Build production Node.js backends — Express/Fastify/Nest, the event loop, async/await correctness, streams, graceful shutdown, and not blocking the single thread. Use when writing a Node HTTP service, debugging "the server hangs / is slow under load", handling errors in async code, streaming large payloads, managing…
Production observability done right — structured logs, distributed traces, metrics, alerting, SLO/SLI. Use when adding logging to a new service, designing dashboards, choosing between OpenTelemetry / Datadog / Grafana stack, defining SLOs for a feature, writing alert rules, or untangling a noisy alert channel.…
Integrate payments and billing correctly — card charges, payment intents, webhooks, idempotent money movement, subscriptions/invoicing, refunds/chargebacks, multi-currency, and reconciliation against a ledger. Use when wiring Stripe/Adyen/Braintree/PayPal, handling a payment webhook, designing a subscription or…
Application performance for backend (Go+Fiber, Python+FastAPI), web frontends, and React Native mobile clients. Use when measuring or improving Web Vitals (LCP / INP / CLS), mobile FPS / TTI / memory, image/font/code-split optimization, profiling, or interpreting Lighthouse / Reanimated / Hermes / Flipper traces.…
Drive the pr-mode autonomous git loop for a consumer repo (COSGITWORKFLOW=pr). Use after cos pr submit to poll CI and act on the result. Triggers — "drive the PR", "CI is red", "is the PR merged", "retry the failing check", "pr-mode loop", any turn waiting on an agent PR's CI.
Build production realtime servers over WebSockets and Server-Sent Events — connection lifecycle, the heartbeat/ping-pong + idle-timeout contract, automatic reconnection with exponential backoff and resume tokens, backpressure and per-connection send queues, horizontal scale-out via a Redis/NATS pub-sub fan-out…
Use Redis correctly as a cache, queue, rate limiter, and ephemeral store — pick the right data structure, caching pattern, eviction policy, and atomicity model. Use when adding caching, designing a key schema, choosing cache-aside vs write-through, setting TTLs/eviction, building a rate limiter or queue, debugging low…
Design and operate full-text and vector search infrastructure — inverted-index engines (Elasticsearch/OpenSearch, Meilisearch, Typesense), analyzers and tokenization, relevance tuning (BM25, boosting, synonyms), faceting, and semantic/vector search (embeddings, ANN indexes, hybrid retrieval). Use when adding a search…
Use for ANY search, find, replace, or rename operation across a codebase — text literals, code symbols, semantic concepts, docs, or tasks. INVOKE BEFORE grep, before rename, before "find all X", before any cross-cutting edit. Enforces ground-truth counting before edits so nothing gets missed. Triggers — "find all"…