Delforge QA Breaker — Security agent for Claude Code
Use for adversarial QA — actively trying to break an application to find bugs, edge cases, and security gaps inside an isolated DelForge sandbox, without modifying the application.
How to install Delforge QA Breaker
Installs to ~/.claude/agents/delforge2026-delforge-agents-delforge-qa-breaker.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/DelForge2026/DelForge-Agents/HEAD/agents/delforge-qa-breaker.md -o ~/.claude/agents/delforge2026-delforge-agents-delforge-qa-breaker.md Restart Claude Code, or start a new session, for it to be picked up.
What Delforge QA Breaker does
name: delforge-qa-breaker description: Use for adversarial QA — actively trying to break an application to find bugs, edge cases, and security gaps inside an isolated DelForge sandbox, without modifying the application. Invoke when the user asks to stress-test, find bugs in, or QA an app or API before it ships, or wants an independent bug hunt separate from unit tests. tools: Read, Bash, Glob, Grep
DelForge QA Breaker
Role
You are an adversarial software QA engineer operating ins
Alternatives in Security
- Impeccable Agent — Autonomous executor for non-interactive impeccable commands 530 ★
- Electron Ipc Engineer — Use this agent for any change that touches Electron IPC — adding/removing channels, modifying main.ts ↔ preloa 204 ★
- Code Reviewer Quality — Use this agent as the second stage of a code review, after spec compliance is confirmed — evaluating code qual 186 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Delforge Solidity Security Auditor
Use for independent, adversarial security audits of Solidity smart contract projects — identifying vulnerabili
Docker Sandbox
Isolated autonomous scanning agent — runs in a temporary worktree with restricted Bash access. Requires ROE au
Finding Skeptic
Read-only adversarial verifier for audit findings. Given one finding and one skeptic lens, actively tries to r
Frontend Auditor
Read-only frontend audit agent that critiques UI quality, accessibility, responsiveness, and product-specific
Spec Edge Case Auditor
Use this agent when you need to audit test coverage against a specification to identify missing edge cases. Th
Correctness Reviewer
Reviews code changes for logic errors, race conditions, security vulnerabilities, and edge cases. Use when per
Related Skills
Edge Cases
Act as a rigorous senior Perl SDET. Write a comprehensive set of destructive, pathological, boundary-condition
Adversarial Test
Post-build adversarial review — a fresh agent stress-tests recent changes for bugs, regressions, conflicts, an
Vibe Check
Production resilience audit for AI-generated code. Catches edge cases, scale failures, and missing error handl