Testing & Debugging for Claude Code

Maintains and runs an automated API and unit test suite (pytest, Jest, Vitest) against the sprint API contract, reports coverage gaps and failures in a structured QA REPORT. Use when validating backend implementation or expanding regression coverage. Trigger with "run QA tests", "validate API contract".

Code quality, testing, and validation enforcement specialist

Recover a Databricks Asset Bundle whose deploy fails with "unexpected EOF reading terraform.tfstate" — restore the guarded backup or switch to the direct engine.

Scan mapped GitHub repos for issue matches, recent commits, affected paths, and deploy changes. Use when gathering evidence for bug clusters after clustering step.

Run integration test suites with proper setup and teardown

> Run API load tests with k6, Artillery, or Gatling to measure performance...

Execute AI/ML task with intelligent automation

Scan codebase for security vulnerabilities

Quick security header check for a single URL

DESCRIPTION_PLACEHOLDER

Designs honest model evaluation frameworks — metric selection matched to business cost functions, statistical significance testing, calibration, and confusion analysis. Use when choosing eval metrics or comparing models. Trigger with \"design a model evaluation framework\", \"compare these models statistically\".

Use when the chain needs the codebase mapped — locating implementations, call sites, conventions, or affected surfaces — before analysis or implementation. The surface-mapping investigator.

> Comprehensive database security scanner with OWASP compliance checks,...

Performs OWASP Top 10 security assessments and generates security test cases covering SQL injection, XSS, IDOR, auth bypass, CSRF, and misconfiguration — producing severity-rated findings with proof-of-concept payloads and fix guidance. Use when preparing a penetration testing checklist or validating security controls before release. Trigger with \"security test scan\", \"OWASP vulnerability assessment\".

Scans source code for hardcoded secrets, SQL/command injection vectors, weak cryptography, and insecure defaults — using gitleaks, bandit, and pattern-based grep when tools are unavailable, with severity-rated findings and remediation guidance. Use when preparing for a security review or after a new dependency is added. Trigger with \"security scan\", \"find hardcoded secrets\".

Generate realistic test data and seed scripts

Set up API request logging

Set up Real User Monitoring

Set up synthetic monitoring for application

Set up distributed tracing

Classify an issue, finding, or vulnerability by severity level (S1-S4)

Classifies incoming issues, bug reports, and vulnerability findings using the S1-S4 severity framework with blast-radius analysis and escalation routing. Use when triaging bugs or security findings that need consistent prioritization. Trigger with "triage this issue", "classify severity".

Run quick smoke tests to verify critical functionality

> Manage snapshot tests with intelligent diff analysis and updates

Guide through SOP-003 Backup System Setup & Verification with pgBackRest

Analyze codebase for potential work and automatically create tasks

Start Sugar's autonomous execution mode

View Sugar system status, task queue, and execution metrics

View Claude's thinking logs for task execution

Analyze terraform plan output for risks and cost impact

Manual UI testing with Chrome browser - explore your app while errors are...

Simple test command for command parsing validation

Instruments LLM systems with tracing, span capture, cost attribution, and debugging tooling. Use when you need to add observability to AI pipelines, debug model behavior, or audit LLM cost attribution. Trigger with \"instrument my LLM calls\", \"debug my AI system with traces\".

Trace Unity Catalog's two-level access model for a user + error and return the exact missing group membership, grant, and who must run it.

Execute AI/ML task with intelligent automation

Track and run regression tests for existing functionality

Track and optimize response times

Track SLAs, SLIs, and SLOs