Generates comprehensive smoke and stress tests for infrastructure components (sandbox runtimes, container orchestration, firewall rules, etc.), prioritizing end-to-end realism that catches real setup issues across platforms. Activate when the user asks to "stress test", "smoke test", "test the sandbox", "verify…
How to find, confirm, and report a security vulnerability with an AI session — in this repo's own sandbox boundary, in a dependency, or upstream. Activate when the user asks to "find vulnerabilities", "look for a bypass", "attack the sandbox", "audit this for security bugs", "is this exploitable", "write up this…
How to write, change, or review tests in this repo — the load-bearing rule is test real behavior, not source text. Also covers non-vacuity (prove the test can fail: red-on-old → green-on-new), e2e tests that secretly stub the component they name, drift guards as a design smell to name rather than launder, SSOT…
AGENTS.md instructions for AlexanderMattTurner/agent-glovebox, a project described as: A minimal-friction secure experience that lets agents do their work. (beta).
Claude Code instructions for AlexanderMattTurner/agent-glovebox, covering claude.md, where the rest of the guidance lives, working style, writing and autonomy: do not stop to ask — run to completion.