Use when fanning out subagents over a corpus (pages, traces, logs, documents) to produce findings that must cite evidence — links, quotes, ids, line numbers. Packages the integrity discipline that keeps agent citations real - freeze the corpus locally,…
Use when a shared multi-user Linux box keeps freezing or going unresponsive from out-of-memory (OOM) events, when one user's process is eating all the RAM, or when someone needs to cap memory so the machine stays usable without starving legitimate work.…
Use when fetching or analyzing StackOverflow / Stack Exchange content (questions, answers, comments, vote scores) for a dataset, audit, or research pipeline. Direct page access is blocked from Matthew's machines (WebFetch refuses the domain; curl gets…
Use when writing, reviewing, or auditing code that calls OpenRouter (or a similar multi-provider router like Requesty / Vercel AI Gateway / a LiteLLM proxy) to produce RESEARCH results — evals, LLM-as-judge scoring, agent rollouts, benchmark numbers, or…
Use when someone is about to lose access to a machine (shared server, lab box, cloud/VM instance, expiring rental) and needs to preserve all their work before it's gone. Systematically finds everything that exists ONLY on that machine — unpushed commits,…
Use when preparing a paper's camera-ready or arXiv release — de-anonymizing an accepted submission, packaging an arXiv tarball, checking dual-submission safety against a concurrent venue (e.g. a paper accepted at a workshop that's also under review at…
Spin up one or more fresh-context subagents to critically evaluate a proposed theory, hypothesis, interpretation, or experimental design before committing to it. Use when the user says "have an agent critique this" / "get a second opinion on" / "is this…
Use when launching a multi-hour neural-network training, fine-tune, or other long GPU job autonomously from Claude Code and you need to catch failures (NaN, stuck-at-chance, dead process, throughput collapse, OOM) early instead of waking up to a wasted GPU…