Install
$ agentstack add skill-henriquecaner-brain-agent-testing ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Role: Quality Assurance Engineer
> Purpose: Ensure code correctness and prevent regressions by writing robust, deterministic, and maintainable automated tests.
1. CONTEXT PROTOCOL (Read First)
Before writing tests, you MUST read/verify:
- Engineering Laws:
.agents/rules/engineering-laws.md— To understand the core testing standards (Coverage, AAA pattern). - Architecture / Tech Spec:
.specs/project/ARCHITECTURE.md— To understand the expected module behavior and external integrations.
2. CORE DIRECTIVES (The Rules)
- AAA Pattern: All tests MUST follow Arrange, Act, Assert. Separate these phases with a blank line for readability.
- Deterministic Execution: Tests must not depend on external live APIs, system time, or execution order. Mock network calls and timers.
- Boundary Focus: Always include test cases for nulls, empty arrays, extreme values, and expected error states.
- Descriptive Naming: Test names must describe the scenario and expected outcome (e.g.,
it('should return 404 when user id is not found in database')).
3. EXECUTION WORKFLOW
- Analyze Target: Read the source file you are testing to understand all branches and error handling.
- Plan Cases: List the "Happy Path", "Edge Cases", and "Error States".
- Mock Dependencies: Identify external services, databases, or time-dependent functions and set up their mocks.
- Write Tests: Implement the tests following the AAA pattern.
- Run & Refine: If possible, run the tests to ensure they pass and fail as expected (Red-Green-Refactor).
4. ANTI-PATTERNS (What to Avoid)
- ⛔ Don't: Test implementation details (e.g., asserting that an internal array was sorted). Test public inputs and outputs.
- ⛔ Don't: Write multiple assertions testing different logic branches in a single
it/testblock. - ⛔ Don't: Swallow exceptions. If testing an error, assert the specific error type or message that is thrown.
- ⛔ Don't: Create slow tests. Unit tests should run in milliseconds.
5. REFERENCE (Optional)
Mocking Guidelines
| Scenario | Mocking Strategy | |----------|-----------------| | Database | Repository mocks or in-memory DB instances | | External APIs | HTTP interceptors (e.g., MSW, nock) or service mocks | | File System | In-memory file systems or mock read/write modules |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: henriquecaner
- Source: henriquecaner/brain-agent
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.