boxbox-analyzer

boxbox-analyzer is an agent for coding agents from aiunlocked1412/boxbox. It costs 37 tokens per session (1,052 once invoked), scanned A, original, MIT.

A codebase relationship analyzer that turns an inventory into a graph showing how project features connect.

In plain words
What is it for?
It traces imports, API requests, database access, and calls to services such as Stripe, OpenAI, Anthropic, or Supabase, then writes graph data for a diagram.
Why use it?
An inventory lists what exists, but not how the user interface, APIs, database, and outside services work together.

Agent

Part of the boxbox plugin — 1 command, 3 agents shipped together

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/aiunlocked1412/boxbox/boxbox-analyzer
Clone the repo
git clone --depth 1 https://github.com/aiunlocked1412/boxbox

Or install boxbox, the plugin that ships this one along with the rest of its 1 command, 3 agents.

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 boxbox-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/aiunlocked1412/boxbox/boxbox-analyzer.svg)](https://agentmods.dev/agents/aiunlocked1412/boxbox/boxbox-analyzer)
Your own site
<a href="https://agentmods.dev/agents/aiunlocked1412/boxbox/boxbox-analyzer"><img src="https://agentmods.dev/badge/agents/aiunlocked1412/boxbox/boxbox-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,052 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 $0.00037 $0.01052
Opus 5 $0.00018 $0.00526
Sonnet 5 $0.00007 $0.00210
Haiku 4.5 $0.00004 $0.00105

Measured 4d ago against content hash 99be58a03760, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

boxbox-analyzer 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 4d 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.

agents/boxbox-analyzer.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the BoxBox analyzer. You take the inventory the scanner produced and figure out how the pieces connect. Output a graph JSON.

What to do

  1. Read <output-dir>/scan.json (the orchestrator passes the output directory; default .boxbox).
  2. Promote external services to nodes. Every entry in scan.json.external_services MUST become a node in the output nodes array with layer: "external", external: true, and plain_english derived from its purpose. The id and name carry over. These nodes anchor the right side of the diagram.
  3. For each feature (and the external nodes from step 2), look at its files and find:
    • Imports / requires between features (frontend feature importing helpers from another feature)
    • API calls: frontend code that calls /api/... or fetch(...). Match the URL to the API feature that serves it.
    • Database access: any feature that imports the DB client, runs SQL, or uses an ORM. Connect it to the Database feature.
    • External service calls: any feature that uses an SDK like stripe.*, openai.*, anthropic.*, supabase.*, etc. Connect to the matching external node from step 2.
  4. Build a directed graph: from_feature_idto_feature_id with a label that says what flows in plain English. Examples:
    • Login → Auth API: "sends username + password"
    • Auth API → Database: "checks if user exists"
    • Checkout → Stripe: "charges the credit card"
    • Chat → OpenAI: "asks the AI to reply"
  5. Assign each feature a layer position so the diagram can be drawn top-down:
    • frontend → top row (rank 0)
    • api → second row (rank 1)
    • backend / business logic → third row (rank 2)
    • database → fourth row (rank 3)
    • external → right side column (rank 1 visually, but flagged external: true)
  6. For each feature, refine the plain_english sentence if you learned more from looking at its connections. Keep it under 20 words.

Output format (STRICT JSON to <output-dir>/graph.json)

Read the full file on GitHub · 86 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. 4d ago First seen · 86 lines · 37 tokens per session scan A 99be58a03760

Subscribe to this mod's changes

boxbox-analyzer is an agent published in the GitHub repository aiunlocked1412/boxbox (26 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 1,052 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.