constructive-io

Build interactive CLI tools with the Constructive CLI SDK. Use when asked to "create a CLI", "build a command-line tool", "add CLI prompts", "create interactive prompts", "store CLI config", "add terminal colors", or when building any CLI application in a Constructive project. This package provides runtime utilities for type coercion, config management, display formatting, and command handler patterns used by generated and custom CLIs.

The _meta schema-introspection plugin for PostGraphile v5 (MetaSchemaPlugin / MetaSchemaPreset in graphile-settings). Exposes a single _meta root query describing every table's fields, indexes, constraints, relations, inflection names, root query/mutation names, and smart-tag-derived metadata (storage, search, i18n, realtime). Use when asked to "expose database metadata in GraphQL", "add a field to _meta", "understand the _meta query", "drive codegen from _meta", or when adding a new smart-tag-detected metadata builder to the meta-schema plugin.

CLI tool (csdk) for the api API — provides CRUD commands for 47 tables and 9 custom operations

CLI tool (csdk) for the auth API — provides CRUD commands for 13 tables and 35 custom operations

CLI tool (csdk) for the compute API — provides CRUD commands for 65 tables and 29 custom operations

CLI tool (csdk) for the config API — provides CRUD commands for 5 tables and 13 custom operations

CLI tool (csdk) for the infra API — provides CRUD commands for 10 tables and 4 custom operations

CLI tool (csdk) for the modules API — provides CRUD commands for 68 tables and 12 custom operations

Declarative schema definition — blueprints, node type registry, presets, and the blueprint definition format. Use when asked to 'create a blueprint', 'blueprint template', 'construct blueprint', 'copy template', 'blueprint definition', 'definition hash', 'table hashes', 'schema marketplace', 'blueprint provisioning', 'module presets', 'what modules should I install', 'auth:email preset', 'b2b preset', or when working with blueprint JSONB definitions.

Feature catalog for Constructive apps — one scannable index of every capability (auth methods, authorization, multi-tenancy, data modeling, storage, search, AI, GraphQL, ops) with pointers to the authoritative skill or toggle that owns it. Use when asked "what can a Constructive app do", "what features are available", "which skill covers X", "is there built-in support for Y", "how do I enable read-only mode / magic links / passkeys / SSO / pgvector / search / uploads", or when orienting to the platform for the first time.

Authorization — Safegres protocol, 23 Authz* policy types, RLS, grants, permissions, permission defaults, GuardStepUp, read-only access, storage policies, and the secureTableProvision workflow. Use when asked to 'add security', 'RLS', 'grants', 'policies', 'Safegres', 'Authz*', 'AuthzEntityMembership', 'AuthzDirectOwner', 'AuthzMemberOwner', 'AuthzComposite', 'AuthzSystemOnly', 'AuthzHumanOnly', 'AuthzValueAllowed', 'AuthzValueExists', 'AuthzValueMatch', 'system-only policy', 'system-only writes', 'human-only mutation', 'block agents from writing', 'read-only mode', 'secure table provision', 'storage policies', 'bucket security', 'permission model', 'permission defaults', 'default_permissions', 'GuardStepUp', 'step-up auth', 'guard step-up', 'require step-up', 'MFA guard', 'named permissions', or when working with authorization in blueprints or the ORM.

Build a Constructive app end-to-end from a brief. Use when asked to build/scaffold an app on Constructive, create a CRUD app, provision a data model with RLS, wire Blocks + auth flows, or verify an app with Chrome QA / agent-browser — keep time-to-app under 10 minutes on a warm hub. Drives the four mainline phases (1 Backend Up, 2 Data Model Provisioned, 3 Frontend + SDK, 4 UI / Blocks) and supports the three policy tiers: owner-scoped, public-read + owner-write, and b2b org-membership. Triggers: "build a Constructive app", "scaffold an app on Constructive", "provision a data model with RLS", "wire Blocks and auth flows", "verify the app with agent-browser". Builds ANY CRUD app generically from a brief — it is NOT for editing the Constructive platform itself (constructive / constructive-db).

AI — agent module, LLM providers, RAG pipelines, embeddings, agentic-kit multi-provider client, Search* blueprint nodes (SearchUnified, SearchVector), ProcessFileEmbedding/ProcessImageEmbedding/ProcessChunks. Use when asked to 'add AI search', 'build RAG pipeline', 'embedding worker', 'agentic-kit', 'LLM integration', 'Ollama', 'Anthropic', 'OpenAI', 'file embedding', 'image embedding', 'chunking', 'SearchUnified', 'SearchVector', 'multiplayer agents', 'shared agents', 'multi-agent', 'agent_id', or when working with AI features in blueprints.

Identity, login, sessions, MFA, devices, identity linking — auth flow (sign-up/sign-in/JWT), auth settings (MFA, anonymous sessions, CAPTCHA, cookie auth, rate limits), device settings (tracking, trusted devices, approval gate), identity linking (link_identity, account collision resolution, allow_link_by_email, primary auth method), and service-level auth config. Use when asked to 'sign up', 'sign in', 'auth flow', 'MFA', 'magic link', 'passkeys', 'device approval', 'trusted devices', 'session management', 'cookie auth', 'anonymous sessions', 'CAPTCHA', 'rate limits', 'bootstrap user', 'JWT', 'link identity', 'identity linking', 'account collision', 'allow_link_by_email', 'primary auth method', 'connected accounts', or when working with authentication.

