Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/josemsantiago/qb-ai-toolkitnpx agentmods add skills/josemsantiago/qb-ai-toolkit/quickbase-codepageWrote 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.
[](https://agentmods.dev/skills/josemsantiago/qb-ai-toolkit/quickbase-codepage)<a href="https://agentmods.dev/skills/josemsantiago/qb-ai-toolkit/quickbase-codepage"><img src="https://agentmods.dev/badge/skills/josemsantiago/qb-ai-toolkit/quickbase-codepage.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00121 | $0.02581 |
| Opus 5 | $0.00060 | $0.01290 |
| Sonnet 5 | $0.00024 | $0.00516 |
| Haiku 4.5 | $0.00012 | $0.00258 |
Grade A, and why
quickbase-codepage 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quickbase code page
Build a browser-delivered code page — self-contained HTML/CSS/JS stored in a Quickbase
app — that does its work client-side and authenticates as the logged-in user via their
existing Quickbase session, so no secret ever lives in the page. Use this to turn a
Python script (usually REST /v1 with a hardcoded QB-USER-TOKEN) into an in-app widget,
or to build a code page from scratch.
New to code pages, or the user asks "how do I make one?" → the full creation guide (click-path, addressing, embedding, limits) is in the repo at
codepages/README.md; the full auth model is incodepages/authentication.md. This skill is the hands-on build workflow.
The one hard rule
Never put a QB-USER-TOKEN (or any REST /v1 user token) in a code page. Code pages are
downloaded in full to every viewer's browser — "View Source"/DevTools expose every string.
A user token is a real credential with its owner's full permissions; in a page it is handed to
everyone who can open it. The .py's token is for server-side use only. In a code page,
auth comes from the user's existing QB session cookie via the classic XML API. (An app
token is fine to include when the app requires one — it is a low-sensitivity gate, not a user
secret. If the page must exceed the viewer's own permissions, see Elevated access below —
the answer is a server-side proxy, still never a user token in the page.)
Auth pattern (the whole point)
Call the classic XML API with the session cookie. Same-origin relative URL → the browser sends the QB session (ticket) cookie → QB runs the query as that user, under their permissions:
fetch('/db/<tableDbid>?act=API_DoQuery&fmt=structured&clist=<f.f.f>&query=<q>', { credentials:'include' })
- Add
&apptoken=<token>only if the app has "Require Application Tokens" enabled (config field or?appToken=param). - Query syntax:
{'<fid>'.EX.'<value>'}(EX equals, XEX not-equal, CT contains, GT/LT/GTE/LTE, OAF/BF for dates; combine withAND/OR).clist= field ids joined by.;slist= sort fid; paginate withoptions=num-N.skp-M. - Parse with
DOMParser('text/xml'). Read<errcode>:4= bad/expired ticket,22= sign-in required → both mean prompt re-login (do NOT key off10— that is "invalid field type"). Records are<record rid="..">with<f id="N">value</f>. Date/DateTime fields come back as ms-since-epoch at UTC midnight → usegetUTC*. File-attachment fields carry a<url>child. - Don't know the field ids? Resolve at runtime with
act=API_GetSchema(map<field id>→<label>), or hardcode them. - Want REST/JSON instead of XML? Mint a temporary token (
GET https://api.quickbase.com/v1/auth/temporary/<tableDbid>with the session; 5-min life; still the same user, no elevation). Details incodepages/authentication.md.
What ships with it
2 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.
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.
- 7d ago First seen · 159 lines · 121 tokens per session scan A 938b94f51268
quickbase-codepage is a skill published in the GitHub repository josemsantiago/qb-ai-toolkit (0 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 2,581 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.
Other skills, from other repositories
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
next-dev-loop
Verify Next.js runtime behavior after editing app code. Use this skill to confirm a change actually works in a running app — not just that it compiles or type-checks. Combines /next/mcp (Next.js's view) with agent-browser (the browser's view). Requires a running next dev.
playwright-component-testing
Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime. Use when asked to test React or Vue components in isolation with Playwright, or to migrate off @playwright/experimental-ct-react / -vue.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.