blackbox-tester

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.

Any agent

npx skills add jggomez/expert-ai-developer-skills --skill blackbox-tester

Clone the repo

git clone --depth 1 https://github.com/jggomez/expert-ai-developer-skills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jggomez/expert-ai-developer-skills/blackbox-tester/github.svg)](https://agentmods.dev/skills/jggomez/expert-ai-developer-skills/blackbox-tester)

Your own site

<a href="https://agentmods.dev/skills/jggomez/expert-ai-developer-skills/blackbox-tester"><img src="https://agentmods.dev/badge/skills/jggomez/expert-ai-developer-skills/blackbox-tester/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/skills/jggomez/expert-ai-developer-skills/blackbox-tester"><img src="https://agentmods.dev/badge/skills/jggomez/expert-ai-developer-skills/blackbox-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,055 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00037	$0.03055
Opus 5.5	$0.00015	$0.01222
Sonnet 5.5	$0.00007	$0.00611
Haiku 4.5	$0.00004	$0.00305

Measured today against content hash 8c36d40f3d87, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

blackbox-tester 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 today.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/check_evidence.py, scripts/e2e_recorder.mjs, scripts/e2e_recorder.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

It enforces a strict **Fail-Honest Anti-Hallucination Protocol**: if no web UI exists in scope it immediately returns `SKIPPED`, and if the dev server or Chromium binary cannot run it immediately stops and returns `BLOCK

plugins/antigravity/python-backend/skills/blackbox-tester/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Black-Box Browser Verification & Visual Testing Skill

Overview

This skill provides deterministic, fail-honest black-box browser verification from the perspective of an actual end user. Operating as a Senior Black-Box QA Engineer, it executes real Chromium browser journeys via Playwright (run_command / Bash), exercises interactive GUI forms, attaches console and network error listeners, captures physical .png screenshots across 4 responsive viewports in docs/<feature-name>/evidence/, and returns a concise Zero-Fluff report (<= 50 lines) in its final message.

Return Contract: Return the review in your final message (<= 50 lines: verdict, findings with file:line, required fixes); do NOT write a report file.

It enforces a strict Fail-Honest Anti-Hallucination Protocol: if no web UI exists in scope it immediately returns SKIPPED, and if the dev server or Chromium binary cannot run it immediately stops and returns BLOCKED with the exact terminal error—never substituting curl, TestClient, jsdom, or static code inspection for a real browser.

When to Use

Trigger Scenarios

Validating runnable web applications, SPAs, and frontend portals served over HTTP/HTTPS.
Testing real end-to-end user flows (signup, login, navigation, checkout, wizard steps) in a live Chromium DOM.
Auditing GUI form behavior (validation errors, disabled submit states, loading feedback, focus management).
Asserting 0 unhandled JavaScript runtime crashes (pageerror / console.error) and 0 unexpected HTTP 4xx/5xx responses.
Capturing physical .png evidence across Mobile (375x812), Tablet (768x1024), Desktop (1280x800), and Widescreen (1920x1080) viewports in docs/<feature-name>/evidence/.
Returning the standard verdict in the final message (<= 50 lines, no report file) during State 3/4 verification.

When NOT to Use

Pure backend/API/CLI/pipeline projects without a web UI: Immediately return SKIPPED: No web UI in scope; route headless API tests to qa-tester.
Unit test creation during coding: Route to test-driven-development or code-implementer.
Static code smell and complexity review: Route to code-critic.
Adversarial stress and concurrency fuzzing: Route to adversarial-challenger.
Flutter native mobile apps: Return SKIPPED: mobile target, not in scope. Flutter web is in scope: follow references/flutter-web-playwright.md.

Read the full file on GitHub · 175 lines

Files

What ships with it

5 files 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.

today First seen · 175 lines · 37 tokens per session scan A 8c36d40f3d87

Subscribe to this mod's changes

blackbox-tester is a skill published in the GitHub repository jggomez/expert-ai-developer-skills (30 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 3,055 once invoked, about $0.0001 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 2026-11-06.

Backend and APIs Browser automation Languages

blackbox-tester next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
blackbox-testerjggomez/expert-ai-developer-skills	Skill	30	yesterday	Apache-2.0	A	37	Claude Code, Codex
chili3dznlgis/opengis-skills	Skill	76	10d ago	MIT	A	109	Claude Code, Codex
agui-dotnet-streaming-chatag-ui-protocol/ag-ui	Skill	17k	yesterday	MIT	A	223	Claude Code
azure-mgmt-apicenter-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	97	Claude Code
azure-communication-chat-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	41	Claude Code
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	43	Claude Code
minimal-apicodewithmukesh/dotnet-claude-kit	Skill	805	2d ago	MIT	A	101	Claude Code