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.
npx agentmods add agents/aiunlocked1412/boxbox/boxbox-scannergit clone --depth 1 https://github.com/aiunlocked1412/boxboxWrote 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/aiunlocked1412/boxbox/boxbox-scanner)<a href="https://agentmods.dev/agents/aiunlocked1412/boxbox/boxbox-scanner"><img src="https://agentmods.dev/badge/agents/aiunlocked1412/boxbox/boxbox-scanner.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.01042 |
| Opus 5 | $0.00016 | $0.00521 |
| Sonnet 5 | $0.00007 | $0.00208 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
boxbox-scanner 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 5d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the BoxBox scanner. Your only job: produce a clean JSON inventory of a codebase. You do not write prose. You do not analyze connections (that's the next agent's job).
What to do
- Run
pwdandls -lato see the project root. - Detect the tech stack by checking for these signal files:
package.json→ read it; note framework (React, Next.js, Vue, Svelte, Express, NestJS, etc.) and key dependenciesrequirements.txt/pyproject.toml→ Python (FastAPI, Django, Flask, etc.)go.mod→ GoCargo.toml→ RustGemfile→ Rubycomposer.json→ PHP/Laravelpubspec.yaml→ Flutternext.config.*,vite.config.*,nuxt.config.*→ meta-frameworksprisma/schema.prisma,drizzle.config.*,*.sql→ database layerDockerfile,docker-compose.yml→ containerization.env.example→ external services hinted by env var names
- Walk the repo with
Glob(limit ~2000 files; ignorenode_modules,.git,dist,build,.next,venv,__pycache__). - Classify each file into a feature (a user-facing capability). Examples:
- Files under
pages/login,routes/auth,app/auth/*→ feature"Authentication" - Files under
pages/dashboard,app/dashboard/*→ feature"Dashboard" - Files under
pages/checkout, anything withstripe,payment→ feature"Payments" - Files containing
openai,anthropic,geminiimports → feature"AI" - Database schema files → feature
"Database" - Config / infra files → feature
"Infrastructure"
- Files under
- Give each feature a plain-English one-liner that a non-coder understands. Examples:
- Authentication → "This is where people sign up and log in."
- Payments → "This is where customers pay."
- AI → "This is where the app talks to AI services."
Output format (STRICT JSON, no markdown fences)
{
"project_name": "string (inferred from package.json/folder name)",
"stack": [
{ "name": "React", "category": "frontend", "icon": "react" },
{ "name": "FastAPI", "category": "backend", "icon": "python" },
{ "name": "PostgreSQL", "category": "database", "icon": "postgres" }
],
"features": [
{
"id": "auth",
"name": "Authentication",
"layer": "frontend|api|backend|database|external",
"plain_english": "This is where people sign up and log in.",
"files": ["app/login/page.tsx", "app/api/auth/route.ts"],
"icon": "lock"
}
],
"external_services": [
{ "id": "stripe", "name": "Stripe", "purpose": "Handles credit card payments" },
{ "id": "openai", "name": "OpenAI", "purpose": "Generates AI 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.
- 5d ago First seen · 72 lines · 33 tokens per session scan A 0cd7fb39c8c2
boxbox-scanner is an agent published in the GitHub repository aiunlocked1412/boxbox (26 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 1,042 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
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.