glassbox

glassbox is a skill for Claude Code, Codex from adihebbalae/glassbox. It costs 101 tokens per session (4,841 once invoked), scanned A, original, MIT.

A browser-based checker for testing a web interface running on your own computer. It reports problems such as console or network errors, broken buttons, layout and colour issues, and accessibility concerns.

In plain words
What is it for?
Use it to test local websites, reproduce interface bugs, check handlers and navigation, inspect browser errors, and review layout, contrast, accessibility, and different viewport or theme settings.
Why use it?
It shows whether frontend code actually works in a real browser instead of relying only on code inspection. Structured findings and screenshots help locate visible and interactive defects.

Skill for Claude CodeCodex

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 skills/adihebbalae/glassbox/skill
Any agent
npx skills add adihebbalae/glassbox --skill skill
Clone the repo
git clone --depth 1 https://github.com/adihebbalae/glassbox

Made for: Claude Code, Codex.

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 glassbox

README.md
[![agentmods](https://agentmods.dev/badge/skills/adihebbalae/glassbox/skill.svg)](https://agentmods.dev/skills/adihebbalae/glassbox/skill)
Your own site
<a href="https://agentmods.dev/skills/adihebbalae/glassbox/skill"><img src="https://agentmods.dev/badge/skills/adihebbalae/glassbox/skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,841 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 $0.00101 $0.04841
Opus 5 $0.00051 $0.02420
Sonnet 5 $0.00020 $0.00968
Haiku 4.5 $0.00010 $0.00484

Measured 4d ago against content hash d7d5c4c44d54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

glassbox 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.

skill/SKILL.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Glassbox — instrumented browser for verifying your own UI

You wrote the code; Glassbox checks it against a real browser and tells you, in structured findings, exactly what's broken and where. It is not a general web agent — it's a verification-and-debug plane for the UI you are building.

Every tool is gb_* and takes a session (except gb_session open). One daemon runs the browser; the MCP tools are thin proxies. Screenshots and full reports are written to a per-session artifact directory on disk and returned as paths — if you need to see an image, Read the path (inline images cost 10-20x the tokens).

1. Session-per-agent (the core pattern)

Open ONE session named for your task. Parallel agents/subagents each open their OWN session — never share one (refs, navigation, and breakpoints are per-session).

gb_session {op:"open", name:"checkout-form"}      → info + a watchUrl for humans

Options: headed:true (visible window — for hover/tooltip/GPU-sensitive checks), viewport:{width,height}, colorScheme:"dark", baseUrl (then gb_goto takes relative paths), your site's own theme switch so verify can sweep it — themeAttr:"data-theme" (attribute) or themeClass:"dark" (Tailwind darkMode:['class'] — the common one) — and ignore404:["/favicon.ico"] for 404s you already know about.

Need a different viewport later? Resize in place instead of opening a second session: gb_session {op:"resize", name:"checkout-form", viewport:{width:390,height:844}} (CLI: glassbox session resize checkout-form 390x844).

Cleanup — you are sharing this daemon. ONE Glassbox daemon serves every agent on the machine, so sessions are owned: whoever opened one owns it. The MCP shim identifies itself automatically (mcp-<pid>); CLI agents export GLASSBOX_CLIENT=my-task once, or pass --client my-task. Clean up with either of:

gb_session {op:"close", name:"checkout-form"}     ← one session
glassbox kill-all --mine                          ← every session YOU opened (CLI)

Read the full file on GitHub · 223 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 223 lines · 101 tokens per session scan A d7d5c4c44d54

Subscribe to this mod's changes

glassbox is a skill published in the GitHub repository adihebbalae/glassbox (0 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 4,841 once invoked, about $0.0005 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 2026-08-31.