By riwaht
Bug-bash plugin: mission brief, intensity modes, risk triage, evidence bars, API/UI subagents—test the running system first, code second; find and reproduce, not fix unless asked.
Deep bug bash—broader negatives, more concurrency/soak where safe, mandatory residual-risk section
Short smoke bug bash—primary paths and a few negative checks only
Load **`bugbash-core`** with the **Skill** tool and run a bug bash for this project.
Use when you want a subagent focused on HTTP/GraphQL/gRPC-style surfaces, CLIs that behave like APIs, webhooks, and contract boundaries—not primary browser UX. Examples: "Hammer the REST checkout endpoints with bad auth and race conditions" or "Negative test the webhook receiver and idempotency keys."
Generalist bug-bash subagent for mixed surfaces when you want one agent to explore APIs, UI, and CLI in scope together—charter is reproduce and report, not fix. Use when splitting api vs ui is not worth it (small feature, tight scope). Examples: user wants one agent to "walk the whole onboarding funnel including API and web" in a single pass.
Use when you want a subagent focused on browser or native UI flows, navigation, forms, and client-visible state—not deep API contract matrices. Examples: "Break the multi-step wizard" or "Double-submit and back-button every form in the settings area."
Core bug-bash workflow with mission brief, intensity modes, risk triage, evidence bars, and structured outputs—running system first, code second; find and reproduce, do not fix unless asked.
Use when the user wants to find bugs, stress-test, QA, exploratory-test, or verify behavior by exercising the running system—not for routine implementation, refactors, or fix-focused debugging unless they ask to switch modes after findings exist.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugin for bug bashing: exercise the running product first, use code second to triage. Charter: find and reproduce with evidence, not to own fixes unless you ask.
/plugin marketplace add riwaht/claude-bugbash
/plugin install bugbash@claude-bugbash
| Command | Role |
|---|---|
/bug-bash | Main entry; optional [quick|standard|deep] then scope. |
/bug-bash-quick | quick intensity shortcut. |
/bug-bash-deep | deep intensity shortcut. |
| Skill | Role |
|---|---|
using-bugbash | When Bugbash applies; philosophy; how to split subagents. |
bugbash-core | Mission brief, intensity, risk triage, phases, evidence bar, flaky table, coverage summary, JSON export. |
| Agent | Role |
|---|---|
bugbash-hunter | Generalist for mixed API + UI in a small scope. |
bugbash-api | Contracts, auth, idempotency, concurrency on machine-facing surfaces. |
bugbash-ui | Flows, forms, navigation, client-visible state; light a11y smoke only. |
Add to CLAUDE.md if you want Bugbash considered whenever you talk like QA—not for every coding message:
When I ask for QA, stress testing, or a bug bash, use the Bugbash plugin skills; stay in find-and-reproduce mode until I ask for fixes.
MIT — see license.txt.
See PRIVACY.md for how this project handles data (high level: no maintainer-operated analytics; third parties like your Claude provider and git host have their own policies).
npx claudepluginhub riwaht/claude-bugbash --plugin bugbashTesting workflow skill for high-value test discovery, strategy selection, focused implementation, realistic workload generation, strict review, and suite health diagnostics.
10 coordinated QA agents for Claude Code: chains diff analysis, AC compliance, test scenarios, browser validation, bug reports, and automation code generation.
Systematically debug issues with step-by-step troubleshooting approaches.
AI 測試大師 — v1.1 QA testing skill backed by an MCP server. 22 tools (21 v1.0-frozen + analyze_stream): run / generate / debug / harden software tests via mk-qa-master. Includes the AI Visual Challenge Solver (reCAPTCHA / hCaptcha), OWASP API Security Top 10 scanner, universal qa_plan + verify bookend across 5 core tools, and the v1.1 Edge AI Runner (RTSP + YOLO via the [edge] extras). Same skill folder loads in Claude Code, Codex, OpenClaw, and Hermes.
QA skills for functional-testing domain.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development