Borrowing it
Nothing to install: this file belongs to agentkitai/agentlens. 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/agentkitai/agentlens/main/.claude/commands/bmad-bmm-qa-automate.mdgit clone --depth 1 https://github.com/agentkitai/agentlensWrote 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/commands/agentkitai/agentlens/bmad-bmm-qa-automate)<a href="https://agentmods.dev/commands/agentkitai/agentlens/bmad-bmm-qa-automate"><img src="https://agentmods.dev/badge/commands/agentkitai/agentlens/bmad-bmm-qa-automate/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/commands/agentkitai/agentlens/bmad-bmm-qa-automate"><img src="https://agentmods.dev/badge/commands/agentkitai/agentlens/bmad-bmm-qa-automate.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 | $0.00015 | $0.00199 |
| Opus 5 | $0.00008 | $0.00100 |
| Sonnet 5 | $0.00003 | $0.00040 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade A, and why
qa-automate 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 10d 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.
This is a copy
72% identical to correct-course — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
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.
- 10d ago First seen · 16 lines · 15 tokens per session scan A e7738a88a39c
qa-automate is a command published in the GitHub repository agentkitai/agentlens (23 stars, last pushed 10d ago), licensed MIT. It adds 15 tokens to every session and 199 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 72% identical to correct-course, differing in 10 lines, and is treated as a copy.
Other commands, from other repositories
ng-red-team
Portable command prompt generated from skills/stress-testing-agent-changes/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
hub-tdd
TDD workflow for MCP Hub implementation. Types → Tests (red) → Implementation (green) with git gates.
profiles-tdd
TDD workflow for SPEC-HUB-002 Agent Profiles. Registry → Identity → Hub Handler → Priming with git gates.
hdd-validate-brief
Command "hdd-validate-brief" from Kastalien-Research/thoughtbox, covering hdd validate module, inputs, steps, outputs and stop conditions.
check
Run every gate that must pass before committing.
run-tests
Run a focused subset of the user's test suite via mk-qa-master, surface failures, and offer next steps.