What is bc-exploratory-test?

A testing workflow for Business Central extensions, which are custom additions to Microsoft’s business software. It uses the web and mobile clients to test real behaviour and prepare an evidence-backed handover.

Use it to explore an extension in Business Central web or MobileNAV, check records and fields, collect test evidence, and hand results to another developer or tester.

It replaces guesswork about selectors and repeated full-page captures with a focused record of what was tested and observed.

bc-exploratory-test — Skill for Claude Code and Codex by Brad-Fullwood

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 Brad-Fullwood/bc-rig --skill bc-exploratory-test

Clone the repo

git clone --depth 1 https://github.com/Brad-Fullwood/bc-rig

Made for: Claude Code, Codex.

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/brad-fullwood/bc-rig/bc-exploratory-test/github.svg)](https://agentmods.dev/skills/brad-fullwood/bc-rig/bc-exploratory-test)

Your own site

<a href="https://agentmods.dev/skills/brad-fullwood/bc-rig/bc-exploratory-test"><img src="https://agentmods.dev/badge/skills/brad-fullwood/bc-rig/bc-exploratory-test/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/brad-fullwood/bc-rig/bc-exploratory-test"><img src="https://agentmods.dev/badge/skills/brad-fullwood/bc-rig/bc-exploratory-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 906 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	$0.00034	$0.00906
Opus 5	$0.00017	$0.00453
Sonnet 5	$0.00007	$0.00181
Haiku 4.5	$0.00003	$0.00091

Measured 12d ago against content hash dd94854142a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

bc-exploratory-test 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 12d 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.

skills/bc-exploratory-test/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BC exploratory testing

Drive the real clients and produce an honest handover. Use the compact referenced workflow; it is faster and materially cheaper than repeated full snapshots or guessed selectors.

Efficient protocol

Call browser_session { operation: "start", launchJson: "/absolute/project/.vscode/launch.json" }. Select configuration only when the project has more than one AL launch entry and the intended entry is not first. Ask the user to complete interactive sign-in in the new isolated window.
Call browser_session { operation: "status" }; continue when it reports auth=OK.
Start evidence with run { operation: "start", label: "specific scope" }.
Call browser_observe in compact mode. It returns a revision and stable controls such as @b7a12f button "New".
Use browser_act with the ref. The action already returns semantic changes; do not immediately call browser_observe again.
Use browser_observe { mode: "query", query: "specific record or field" } for page data omitted by compact mode. Use full mode only to diagnose missing accessibility state.
For polling, pass the prior revision as since. unchanged rev=… is a complete result—do not request the same state again.

Refs should replace selector trial-and-error. If a ref is stale, observe once and use the new ref. Exact accessible names are available when a ref is unavailable. Raw CSS/Playwright selectors are intentionally not part of the MCP API.

Test loop

Enumerate the extension-owned pages, fields, actions, and MobileNAV surfaces. Navigate with browser_act { action: "navigate", url }, observe compact controls, and query specific data.
Exercise every web surface. Rendering alone is observation, not verification: click actions and fill fields through refs. Capture browser_screenshot only when visual evidence adds value.
Probe at least an empty/invalid required field, an action in a blocked state, and a boundary value. Tool failures are automatically recorded when a run is active; add contextual judgement with run { operation: "step", ... } when needed.
Exercise MobileNAV when the extension has a mobile surface:
- mobile_act { action: "connect", file } imports an .mnlc configuration. Do not hand-fill it.
- The user completes Microsoft sign-in interactively when required.
- mobile_observe returns compact @m… refs. Tap/type through mobile_act refs.
- After MFA, tap the referenced Login control again to complete MobileNAV's own login.
- Decline an optional PIN unless the test specifically covers it.
- Confirm the company header/module menu before claiming the app is connected.
Finish with run { operation: "finish" }, then run bc-rig handover --run latest. Read the Not covered section and close meaningful gaps before delivery.

Read the full file on GitHub · 66 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.

12d ago First seen · 66 lines · 34 tokens per session scan A dd94854142a8

Subscribe to this mod's changes

bc-exploratory-test is a skill published in the GitHub repository Brad-Fullwood/bc-rig (0 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 906 once invoked, about $0.0002 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.

E2E testing Testing android business-central mcp mobilenav model-context-protocol playwright

lastest

Lastest is a visual regression testing platform. It records browser tests, runs them via Playwright, diffs screenshots, and uses AI to classify changes. Available as an MCP server for AI agent integration.

las-team/lastest · 0 tokens

playwright-cli

Automate browser interactions, test web pages and work with Playwright tests.

microsoft/playwright · 19 tokens

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.

microsoft/playwright · 69 tokens

bc-exploratory-test