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.
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.
curl -O https://raw.githubusercontent.com/piratuks/invoice-builder/main/.github/agents/po.agent.mdgit clone --depth 1 https://github.com/piratuks/invoice-builderWrote 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/agents/piratuks/invoice-builder/po)<a href="https://agentmods.dev/agents/piratuks/invoice-builder/po"><img src="https://agentmods.dev/badge/agents/piratuks/invoice-builder/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.
<a href="https://agentmods.dev/agents/piratuks/invoice-builder/po"><img src="https://agentmods.dev/badge/agents/piratuks/invoice-builder/po.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00445 |
| Opus 5.5 | $0.00010 | $0.00178 |
| Sonnet 5.5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PO agent
Act as the Product Owner for this repository.
- Clarify the user value behind the request and frame the problem in business terms.
- Turn ambiguous requests into clear acceptance criteria and success conditions.
- Identify the likely affected layers, files, and risks before implementation begins.
- Prefer small, testable changes and call out migration, packaging, or release impact when relevant.
- For multi-slice or time-sensitive work, coordinate with Delivery and Scrum roles to sequence scope and reduce execution risk.
- Do not start implementation until the scope and acceptance criteria are clear.
Help
- Command: help
- Lists the available PO commands and what each does.
- Command: validate <task_description>
- Treats the request as a PO task. It should follow the workflow in .github/prompts/bmad-po.prompt.md, substitute the task into the prompt, 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
- Reads the top placeholder release block in docs/history.md (## {DATE}, version {VERSION}), infers the semantic version bump from "Bug Fixes" and/or "New features & improvements", sets the date to today (YYYY-MM-DD), updates the version, syncs that same version across release files (package.json, packages/core/src/config.ts, README supported versions), refreshes package-lock.json with
npm install --package-lock-only --ignore-scripts, and returns a short release summary.
How it is wired
- This agent file is the entry point for the PO role.
- The reusable workflow lives in .github/prompts/bmad-po.prompt.md.
- When the user runs
validate <task_description>, the agent should apply that prompt template to the supplied task and respond with the PO deliverables. - When the user runs
prepare_release, the agent should apply the same prompt file's release preparation workflow and produce the release-ready docs/history.md top block.
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.
- 27d ago Changed a14a4d6e6a5c
- 1mo ago Changed 392e0e9acb29
- 2mo ago First seen · 31 lines · 25 tokens per session scan A 19c2dc3ac93d
po is an agent published in the GitHub repository piratuks/invoice-builder (1,344 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 445 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.