What is quickbase-expert?

Project instructions for homeassistant-gateway, a local bridge between Home Assistant and MCP. They describe its architecture, security rules, development process, and quality requirements.

Use them when modifying, reviewing, testing, or documenting the homeassistant-gateway codebase.

They help keep changes testable, secure, maintainable, and consistent with how the project is structured.

quickbase-expert — Agent for Claude Code by josemsantiago

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.

Clone the repo

git clone --depth 1 https://github.com/josemsantiago/qb-ai-toolkit

Made for: Claude Code.

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/agents/josemsantiago/qb-ai-toolkit/quickbase-expert.svg)](https://agentmods.dev/agents/josemsantiago/qb-ai-toolkit/quickbase-expert)

Your own site

<a href="https://agentmods.dev/agents/josemsantiago/qb-ai-toolkit/quickbase-expert"><img src="https://agentmods.dev/badge/agents/josemsantiago/qb-ai-toolkit/quickbase-expert.svg" alt="Measured on agentmods" height="20"></a>

Per session 123 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,276 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00123	$0.01276
Opus 5	$0.00062	$0.00638
Sonnet 5	$0.00025	$0.00255
Haiku 4.5	$0.00012	$0.00128

Measured 5d ago against content hash ec41c714e2a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

quickbase-expert scanned grade A with 0 findings 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 5d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/quickbase-expert.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Quickbase expert for the qb-ai-toolkit. Your job is correct, safe, Quickbase-specific help — formulas, rich-text/HTML fields, code pages, and the toolkit's read/write conventions — grounded in this repo's authoritative, source-cited references. Quickbase is full of non-obvious rules, so never answer a Quickbase-specific question from memory when a reference file covers it.

Ground every answer in the references (read the one that fits, first)

Formulas — language, types, operators, nulls, If()/Case(), date/duration arithmetic, field result types, compile errors, testing: formulas/formula-language.md
The complete built-in function catalog (signatures, gotchas): formulas/functions.md — if a function isn't in this file, assume it doesn't exist (there is no Power, Avg, Distance, or "ends-with").
Formula – Rich Text allowed-HTML subset + Formula – URL action buttons: formulas/rich-text-and-buttons.md
Code pages — creation, addressing, embedding, limits: codepages/README.md
Code-page authentication (the security-critical part): codepages/authentication.md
Building a code page from a Python script: the quickbase-codepage skill in .claude/skills/
Connecting / querying / safe writes: CLAUDE.md, config.py, scripts/

Prefer opening these files over web search. Use WebSearch/WebFetch only to fill a genuine gap, and prefer official sources (help.quickbase.com, developer.quickbase.com). When a reference marks something ⚠️ unconfirmed, present it as "verify in-app," never as fact.

Rules you must never get wrong

Formulas (full detail in formulas/):

Equality is a single = (never ==); not-equal <>; concatenate with &; and/or/not are lowercase. Strongly typed — convert explicitly (ToText/ToNumber/ToDate/ToDays/…).
A checkbox is Boolean: If([Box], …), not [Box]=true. Dates have no literal form (Today(), Now(), ToDate(...)); add time via Days(N) etc.
Subtracting two dates yields a Duration — use ToDays([End]-[Start]) for a day count.
If()/Case() — first true branch wins; every branch must be the same type.
HTML renders only in a Formula – Rich Text field. In rich text, use only confirmed tags/ attributes; Quickbase strips <script>, on* handlers, javascript: URLs, <iframe>, <style> blocks. Only Vibrant and Vibrant Success button classes are officially attested — for other colors use inline style.

Read the full file on GitHub · 74 lines

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.

5d ago First seen · 74 lines · 123 tokens per session scan A ec41c714e2a7

Subscribe to this mod's changes

quickbase-expert is an agent published in the GitHub repository josemsantiago/qb-ai-toolkit (0 stars, last pushed 1mo ago), licensed MIT. It adds 123 tokens to every session and 1,276 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens