Mechanical recipes for reading agent memory and running the learning loop (cross-session patterns, decisions, failure modes) via the cossearch / cosdetails / costimeline / coslearn tool family, plus how observation capture actually works (automatic, edit-derived). Use when recalling a past pattern in a new session…
Design HTTP / REST / GraphQL API contracts that survive multiple consumers and years of evolution. Use when defining a new endpoint, reviewing an OpenAPI spec, evolving a public API, debating REST vs GraphQL, deciding versioning strategy, designing pagination or idempotency keys, or shaping error envelopes. Paired…
Design authentication and authorization for the project's stack — JWT vs server sessions, refresh-token rotation, OAuth 2.1 + PKCE, magic links, passkeys (WebAuthn), TOTP/2FA + backup codes, RBAC vs ABAC vs ReBAC, secure cookie flags, mobile token storage. Use when adding sign-in to a new app, designing the token…
Stack-agnostic backend patterns. Use when writing or modifying any server-side code (HTTP handler, DB query, background job, auth/middleware, webhook) regardless of language or framework. Covers services/selectors split, idempotency, error envelopes, migration discipline, N+1 avoidance, scale-aware design, auth…
Universal coding principles applied on every code change — fail-closed error handling, self-documenting code, edge-case awareness, and test coverage for error paths. Stack-agnostic; covers Python, TypeScript/JavaScript, Go, and any other language. Triggers on every commit that touches code files.
Conceptual code-reading for unfamiliar areas — trace a feature, follow a data flow, understand a domain. Use when the question is conceptual ("how does auth work?", "what happens when a user buys X?"); for symbol-precise queries (callers, blast radius, rename) use graph-explorer instead. The two are complementary …
Design and evolve PostgreSQL schemas that survive scale and refactors. Use when modeling a new domain, choosing between normalization and denormalization, designing indexes for known query patterns, writing migrations safely, picking ORM-vs-raw-SQL trade-offs, deciding on soft delete vs hard delete, or evaluating…
Production-ready CI/CD pipelines, container images, and release patterns. Use when designing a CI pipeline, writing Dockerfiles, choosing between blue-green / canary / rolling, setting up semantic versioning, defining a rollback playbook, or migrating from manual deploys to GitOps. Stack-agnostic; recipes target…
Build small, secure, reproducible container images and compose stacks. Use when writing or reviewing a Dockerfile, debugging a bloated/slow image build, setting up docker-compose for local dev, adding a healthcheck, handling build secrets, or hardening a container (non-root, minimal base). Triggers — "Dockerfile"…
Write reliable end-to-end tests that exercise real user journeys — Playwright for web, Maestro for mobile — without the flakiness that makes teams ignore them. Use when adding an end-to-end test, debugging a flaky test, choosing what to cover end-to-end vs unit/integration, setting up CI for browser/device tests, or…
Create distinctive, production-grade visual interfaces — design principles that apply to ANY frontend (React, Next.js, Vue, Svelte, plain HTML/CSS, React Native). Use when the aesthetic direction matters — building a component, page, landing site, or app where it must look intentional, not generic "AI slop". Covers…
Stack-agnostic frontend patterns. Use when writing or modifying any UI code (React, React Native, Vue, Svelte) regardless of framework. Covers three-state async UI, loading/error/empty handling, client vs server components, hydration safety, accessibility, performance, SEO basics, and state management patterns.
Navigate the graphos knowledge graph before editing load-bearing code. Use when tracing dependencies, planning a rename, auditing API surface, or answering "what breaks if I change this?". Pairs with codebase-explorer — graph-explorer wins for symbol-precise queries, codebase-explorer wins for conceptual code-reading.
Build and operate production GraphQL servers — schema-first SDL design, resolver architecture, the N+1 problem and DataLoader batching, pagination (Relay cursor connections), error handling, schema federation/stitching, persisted queries, and depth/complexity/cost limiting. Use when authoring a GraphQL schema or…
Build and operate gRPC services and the service-to-service mesh — Protobuf schema design with wire-compatible evolution, the four RPC kinds (unary, server/client/bidi streaming), deadline propagation, retries and hedging, status-code semantics, interceptors for auth/tracing/metrics, mTLS, load balancing (client-side…
Design and refactor systems using Ports & Adapters (Hexagonal Architecture). Use when starting a new service, untangling framework-coupled business logic, supporting multiple delivery mechanisms (HTTP + queue + CLI), swapping infrastructure (Postgres → Mongo, REST → gRPC) without touching domain code, or planning…
Strip AI writing tells from prose a human will read outside the repo — README, release notes, launch announcements, blog posts, community and forum posts, PR bodies, landing copy. Use before publishing any text to an audience that did not ask for a document. Catches inflated claims, sales language, forced triads…
Internationalize and localize software — externalized message catalogs, ICU MessageFormat for plurals/gender/select, locale-aware formatting of dates/numbers/currency, RTL/bidi layout, Unicode correctness, content negotiation, and the translation pipeline. Use when extracting hardcoded UI strings, choosing an i18n…
Production incident handling — severity classification, runbook execution, communication, postmortem. Use when something is on fire (CHAOTIC quadrant), when designing a runbook before launch, after an incident to drive the postmortem, or to define the SEV scale + on-call rotation. Pairs with observability (alerts →…
Operate and harden Linux hosts — SSH, systemd services, users/permissions, package management, networking, firewall, log triage, and resource inspection. Use when configuring a server, writing a systemd unit, hardening SSH, debugging "the box is slow / a port won't bind / a service won't start", setting up a firewall…
Design production async messaging — queues, brokers, pub/sub, event streams, and the delivery-guarantee math behind them. Use when introducing a message broker (RabbitMQ / Kafka / SQS / NATS / Redis Streams), choosing queue vs log vs pub/sub, designing idempotent consumers, sizing retries and dead-letter queues…