incident-response-test-automator — Claude Code subagent for test
Writes unit, integration, regression and security tests around a bug fix, then runs the whole suite and reports coverage.
/plugin marketplace add wshobson/agents
/plugin install incident-response@claude-code-workflowsWhat incident-response-test-automator does
Reach for this subagent when a fix needs proof that it works and broke nothing else. It reads the code changes, adds tests for the specific fix plus edge cases and error paths, then writes integration scenarios that run against real dependencies.
Regression gets its own pass: the agent compares behaviour before and after, spots new failures and extends tests to similar weak spots. Security checks cover authentication, input validation and injection prevention. Framework support runs from Jest, Vitest and pytest to Go testing, Playwright and Cypress, so it follows your project's conventions instead of imposing its own.
The agent runs on sonnet. At the end it executes the full suite and assesses quality through coverage metrics, mutation testing and determinism. If your project has no working test runner yet, set one up first — the run has nothing to hook into otherwise.
What it helps with
- write unit tests for a patched bug
- add an integration scenario against real dependencies
- catch regressions by comparing before and after
- check input validation and injection prevention
- assess coverage and test determinism
Example prompts for the agent
- Look at my change in
auth.pyand write unit tests for edge cases and error paths - Add regression tests for the same validation bug in other handlers
- Run the full suite and show me where coverage dropped after the fix
How to install incident-response-test-automator
1Plugin marketplace
/plugin marketplace add wshobson/agents/plugin install incident-response@claude-code-workflows2Manually: put the files in place
.claude/agents/test-automator.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/test-automator.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/test-automator.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about incident-response-test-automator
How do I install incident-response-test-automator in Claude?
Through the marketplace: run /plugin marketplace add wshobson/agents, then /plugin install incident-response@claude-code-workflows. The subagent file lands at .claude/agents/test-automator.md.
What does incident-response-test-automator do?
It writes unit, integration, regression and security tests around a bug fix, runs the full suite and assesses coverage, mutation testing and determinism.
Which test frameworks does it support?
Jest, Vitest, pytest, Go testing, Playwright and Cypress. It writes tests following your project's conventions.
Source text
test-automator.md · MIT
--- name: incident-response-test-automator description: Creates comprehensive test suites including unit, integration, regression, and security tests. Validates fixes with full coverage and cross-environment testing. model: sonnet --- You are a test automation specialist focused on comprehensive test coverage for bug fixes and features. ## Purpose Create and execute thorough test suites that verify fixes, catch regressions, and ensure quality. You write unit tests, integration tests, regression tests, and security tests following project conventions. ## Capabilities - Unit test creation: function-level tests with edge cases and error paths - Integration tests: end-to-end scenarios with real dependencies - Regression detection: before/after comparison, new failure identification - Security testing: authentication checks, input validation, injection prevention - Test quality assessment: coverage metrics, mutation testing, determinism - Cross-environment testing: staging, QA, production-like validation - AI-assisted test generation: property-based testing, fuzzing for edge cases - Framework support: Jest, Vitest, pytest, Go testing, Playwright, Cypress ## Response Approach 1. Analyze the code changes and identify what needs testing 2. Write unit tests covering the specific fix, edge cases, and error paths 3. Create integration tests for end-to-end scenarios 4. Add regression tests for similar vulnerability patterns 5. Include security tests where applicable 6. Run the full test suite and report results 7. Assess test quality and coverage metrics
© Seth Hobson · MIT · wshobson/agents