Principals — scoped sub-identities for API keys and agents. A principal is a delegated identity owned by a human (or org) that authenticates via an API key and operates with a subset of its parent's permissions. Use when asked to 'create an API key', 'issue an agent credential', 'scope an agent to an org', 'read-only API key', 'revoke an API key', 'create a principal', 'org API key', 'service account', 'machine identity', 'agent identity', 'bypass step-up for a bot', 'principalEntity', 'principalScopeOverride', or when managing agent/API-key identities via the SDK ORM.

Subscriptions, notifications, change_log, CursorTracker, ephemeral realtime — real-time data via GraphQL subscriptions, PostGraphile live queries, change tracking, and ephemeral pg_notify delivery. Use when asked to 'add subscriptions', 'real-time updates', 'live queries', 'notifications', 'change_log', 'CursorTracker', 'websocket', 'ephemeral realtime', 'pg_notify', 'high-frequency signals', or when working with real-time features in Constructive.

Control PostGraphile v5 schema generation with the behavior system. Use when asked to "disable mutations", "hide fields", "control what gets generated", "disable unique lookups", "make features opt-in", or when you need fine-grained control over the GraphQL schema.

Configure connection filtering in PostGraphile v5. Use when asked to "add filtering", "configure filters", "filter by column", "disable relation filters", "enable all column filters", or when setting up the connection filter plugin.

Debug PostGraphile v5 schema generation issues. Use when asked to "debug schema", "why is this field generated", "log inflector calls", "detect naming conflicts", "understand schema generation", or when troubleshooting PostGraphile v5 issues.

Customize GraphQL naming and inflection in PostGraphile v5. Use when asked to "customize naming", "change field names", "simplify relation names", "remove schema prefix", "fix pluralization", or when GraphQL names don't match your conventions.

Configure PostGraphile v5 default plugins and features. Use when asked to "configure default plugins", "customize base schema", "keep id as id", "configure Node/Relay features", or when setting up PostGraphile v5 for your specific needs.

Create custom PostGraphile v5 plugins using hooks. Use when asked to "create a plugin", "add custom field", "extend schema", "detect conflicts", "add metadata query", or when you need to extend PostGraphile's functionality.

Create and compose PostGraphile v5 presets. Use when asked to "create a preset", "configure PostGraphile", "combine presets", "disable plugins", or when setting up a new PostGraphile v5 server.

CLI tool (agentic-db) for the default API — provides CRUD commands for 95 tables and 3 custom operations

ORM client for the default API — provides typed CRUD operations for 95 tables and 3 custom operations

ORM client for the default API — typed CRUD, vector + hybrid search, and relation walking for the 91 generated tables.

CLI tool (agentic-db) for the default API — typed CRUD, unified search, and context/config commands for the 91 generated tables.

Install and deploy the agentic-db PostgreSQL module using pgpm. Use when asked to 'install agentic-db', 'deploy the database', 'set up agentic-db', 'create a workspace', or when bootstrapping a new project that depends on agentic-db.

Unified GraphQL skill for Constructive — code generation (React Query hooks, Prisma-like ORM, CLI), runtime query generation, search (tsvector, BM25, trgm, pgvector, PostGIS, unified composite), pagination, and documentation generation. Use when asked to generate hooks, ORM, CLI, query data, add search, paginate results, or work with @constructive-io/graphql-codegen or @constructive-io/graphql-query.

All PostgreSQL and database testing frameworks — pgsql-test (RLS, seeding, snapshots, JWT context, scenario setup), drizzle-orm-test (type-safe Drizzle testing), supabase-test (Supabase RLS testing), drizzle-orm (schema patterns), and pgsql-parser testing. Use when writing database tests, testing RLS policies, seeding test data, or testing with any Constructive test framework.

Developer tools — pnpm workspace management (monorepo configuration, publishing, dependency management), inquirerer CLI framework (interactive prompts, appStash, yanse colors), and README formatting conventions. Use when configuring pnpm workspaces, building CLIs with inquirerer, or formatting documentation.

PostgreSQL Package Manager — deterministic, plan-driven database migrations with dependency management. Use when asked to "deploy database", "run migrations", "manage pgpm modules", "add a table", "create a function", "add a migration", "write database changes", "create a workspace", "set up pgpm", "manage dependencies", "revert a migration", "verify deployments", "tag a release", "start postgres", "run database locally", "set up database environment", "load env vars", "add an extension", "install a module", "publish pgpm module", "test database", "write integration tests", "troubleshoot pgpm", or when working with PostgreSQL package management, .control files, pgpm.plan, or SQL migration scripts.

Test wavegrid command-mode fixes end-to-end. Covers unit tests, adversarial fix verification, WebSocket integration tests, and build/lint checks. Use when verifying receiver or server command-mode changes.

How to write and send dynamic JavaScript patterns to wavegrid receivers via the evalPattern command. Covers the pattern ABI, ctx API, safety limits, wire format, and interaction with existing controls. Use when building or debugging JS patterns for the wavegrid laser system.

Developer utilities monorepo — inquirerer (interactive CLI prompts), yanse (terminal colors), appStash (state persistence), inflekt (string inflection), strfy-js (JSON stringify), clean-ansi, and 25+ other packages. Use when building CLIs with inquirerer, working with terminal colors, string inflection, or any package in the dev-utils repo.

Reference for the makage CLI tool — build helper, asset management, workspace updates, and cross-repo dependency synchronization. Use when asked about makage commands, monorepo builds, update-deps, or cross-repo dependency workflows.