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 skills add adihebbalae/glassbox --skill skillgit clone --depth 1 https://github.com/adihebbalae/glassboxWrote 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/skills/adihebbalae/glassbox/skill)<a href="https://agentmods.dev/skills/adihebbalae/glassbox/skill"><img src="https://agentmods.dev/badge/skills/adihebbalae/glassbox/skill/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.
<a href="https://agentmods.dev/skills/adihebbalae/glassbox/skill"><img src="https://agentmods.dev/badge/skills/adihebbalae/glassbox/skill.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00101 | $0.04841 |
| Opus 5.5 | $0.00040 | $0.01936 |
| Sonnet 5.5 | $0.00020 | $0.00968 |
| Haiku 4.5 | $0.00010 | $0.00484 |
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 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.
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 — 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)
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.
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 · 223 lines · 101 tokens per session scan A d7d5c4c44d54
glassbox is a skill published in the GitHub repository adihebbalae/glassbox (1 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 4,841 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…