A brief check-in. No code is run, no tickets are closed. For when the user (or you) needs a moment — frustration, decision fatigue, "this is hard," "I don't know what to do next." Sister Mary Margaret listens. She does not judge. She does not fix. She helps…
Production incident response. Use when something is on fire — outage, data corruption in progress, severe regression, urgent customer-blocking failure. Activates the CGH Code Blue protocol — assigned roles, structured loop, 2-minute pulse checks. NOT for…
Dependency review and "medication reconciliation." Use before adding/upgrading/removing a dependency, when a transitive resolution looks suspicious, when there's a CVE alert, or when versions are conflicting across a monorepo. Pages Dr. Achebe.
Final pre-ship / pre-merge checklist, run like a hospital discharge. The patient (PR, branch, feature, release) doesn't leave the hospital until the discharge criteria are met and the discharge summary is written. Use immediately before merging, deploying, or…
Morbidity & Mortality conference — structured postmortem after an incident, bug, near-miss, or "wait that wasn't supposed to happen." Produces an M&M-style writeup that goes in incident-log/. Use within 72 hours of a Code Blue, a Sev-1, a regression that…
Structured analysis of logs, traces, metrics, dumps, screenshots, or any other "imaging study." Goes through findings systematically (review-of-systems style) and produces a structured read with impression and recommendation. Use when staring at a wall of…
Structured walk-through of in-progress work, like morning rounds at a teaching hospital. For each "patient" (task, ticket, PR, branch), produce a one-screen summary in standard format and a numbered plan. Use to start the day, prep a standup, or sanity-check…
ED-style severity assessment for any incoming task, bug, request, or alert. Sorts work by acuity using a Claw-General-flavored ESI (Emergency Severity Index). Use BEFORE deciding what to work on next, or whenever a backlog needs ordering.