qb-ai-toolkit: Instructions file for Claude Code

CLAUDE.md

qb-ai-toolkit CLAUDE.md is an instructions file for Claude Code from josemsantiago/qb-ai-toolkit. It costs 1,561 tokens per session, scanned A, original, MIT.

Project instructions for a Python toolkit that safely works with Quickbase, an online database and business-app platform. They explain its read-only MCP server, its wrapper for changes, and how to discover apps, tables, and fields.

In plain words
What is it for?
Use them when querying, exporting, drafting formulas, or making controlled bulk updates in Quickbase through this toolkit.
Why use it?
They prevent unsafe or incorrect Quickbase access, such as using the wrong field identifiers or putting write operations through the read-only interface.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is josemsantiago/qb-ai-toolkit's own configuration. It tells Claude Code how to work on qb-ai-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything qb-ai-toolkit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to josemsantiago/qb-ai-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/josemsantiago/qb-ai-toolkit/main/CLAUDE.md
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.

agentmods badge for qb-ai-toolkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/josemsantiago/qb-ai-toolkit/claude-md/github.svg)](https://agentmods.dev/instructions/josemsantiago/qb-ai-toolkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/josemsantiago/qb-ai-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/josemsantiago/qb-ai-toolkit/claude-md/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.

agentmods 80×15 button for qb-ai-toolkit CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/josemsantiago/qb-ai-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/josemsantiago/qb-ai-toolkit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,561 This file is loaded in full into every session.
When invoked 1,561 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01561 $0.01561
Opus 5 $0.00781 $0.00781
Sonnet 5 $0.00312 $0.00312
Haiku 4.5 $0.00156 $0.00156

Measured 9d ago against content hash 5dd21c240303, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

qb-ai-toolkit CLAUDE.md 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 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.

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.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — context for Claude Code

This file is read automatically by Claude Code. Keep it short, accurate, and specific to THIS project so suggestions are grounded in our real setup.

What this repo is

A small toolkit for working with our Quickbase app safely from the command line, built on the QuickBaseClient wrapper (Python). Use it for analysis, exports, formula drafting, and careful bulk updates.

There are two ways in: a read-only MCP server (quickbase_mcp.py) for asking questions in Claude chat, and this wrapper for building and for any writes. All create / update / delete work goes through the wrapper — never the MCP.

When using the MCP, users speak in plain language and won't know table names or field ids. The server scans the configured app(s) on startup and exposes a get_catalog() tool (apps, tables, fields, types, choices, example values) — call it first, map the user's wording to the right ids, then query. If access looks wrong or recently changed, call refresh_access() to re-scan.

How to connect (do this — don't invent another way)

  • Never hard-code or paste the token. Credentials come from environment variables.
  • Use config.get_client() — it reads QB_REALM, QB_USER_TOKEN, and QB_APP_ID from the environment (a local .env is loaded automatically in dev).
  • Example:
    from config import get_client
    client = get_client()
    result = client.query_records(table_id="bxxxxxxx", where="{3.GT.'0'}", select=[3, 6, 7])
    

The wrapper's key methods

  • query_records(table_id, select=[...], where="...", sort_by=[...], options={...}) → dict with data (list of { "<fieldId>": {"value": ...} }), fields, metadata.
  • get_records_paginated(table_id, where=..., select=..., page_size=1000, max_records=None) → iterator over individual record dicts (use this for large pulls).
  • upsert_records(table_id, records, merge_field_id, fields_to_return=None)records is [{fieldId: value, ...}]. Use merge_field_id=3 (Record ID#) to UPDATE existing records only — this never creates new records.
  • get_fields(table_id), get_tables(app_id), get_app(app_id), get_relationships(table_id).
  • run_formula(table_id, formula, record_id=None) → test a formula via the API without changing the schema.
  • delete_records(table_id, where)permanent. Do not call without explicit human sign-off.

Read the full file on GitHub · 95 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.

  1. 9d ago First seen · 95 lines · 1,561 tokens per session scan A 5dd21c240303

Subscribe to this mod's changes

qb-ai-toolkit CLAUDE.md is an instructions file published in the GitHub repository josemsantiago/qb-ai-toolkit (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,561 tokens to every session, about $0.0078 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.

Related

Other instructions, from other repositories