What is bluebox CLAUDE.md?

Development instructions for the VectorlyApp/bluebox codebase. They document how to set up the Python environment, run tests and benchmarks, and use the project's browser-monitoring and discovery commands.

Use them when working on bluebox: create or activate its Python environment, install it for development, run the test suite or benchmarks, and start browser monitoring or routine discovery.

They give agents a consistent way to prepare the project, verify changes, and run its development tools. The supplied excerpt is specific to this codebase and does not describe a general add-on.

How VectorlyApp/bluebox configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to VectorlyApp/bluebox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/VectorlyApp/bluebox/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/VectorlyApp/bluebox

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vectorlyapp/bluebox/claude-md/github.svg)](https://agentmods.dev/instructions/vectorlyapp/bluebox/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vectorlyapp/bluebox/claude-md"><img src="https://agentmods.dev/badge/instructions/vectorlyapp/bluebox/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/vectorlyapp/bluebox/claude-md"><img src="https://agentmods.dev/badge/instructions/vectorlyapp/bluebox/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,431 This file is loaded in full into every session.

When invoked 3,431 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.03431	$0.03431
Opus 5.5	$0.01372	$0.01372
Sonnet 5.5	$0.00686	$0.00686
Haiku 4.5	$0.00343	$0.00343

Measured 2mo ago against content hash 877105bf2efb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bluebox CLAUDE.md scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Verify: `curl http://127.0.0.1:9222/json/version`

CLAUDE.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bluebox Development Guide

This file provides context and guidelines for working with the bluebox codebase.

Bash Commands

Development Setup

uv venv bluebox-env && source bluebox-env/bin/activate - Create and activate virtual environment (recommended)
python3 -m venv bluebox-env && source bluebox-env/bin/activate - Alternative venv creation
uv pip install -e . - Install package in editable mode (faster with uv)
pip install -e . - Install package in editable mode (standard)

Testing

pytest tests/ -v - Run all tests with verbose output
pytest tests/unit/test_js_utils.py -v - Run specific test file
pytest tests/unit/test_js_utils.py::test_function_name -v - Run specific test
python scripts/dev/run_benchmarks.py - Run routine discovery benchmarks
python scripts/dev/run_benchmarks.py -v - Run benchmarks with verbose output

CLI Tools

bluebox-monitor --host 127.0.0.1 --port 9222 --output-dir ./cdp_captures --url about:blank --incognito - Start browser monitoring
bluebox-discover --task "your task description" --cdp-captures-dir ./cdp_captures --output-dir ./routine_discovery_output --llm-model gpt-5.2 - Discover routines from captures
bluebox-execute --routine-path example_data/example_routines/amtrak_one_way_train_search_routine.json --parameters-path example_data/example_routines/amtrak_one_way_train_search_input.json - Execute a routine
bluebox-api-index --cdp-captures-dir ./cdp_captures --task "your task" --output-dir ./api_indexing_output --model gpt-5.2 --post-run-analysis - Run the API indexing pipeline (exploration + routine construction)
bluebox-agent-adapter --agent NetworkSpecialist --cdp-captures-dir ./cdp_captures - Start HTTP adapter for programmatic agent interaction (see Agent HTTP Adapter section below)
bluebox-agent-adapter --list-agents - List all available agents and their required data

Chrome Debug Mode

macOS: /Applications/Google Chrome.app/Contents/MacOS/Google Chrome --remote-debugging-address=127.0.0.1 --remote-debugging-port=9222 --user-data-dir="$HOME/tmp/chrome" --remote-allow-origins='*' --no-first-run --no-default-browser-check
Verify: curl http://127.0.0.1:9222/json/version

Read the full file on GitHub · 295 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.

2mo ago First seen · 295 lines · 3,431 tokens per session scan A 877105bf2efb

Subscribe to this mod's changes

bluebox CLAUDE.md is an instructions file published in the GitHub repository VectorlyApp/bluebox (202 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 3,431 tokens to every session, about $0.0137 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

ai-agents ai-web-app ai-website api browser-automation cdp

bluebox CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
bluebox CLAUDE.mdVectorlyApp/bluebox	Instructions file	202	8mo ago	Apache-2.0	A	3,431	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

bluebox: Instructions file for Claude Code