agentmods.dev

bobbit: Skill for Claude Code

.claude/skills/qa-test/SKILL.md

qa-test is a skill for Claude Code from G-Research/bobbit. It costs 16 tokens per session (3,002 once invoked), scanned C, original, MIT.

A browser-based quality-assurance process for testing an application in a temporary isolated environment. It runs user scenarios, records screenshots, and produces an HTML validation report.

In plain words
What is it for?
Setting up a temporary test copy, driving browser scenarios, checking page behavior and errors, capturing evidence, and reporting results.
Why use it?
It provides repeatable evidence of whether real user flows work without affecting the main application environment.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is G-Research/bobbit's own configuration. It tells Claude Code how to work on bobbit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bobbit configures →

not rated 18repo +2 changed 1mo ago C scan 16 tokens original MIT
View source ↗ G-Research/bobbit
Reuse

Borrowing it

Nothing to install: this file belongs to G-Research/bobbit. 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/G-Research/bobbit/main/.claude/skills/qa-test/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/G-Research/bobbit

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.

agentmods badge for qa-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/g-research/bobbit/qa-test/github.svg)](https://agentmods.dev/skills/g-research/bobbit/qa-test)
Your own site
<a href="https://agentmods.dev/skills/g-research/bobbit/qa-test"><img src="https://agentmods.dev/badge/skills/g-research/bobbit/qa-test/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.

agentmods 80×15 button for qa-test

Your own site · 80×15
<a href="https://agentmods.dev/skills/g-research/bobbit/qa-test"><img src="https://agentmods.dev/badge/skills/g-research/bobbit/qa-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,002 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.03002
Opus 5.5 $0.00006 $0.01201
Sonnet 5.5 $0.00003 $0.00600
Haiku 4.5 $0.00002 $0.00300

Measured 1mo ago against content hash bd48eb162742, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

qa-test scanned grade C with 2 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 1mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

2. Remove the temp directory: `rm -rf "$WORK_DIR"`

Makes network callslowCapability

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

if curl -sf "<health_check_url>" > /dev/null 2>&1; then
.claude/skills/qa-test/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Testing Protocol

You are running QA testing for a goal. This protocol stands up an isolated copy of the application, drives a real browser through user scenarios, captures screenshot evidence, and produces an HTML validation report.

Prerequisites

  • You need browser tools available. Use the native browser tools — NOT the mcp__playwright__* tools. The MCP Playwright browser is a single shared instance across all sessions — other agents and the dev server will hijack your page. The native browser tools give you an isolated browser instance per session.
  • Available native browser tools: browser_navigate, browser_screenshot, browser_click, browser_type, browser_eval, browser_wait, browser_snapshot, browser_console_messages, browser_press_key, browser_hover, browser_select_option, browser_resize
  • browser_snapshot is the best way to understand page structure — it returns an ARIA accessibility tree with element roles, names, and refs. Use it instead of screenshots when you need to find interactive elements or verify page content.
  • browser_console_messages captures JS console output. Call with level="error" after each navigation to catch silent errors.
  • At least one component in .bobbit/config/project.yaml must carry config.qa_start_command

Step 1: Read Configuration

Read the project config to discover the component(s) with QA testbed configuration:

cat .bobbit/config/project.yaml

Each component in components[] may carry an opaque config: map. The component you want is the one whose config.qa_start_command is set. Pick it as follows:

  1. Look for a [QA-TEST CONTEXT]\ncomponent: <name> block near the top of your kickoff message. When the verification harness invokes you for an agent-qa step that declares a component: field, it prepends this context block to your prompt. If present, prefer that component.
  2. Else, if multiple components have config.qa_start_command, use the component whose name matches the project name.
  3. Else use the first component with config.qa_start_command.

Read the full file on GitHub · 224 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.

  1. 1mo ago Changed · -64 lines bd48eb162742
  2. 2mo ago First seen · 288 lines · 16 tokens per session scan C d5859add1d5a

Subscribe to this mod's changes

qa-test is a skill published in the GitHub repository G-Research/bobbit (18 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 3,002 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

E2E testingTesting
Related

qa-test compared with skills from other repositories

qa-test next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
qa-testG-Research/bobbitSkill181mo agoMITC16Claude Code
verify-omnigentomnigent-ai/omnigentSkill11kyesterdayApache-2.0A100Claude Code, Codex
test-masterJeffallan/claude-skillsSkill12k7d agoMITA104Claude Code
eval-dataset-designbojieli/ai-agent-bookSkill57k29d agoApache-2.0A138Claude Code, Codex
dogfoodcallstack/agent-deviceSkill5.3kyesterdayMITA55Claude Code
cua-driverdavidondrej/skillsSkill4.3k3d agoMITA68Claude Code, Codex
test-warp-uiwarpdotdev/warpSkill66kyesterdayAGPL-3.0A55Claude Code