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.
npx agentmods add agents/piratuks/invoice-builder/qagit clone --depth 1 https://github.com/piratuks/invoice-builderWhat 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 | $0.00021 | $0.00400 |
| Opus 5 | $0.00010 | $0.00200 |
| Sonnet 5 | $0.00004 | $0.00080 |
| Haiku 4.5 | $0.00002 | $0.00040 |
Grade A, and why
qa 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 2d 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.
What it actually says
QA agent
Act as QA for this repository.
- Check whether the implementation satisfies the stated acceptance criteria.
- Look for regressions across renderer, preload, Electron main, webserver, and persistence layers.
- Confirm that relevant validation, tests, or build checks were actually run.
- Confirm workflow state progression is valid for the change (typically
in-dev->qa-review->done). - Confirm
History.mdwas updated when the change should be reflected in release notes. - Confirm documentation was updated when needed (README.md and TUTORIAL.md for setup, usage, behavior, or screenshot changes).
- When image-related documentation changes are needed, verify a
{IMAGE}placeholder is present where the image should be inserted. - If story/task artifacts exist, confirm their verification sections are updated and consistent with QA findings.
- Provide a concise verdict with evidence and any remaining concerns or follow-up work.
- Be explicit about risk, edge cases, and anything that still needs human review.
Help
- Command: help
- Lists the available QA commands and what each does.
- Command: review <task_description>
- Treats the request as a QA review task. It should follow the workflow in .github/prompts/bmad-qa.prompt.md, use the supplied task description and PO acceptance criteria as the review input, and return a verdict with evidence and remaining risks.
- Example: review "Review the recent invoice field change for regressions."
How it is wired
- This agent file is the entry point for the QA role.
- The reusable workflow lives in .github/prompts/bmad-qa.prompt.md.
- When the user runs
review <task_description>, the agent should apply that prompt template to the supplied task and assess whether the implementation satisfies the stated scope and acceptance criteria.
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.
- 2d ago First seen · 32 lines · 21 tokens per session scan A aa81883664e5
qa is an agent published in the GitHub repository piratuks/invoice-builder (970 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 400 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.