Use before claiming work is done, before committing, before creating PRs, or before saying "it should work now." Enforces running verification commands and reading their output before making any completion claims. Evidence before assertions.
Record Architecture Decision Records (ADRs) when significant technical decisions are made. MUST trigger when switching, migrating, or replacing libraries, SDKs, frameworks, databases, or infrastructure. MUST trigger when making decisions that shape how the…
Use before starting any feature, entering unfamiliar code, or beginning a non-trivial task. Enforces understanding before action. No code, no scaffolding, no implementation until the problem is explored and a direction is approved. Use when: user says "let's…
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Enforces root cause investigation before fixing. No guessing, no shotgun debugging. Hard stop after 3 failed hypotheses. Use when: tests fail, errors appear, behavior…
Use when the user asks a research question, wants to explore a topic, compare options, or needs to investigate something before making a decision. Sets up a structured research folder with living documents and uses sub-agents for parallel exploration. Use…
Use when reviewing code for security vulnerabilities, before shipping to production, or when the user asks for a security audit. Runs OWASP Top 10 + STRIDE analysis with a strict false positive filter. Confidence gate at 8/10. No theoretical hand-waving.
Use when shipping, deploying, creating a PR, or preparing a release. Review staleness detection, gated review requirement with override options, and a structured release flow. Use when: user says "ship it", "create a PR", "let's deploy", "ready to merge", or…