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.
git clone --depth 1 https://github.com/fockus/skill-memory-bankWrote 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/fockus/skill-memory-bank/qa)<a href="https://agentmods.dev/commands/fockus/skill-memory-bank/qa"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/qa/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/fockus/skill-memory-bank/qa"><img src="https://agentmods.dev/badge/commands/fockus/skill-memory-bank/qa.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 | $0.00044 | $0.01505 |
| Opus 5.5 | $0.00018 | $0.00602 |
| Sonnet 5.5 | $0.00009 | $0.00301 |
| Haiku 4.5 | $0.00004 | $0.00151 |
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 today.
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mb qa: $ARGUMENTS
Acceptance QA, not a test framework: a scenario is a short md file, the mb-qa-runner agent walks it against the live
product like a user and records what it observes. Unit and e2e tests prove the code; /mb qa run proves the user path.
Set SKILL_DIR to the absolute directory containing the loaded SKILL.md (or MB_SKILLS_ROOT); run this setup in
the same shell as each command below. <bank> below is $BANK.
SKILL_DIR="${MB_SKILLS_ROOT:-${SKILL_DIR:?Set SKILL_DIR from the loaded skill path}}"
source "$SKILL_DIR/scripts/_lib.sh"
BANK="$(mb_resolve_path)"
[ -d "$BANK" ] || { echo "[MEMORY BANK: ABSENT] — /mb init first"; exit 0; }
Layout
<bank>/qa/README.md target: stand URL or entry point, users, credentials source, fixtures, Diagnostics, Data rules
<bank>/qa/test_cases/**/*.md one file = one scenario; subfolders group suites
<bank>/qa/fixtures/ files scenarios upload or feed
<bank>/qa/runs/<run-id>/ report.md + screenshots and output excerpts (run-id = YYYY-MM-DD_HHMM)
<bank>/qa/bugs.md bug registry, written only by scripts/mb-qa-bug.sh
new <name>
Create <bank>/qa/test_cases/<name>.md (<name> may include a suite folder, checkout/guest-pay). If
qa/README.md is absent, create it with the sections ## Target, ## Users (logins and where the credentials are
read from — env var, secret store; never the secret itself), ## Fixtures, ## Diagnostics (commands that fetch
logs for a request id or time window), ## Data rules (what scenarios may create and must delete).
---
tags: [smoke] # free-form; `run @smoke` selects by tag
driver: browser # browser | cli | api
id: checkout-pay # catalog cases only: the file stem
covers: [REQ-001] # spec REQ ids, or DoD-<n> for a plan without REQs
origin: specified # specified | derived | regression
proof: live # live | test | both
status: needs_spec # only when the expected result is not derivable from the requirements or DoD; omit otherwise
---
# <Title — the user goal>
## Preconditions
- <user, state, fixtures from qa/fixtures; no secrets>
## Steps
1. <one user action> → <observable expected result>
2. <one user action> → <observable expected result>
## Pass criteria
- <what must be true at the end>
## Cleanup
- <what the scenario created and how to remove it>
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.
- today First seen · 111 lines · 44 tokens per session scan A de1b548a9502
qa is a command published in the GitHub repository fockus/skill-memory-bank (26 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,505 once invoked, about $0.0002 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 2026-10-19.
Other commands, from other repositories
e2e
Generate and run E2E tests with Playwright.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
playwright-setup
Verify Playwright CLI installation and create a .playwright/cli.config.json configuration file. Use when setting up browser automation, configuring Playwright, or user mentions "setup playwright", "configure browser testing", "install playwright".
browsertest
Run, create, debug, and maintain browser tests.
qa
Pre-PR quality gate — browser-driven QA for web changes with a mandatory evidence packet against a provisioned environment. No QA-passed claim without artifacts. Workspace-aware. For a quick behavioral check without the evidence packet, prefer the bundled /verify or /run.
create-smoke-test.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.