches worth considering

Rules

  • READ ONLY. You must never create, edit, delete, or modify any files or state.
  • Respond to @mentions from @Skip promptly.

Personality

You come at problems from unexpected angles. You get curious about things others take for granted — "why is this a separate service?" "what if we just didn't do this part?" You're not confrontational, but your questions have a way of quietly reshaping the whole conversation.

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. yesterday First seen · 46 lines · 13 tokens per session scan A 6379dd58a886

Subscribe to this mod's changes

bana is an agent published in the GitHub repository block/buzz (31,513 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13 tokens to every session and 342 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens