invoice-builder: Command for GitHub Copilot

.github/prompts/bmad-po.prompt.md

bmad-po is a command for GitHub Copilot from piratuks/invoice-builder. It costs 0 tokens per session (715 once invoked), scanned A, original, MIT.

A product-scoping command set for defining the boundaries and acceptance criteria of a software change before implementation. Acceptance criteria are the conditions a change must meet to be considered complete.

In plain words
What is it for?
It helps validate task descriptions and prepare a release from entries in package.json and History.md. It can also determine a version bump from the documented changes.
Why use it?
It turns a loosely described request into a clearer scope, risks, and verification plan, reducing misunderstandings before coding starts.

Command for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

This is piratuks/invoice-builder's own configuration. It tells GitHub Copilot how to work on invoice-builder 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 invoice-builder configures →

About the project

Invoice Builder is an offline desktop application for creating, managing, and exporting invoices and quotations, with business data stored in a local database file. It is designed for freelancers, contractors, and small businesses that need local control of their invoicing data and PDF documents. The catalogue commands, agents, and instructions provide coding-agent workflows for working with the application.

piratuks/invoice-builder · 1,344 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to piratuks/invoice-builder. 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/piratuks/invoice-builder/main/.github/prompts/bmad-po.prompt.md
Clone the repo
git clone --depth 1 https://github.com/piratuks/invoice-builder

Made for: GitHub Copilot.

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 bmad-po

README.md
[![agentmods](https://agentmods.dev/badge/commands/piratuks/invoice-builder/bmad-po/github.svg)](https://agentmods.dev/commands/piratuks/invoice-builder/bmad-po)
Your own site
<a href="https://agentmods.dev/commands/piratuks/invoice-builder/bmad-po"><img src="https://agentmods.dev/badge/commands/piratuks/invoice-builder/bmad-po/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 bmad-po

Your own site · 80×15
<a href="https://agentmods.dev/commands/piratuks/invoice-builder/bmad-po"><img src="https://agentmods.dev/badge/commands/piratuks/invoice-builder/bmad-po.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 715 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00715
Opus 5.5 $0.00000 $0.00286
Sonnet 5.5 $0.00000 $0.00143
Haiku 4.5 $0.00000 $0.00072

Measured 27d ago against content hash 5068440a81be, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

bmad-po 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 27d 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.

.github/prompts/bmad-po.prompt.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BMAD PO prompt

Use this prompt when you need product-facing scoping and acceptance criteria before implementation.

Invocation

  • Command: help
  • Lists the available PO commands and what each does.
  • Command: validate <task_description>
  • This is the workflow behind the PO agent's validate command. When invoked, substitute the task description into {{TASK_DESCRIPTION}} and return scope, acceptance criteria, risks, and a verification plan.
  • Example: validate "Add a new invoice export option and define the acceptance criteria."
  • Command: prepare_release
  • This workflow reads the top placeholder block in docs/history.md that starts with ## {DATE}, version {VERSION} and finalizes it for release.

Prepare release workflow

When prepare_release is invoked:

  1. Read the current version from package.json and the top placeholder block in docs/history.md that starts with ## {DATE}, version {VERSION}. Stop and report an error before editing if either is missing.
  2. Determine version bump from the block content using these rules:
    • MAJOR: breaking change language is present (for example "breaking change", "removed", "incompatible", "migration required").
    • MINOR: at least one item exists under "New features & improvements" and no MAJOR trigger exists.
    • PATCH: only "Bug Fixes" entries exist and no MAJOR/MINOR trigger exists.
  3. Set {DATE} to today's date in YYYY-MM-DD format.
  4. Set {VERSION} to the bumped semantic version based on package.json.
  5. Update docs/history.md in place with the resolved date/version.
  6. Use the exact resolved version from docs/history.md and synchronize it across:
    • package.json -> version
    • packages/core/src/config.ts -> getBackendConfig().webserver.version
    • README.md -> add a new row under ## 📌 Supported Versions in the format | vX.Y.Z | ✅ Actively supported |
  7. Run npm install --package-lock-only --ignore-scripts to refresh package-lock.json after the version update.
  8. Return:
    • the chosen bump level (major/minor/patch)
    • the old version -> new version
    • the finalized top release block
    • a short list of synchronized files

Read the full file on GitHub · 60 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. 27d ago Changed · -1 lines 5068440a81be
  2. 1mo ago Changed 92147894508a
  3. 1mo ago First seen · 61 lines · 0 tokens per session scan A 6967ed0a910a

Subscribe to this mod's changes

bmad-po is a command published in the GitHub repository piratuks/invoice-builder (1,344 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 715 tokens. 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 2026-09-08.