Agent skill

Test And Break

by rohunj in rohunj/claude-build-workflow

Autonomous testing skill that opens a deployed app, goes through user flows, tries to break things, and writes detailed bug reports.

No licenceAuto-check passedTesting & QA

Install Test And Break

skills CLI
$ npx skills add rohunj/claude-build-workflow --skill test-and-break -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install rohunj/claude-build-workflow test-and-break --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/rohunj/claude-build-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/test-and-break .claude/skills/test-and-break && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
test-and-break
GitHub stars
231
Token cost
~1.6k tokens
SKILL.md length
497 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
None found

At a glance

Autonomous testing skill that opens a deployed app, goes through user flows, tries to break things, and writes detailed bug reports.

  • Works in 4 steps: Understand the App → Open the App → Test Each User Flow → …
  • QA the deployment
  • SKILL.md covers Prerequisites, The Job, Testing Process and Severity Guidelines, plus 5 more sections
  • Calls jq and npm

What it does

Test And Break is an agent skill from rohunj/claude-build-workflow. Autonomous testing skill that opens a deployed app, goes through user flows, tries to break things, and writes detailed bug reports. Use after deploying to staging. Triggers on: test the app, find bugs, QA the deployment, break the app, test staging.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering UX design, QA and bug reports and Debugging. The repository describes itself as: Automated workflow for building apps with Claude Code. Describe what you want, answer questions, let it build autonomously.

When your agent uses it

  • QA the deployment
  • Tasks that involve UX design
  • Tasks that involve QA and bug reports

Example prompts

  • “/test-and-break”

Requirements

  • Node.js

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Understand the App
  2. Open the App
  3. Test Each User Flow
  4. Document Each Bug

What it can do on your machine

Read from SKILL.md and the folder at commit 91f884e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq
    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Test And Break loads about 1.6k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 497 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 497 words (~1,566 tokens).

“Systematically test a deployed application by going through user flows, trying edge cases, and attempting to break things. Outputs structured bug reports that can be converted to user stories for autonomous fixing.”

— opening of SKILL.md by rohunj
name
test-and-break

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/test-and-break of rohunj/claude-build-workflow.

Open the folder on GitHubat commit 91f884e

Compare with similar skills

Test And Break next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Test And Break compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Test And Break this skillrohunj/claude-build-workflow231—~1.6kAutomated safety check: PassNone
Scoutqa Testgithub/awesome-copilot40k1 repos~3.5kAutomated safety check: PassMIT
Exploratory Testtobihagemann/turbo408—~2kAutomated safety check: PassMIT
Exploratory Testtobihagemann/turbo408—~2kAutomated safety check: PassMIT
Actionbook Web Testactionbook/actionbook1.6k—~9.7kAutomated safety check: PassApache-2.0
Team Frontend Debugcatlog22/Claude-Code-Workflow2.1k—~2.8kAutomated safety check: NotesMIT

Similar skills

  • Scoutqa Test

    github/awesome-copilot

    Official

    This skill should be used when the user asks to "test this website", "run exploratory testing", "check for accessibility issues", "verify the login flow works", "find bugs on this page", or requests…

    40k GitHub starsUsed in 1 repo~3.5k tokens
    Testing & QAAuto-check passed
  • Exploratory Test

    tobihagemann/turbo

    Execute multi-level exploratory testing of the app covering basic functionality, complex operations, adversarial testing, and cross-cutting scenarios, plus usability observations through a UX lens…

    408 GitHub stars~2k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Exploratory Test

    tobihagemann/turbo

    Execute multi-level exploratory testing of the app covering basic functionality, complex operations, adversarial testing, and cross-cutting scenarios, plus usability observations through a UX lens…

    408 GitHub stars~2k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Actionbook Web Test

    actionbook/actionbook

    Run browser-based web tests against websites using Actionbook CLI.

    1.6k GitHub stars~9.7k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Team Frontend Debug

    catlog22/Claude-Code-Workflow

    Frontend debugging team using Chrome DevTools MCP. An agent skill from catlog22/Claude-Code-Workflow.

    2.1k GitHub stars~2.8k tokensUpdated 3 mo ago
    Testing & QAAuto-check: notes
  • Gstack

    LeoYeAI/openclaw-master-skills

    Fast headless browser for QA testing and site dogfooding. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub stars~4.1k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check: notes

More from rohunj/claude-build-workflow

  • Ralph

    rohunj/claude-build-workflow

    Convert PRDs to prd.json format for the Ralph autonomous agent system.

    231 GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed
  • Bugs To Stories

    rohunj/claude-build-workflow

    Convert bug reports into prd.json user stories for autonomous fixing.

    231 GitHub stars~1.4k tokensUpdated 8 mo ago
    Auto-check passed
  • Compound Engineering

    rohunj/claude-build-workflow

    Compound Engineering workflow for AI-assisted development. An agent skill from rohunj/claude-build-workflow.

    231 GitHub stars~2.1k tokensUpdated 8 mo ago
    Auto-check passed
  • Edge Cases

    rohunj/claude-build-workflow

    Analyze a PRD for edge cases, failure modes, and scenarios that might be missed.

    231 GitHub stars~1.5k tokensUpdated 8 mo ago
    Auto-check passed
  • Story Quality

    rohunj/claude-build-workflow

    Review user stories for quality, proper sizing, sequencing, and acceptance criteria.

    231 GitHub stars~1.7k tokensUpdated 8 mo ago
    Auto-check passed

Questions about Test And Break

What does Test And Break do?

Autonomous testing skill that opens a deployed app, goes through user flows, tries to break things, and writes detailed bug reports. Test And Break is an agent skill from rohunj/claude-build-workflow. Autonomous testing skill that opens a deployed app, goes through user flows, tries to break things, and writes detailed bug reports.

When should I use Test And Break?

Test And Break fits situations like: QA the deployment; tasks that involve UX design; tasks that involve QA and bug reports.

How do I install Test And Break in Claude Code?

Run `npx skills add rohunj/claude-build-workflow --skill test-and-break -a claude-code`. Or copy the skill folder (skills/test-and-break in rohunj/claude-build-workflow) into .claude/skills/test-and-break in your project. Claude Code loads it when a task matches its description.

How do I install Test And Break in Codex?

Run `npx skills add rohunj/claude-build-workflow --skill test-and-break -a codex`. Or copy the skill folder (skills/test-and-break in rohunj/claude-build-workflow) into .agents/skills/test-and-break in your project. Codex loads it when a task matches its description.

Can I use Test And Break in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rohunj/claude-build-workflow --skill test-and-break -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/test-and-break, .gemini/skills/test-and-break, .github/skills/test-and-break and .opencode/skills/test-and-break in your project.

What does Test And Break need to run?

Going by SKILL.md and its folder, Test And Break needs the command-line tools its instructions call (jq and npm). Our summary lists: Node.js.

Does Test And Break access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Test And Break safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Test And Break use?

No licence was found for Test And Break or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Test And Break use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Test And Break?

Skills that share tags, products or a category with Test And Break: Scoutqa Test (github/awesome-copilot, 40k stars), Exploratory Test (tobihagemann/turbo, 408 stars), Exploratory Test (tobihagemann/turbo, 408 stars) and Actionbook Web Test (actionbook/actionbook, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Test And Break?

rohunj (a GitHub user) maintains it in rohunj/claude-build-workflow, which has 231 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on January 18, 2026.

Source: rohunj/claude-build-workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.