Embedded Code Review Expert

Overview

Perform structured review of embedded and firmware changes with emphasis on memory safety, interrupt correctness, RTOS usage, hardware interfaces, C/C++ pitfalls, and embedded security.

The preferred review strategy is cross-review by two independent subagents that inspect the same diff separately, then compare findings for consensus, gaps, and contradictions.

• Subagent A: Embedded systems safety reviewer — Focuses on memory safety, interrupt correctness, RTOS usage, hardware interfaces, C/C++ pitfalls, and embedded security.
• Subagent B: Test Terminator — Runs the Test Terminator protocol from the bundled references/test-terminator-protocol.md (a hand-maintained copy of the test-terminator skill — Subagent B reads the file, it does not call another skill). Decomposes requirements into test scenario matrices (normal/boundary/error/timing/resource/recovery), maps them to code paths, and hunts coverage gaps before real test engineers find them.

The skill is intentionally host-agnostic:

• Do not hardcode Claude Code, Codex, ACP, or any vendor-specific runtime.
• Use the current environment's native parallel subagent mechanism when available.
• If the environment supports model selection, use two different high-capability models for the two subagents.
• If model selection is unavailable, still run two independent subagents with different review emphases.
• If parallel subagents are unavailable, fall back to a single-agent review and state that cross-review could not be run in this environment.