A toolkit for building applications on Powabase, a hosted backend that provides databases, user accounts, file storage, live updates, and AI features through one API.

Use it to build knowledge bases that search uploaded documents, AI agents with tools and sessions, and workflows triggered by webhooks or schedules. It can also support application data, authentication, storage, and realtime updates.

It gives you one place to connect common backend services instead of building and wiring them separately. It also covers document search, AI agents, and automated workflows.

powabase — Skill for Claude Code and Codex by powabase-ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add powabase-ai/agent-skills --skill powabase

Clone the repo

git clone --depth 1 https://github.com/powabase-ai/agent-skills

Made for: Claude Code, Codex.

Or install powabase, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/powabase-ai/agent-skills/powabase/github.svg)](https://agentmods.dev/skills/powabase-ai/agent-skills/powabase)

Your own site

<a href="https://agentmods.dev/skills/powabase-ai/agent-skills/powabase"><img src="https://agentmods.dev/badge/skills/powabase-ai/agent-skills/powabase/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/powabase-ai/agent-skills/powabase"><img src="https://agentmods.dev/badge/skills/powabase-ai/agent-skills/powabase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 210 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,662 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00210	$0.04662
Opus 5	$0.00105	$0.02331
Sonnet 5	$0.00042	$0.00932
Haiku 4.5	$0.00021	$0.00466

Measured 9d ago against content hash b1f8ff1db4dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

powabase scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

requests.get(f"{BASE_URL}/api/agents", headers=headers).json() # verify: 200 + {agents, total, ...}

skills/powabase/SKILL.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Powabase

Powabase is a multi-tenant AI Backend-as-a-Service. One REST API gives every project an isolated stack — Postgres + pgvector, an API gateway, auth, storage, realtime, and an AI worker — exposing three composable modules on top of a Supabase-style backend:

Module	What it is	Entry reference
Context Engineering (RAG)	Sources → extraction → Knowledge Bases → indexing → retrieval → reranking	rag-context-engineering.md
Agent Orchestration	ReAct agents with tools, sessions, streaming; multi-agent coordinators	agents-and-tools.md · orchestrations.md
Workflow Automation	DAG of blocks; webhook / scheduled triggers; NL Copilot	workflows-and-copilot.md
BaaS layer	PostgREST + RLS, GoTrue auth, Storage, Realtime, direct Postgres	baas-database-rls.md · baas-auth-storage-realtime.md

Use only the modules you need. A KB can attach to an agent; an agent can be a block in a workflow; a workflow can call a KB search — they compose.

Core principles

The /api/* surface is still evolving — verify against live docs. Don't trust this snapshot for exact request/response shapes. The docs at https://docs.powabase.ai are the contract; fetch the relevant page (Mintlify — you can append .md to a page path) before relying on a field you're unsure about. This skill flags known ambiguities inline.
Verify your work. After a change, make a real call (GET /api/agents, a KB search, a one-message run) and read the response. A fix without a confirming call is incomplete.
Recover, don't loop. If an approach fails 2–3 times, stop and reconsider — re-read the error, check the run record (see the debugging playbook), try a different method. The agent itself fails a run if it calls the same tool with the same args 3× in a row ("doom loop").
Two headers or 401. Every /api/*, /rest/v1/*, /auth/v1/*, /storage/v1/* request needs both apikey and Authorization: Bearer. Sending one is the #1 cause of 401s.
Security is not the default — make it explicit. See the security box below.
Hand off to the human for Studio-only setup. Credentials, BYOK provider keys, and tool API keys live behind the Studio UI. Don't guess them — ask, and point the user to the exact place. See studio-setup-and-human-handoff.md.

Read the full file on GitHub · 258 lines

Files

What ships with it

13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 258 lines · 210 tokens per session scan A b1f8ff1db4dc

Subscribe to this mod's changes

powabase is a skill published in the GitHub repository powabase-ai/agent-skills (9 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 210 tokens to every session and 4,662 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs Claude Code Data and AI RAG and vectors agent-skills agents ai baas cursor

azure-search-documents-dotnet

Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET"…

microsoft/skills · 102 tokens

azure-search-documents-ts

Build search applications using Azure AI Search SDK for JavaScript (@azure/search-documents). Use when creating/managing indexes, implementing vector/hybrid search, semantic ranking, or building agentic retrieval with knowledge bases.

microsoft/skills · 48 tokens

astra-vector-backend

Design Astra DB Data API and vector-search backends for retrieval, metadata filtering, and LangChain-compatible stores.

erichare/skillroute · 27 tokens

pn-rag-evaluation

Evaluate retrieval-augmented generation pipelines — golden sets, automated metrics (incl. RAGAS-style), human rubrics, regression gates in CI. Use when building or changing RAG (chunks, embeddings, rerankers, prompts) and need quality proof, not vibes.

perniemann/pnCore · 62 tokens

gemini-api

Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia…

aboalrejal-ai/skills · 80 tokens

architecture-patterns

Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use this skill when designing clean architecture for a new microservice, when refactoring a monolith to use bounded contexts, when implementing hexagonal or onion architecture patterns, or…

wshobson/agents · 65 tokens

powabase