Prompt library

View .md

Prompts that work, grouped by who types them and where. Replace the parts in <angle brackets>. Each prompt names the Beacon page the AI should read, so the answer follows the current docs and not the model’s memory of them.

In your repository (coding agents)

For Claude Code, Cursor, Copilot or any agent that edits code. With Claude Code, the Beacon plugin adds skills that do the same with less typing.

Set Beacon up

Add an MCP gateway to this ASP.NET Core app with Beacon.
Read https://moberghr.github.io/beacon/llms-gateway.txt first and follow it step by step.
Before writing code, read the app and tell me: how users sign in, where the users table and its Entra object id are,
which database and migrator we use, and which endpoints look like self-service reads. Then ask me the decisions
the guide lists.

Integrate Beacon into this ASP.NET Core app, with <PostgreSQL | SQL Server> for Beacon's own data and
<Warp | Hangfire | our own scheduler> for jobs.
Read https://moberghr.github.io/beacon/llms-integrate.txt and follow its checklist in order.
Ask me before every decision it marks as one, keep secrets in user secrets, and show me each verification step.

Turn on Entra ID single sign-on for Beacon in this app.
Read https://moberghr.github.io/beacon/cookbooks/entra-sso.md and follow it. Print the app registration steps for me
to run in the portal instead of changing the tenant yourself.

Upgrade this application from Beacon 4.x to 5.0.
Read https://moberghr.github.io/beacon/getting-started/whats-new.md and apply every item under "Upgrade from 4.x"
that applies. List the ones that did not apply and why. Build and run the tests afterwards.

Tools for agents

Make <GET /api/my/orders> available to Claude as a Beacon MCP tool.
Read https://moberghr.github.io/beacon/cookbooks/endpoint-as-tool.md first. Check the endpoint against its
tool review checklist before marking it, bind the person's id from the caller, write an agent-facing description
field by field, and add a Moberg.Beacon.Testing test that proves it refuses somebody else's data.

List every endpoint in this repository marked with WithBeaconTool or [BeaconTool].
For each, check it against the tool review checklist in
https://moberghr.github.io/beacon/cookbooks/endpoint-as-tool.md and report: self-service or not, what data it
returns, whether ReadOnly is declared, whether the person's id is bound from the caller, and whether a test pins it.
Do not change anything yet.

Walk me through publishing our approved saved query "<name>" as an MCP tool.
Follow https://moberghr.github.io/beacon/cookbooks/saved-query-tool.md and tell me who has to do which step.

Fix and harden

Beacon refused to start with this message: <paste the message>.
Read https://moberghr.github.io/beacon/integrate/troubleshooting.md and the page the message points to, explain the
cause in two sentences, then fix it in this repository.

Claude cannot connect to https://<your-app>/beacon/mcp. The error is: <error or AADSTS code>.
Read https://moberghr.github.io/beacon/mcp/gateway.md (sections 6 to 8) and tell me what to check, in order.
Then run: beacon-doctor mcp https://<your-app>/beacon/mcp and explain every WARN and FAIL it prints.

Review this application's Beacon set-up against https://moberghr.github.io/beacon/integrate/production.md.
Go through every checklist item and answer pass, fail or not applicable, with the file and line that shows it.
Do not change anything; give me the list.

Ask your data

For Claude, Claude Desktop, Cursor or any MCP client connected to Beacon’s MCP server. The recipe Ask your data questions with an AI agent explains the workflow behind these.

Use Beacon's get_context to describe my project: its data sources, the main tables and how well they are
documented. Do not run any queries yet.

Where does Beacon keep <customer refunds>? Search for it, read the documentation of the most likely tables, and tell
me which columns hold the amount, the date and the customer.

I need <monthly refund totals for the last six months>. Get the grounding context for that question, write the SQL
yourself, validate it with dry_run and show me the SQL and the verdict. Run it with query only after I say go.

Ask Beacon: "<How many orders were placed last week, by country?>" Show me the SQL it generated with the answer.

Explain where the figure <12,430 active customers> comes from: the SQL, the tables it reads, and the filter that
decides who counts. If Beacon has no definition of the term, say so instead of guessing.

Compare <revenue> in <September> and <October> by <product line>. Use one query, validate it with dry_run first, and
point out the three biggest changes. Say if any result was truncated or masked.

Which saved-query tools (q_…) do I have? If one of them answers "<question>", run it instead of writing SQL, and
tell me which one you used.

That answer was <correct | wrong because it counted cancelled orders>. Record it with Beacon's feedback tool and the
signal_id from the answer<, with this corrected SQL: …>.

Call get_context with format "agents_md" and turn the result into a short section I can paste into AGENTS.md:
the data sources, the main tables and what they mean, and the rules for using Beacon's tools.

In an application with a Beacon gateway

For people whose own application has a Beacon MCP gateway: Claude acts as you, through the application’s own endpoints, and sees only what the application lets you see.

List the <app> tools you have and, for each, one line on what it does and whether it changes anything.

Show me my <open leave requests> in <app>, newest first, with their status.

Request <leave from 3 to 7 November> in <app>. Before you call the tool, tell me exactly what you will send.

Running Beacon (admins)

We have these teams and databases: <list>. Read https://moberghr.github.io/beacon/security.md and propose Beacon
projects, which data sources each links, who is a member with which role, and which projects stay restricted.
Explain each choice in one line.

I want an AI agent to read only the <finance> project. Follow
https://moberghr.github.io/beacon/cookbooks/agent-one-project.md and give me the exact steps for our Beacon, the key
settings and the project settings I should check.

Here is an export of Beacon's MCP audit: <paste or attach>. Read
https://moberghr.github.io/beacon/mcp/observability-and-audit.md for what the fields mean, then summarise: which
callers ran what, which calls were refused and why, and anything that looks unusual.

Read https://moberghr.github.io/beacon/mcp/server.md (Deployment locks and ceilings) and propose the Beacon:Mcp
configuration for a regulated production deployment, with one line per setting on why.

Writing your own

Name the page. “Read https://moberghr.github.io/beacon/<page>.md” is short, and the agent works from current docs.
Ask for the plan first on anything that changes code, a tenant or a deployment: “tell me what you will do, then wait”.
Name the tool when it matters. “Validate it with dry_run” is more reliable than “be careful”.
Ask for evidence. The SQL, the row count, the beacon-doctor output, the test that pins it.
Never paste secrets. Give environment variable names, not API keys or client secrets.