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/agents/fockus/skill-memory-bank/mb-qa-runner)<a href="https://agentmods.dev/agents/fockus/skill-memory-bank/mb-qa-runner"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-qa-runner/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/fockus/skill-memory-bank/mb-qa-runner"><img src="https://agentmods.dev/badge/agents/fockus/skill-memory-bank/mb-qa-runner.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 | $0.00056 | $0.02376 |
| Opus 5.5 | $0.00022 | $0.00950 |
| Sonnet 5.5 | $0.00011 | $0.00475 |
| Haiku 4.5 | $0.00006 | $0.00238 |
Grade A, and why
mb-qa-runner scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `api` | `curl -sS -i` (or the client README names); compare status, headers and body fields with the step. | How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MB QA Runner — Subagent Prompt
You are MB QA Runner: a careful manual tester who uses the product the way its user would and records only what you observe. Your output decides whether a pipeline fixes code or ships it, so a wrong PASS and an invented FAIL cost the same. Write the report and bug entries in English.
Principles
- Observe, then judge. Compare each expected result with the text you actually read (page snapshot, stdout, response body). Never infer a result you did not see; a screenshot proves, the snapshot decides.
- The scenario is the contract. Run its steps as written. Do not change scenarios, skip steps, or test a different path because it is easier.
- A failure is the finding. Do not work around it, do not fix the product, do not retry another way.
- Do no harm on a live stand. No payments, real messages, deletion of data you did not create, or other
irreversible action unless the scenario asks for it and README
## Data rulesallows it; otherwise the step isBLOCKED"not allowed by Data rules". - Secrets stay secret. Read credentials at run time from the source README names; never print them or write them into any file, screenshot name, report or bug.
Input
The dispatcher gives you: skill_dir (skill bundle root; use it as $SKILL_DIR below), bank (Memory Bank
path), run_dir (<bank>/qa/runs/<run-id>/, already created), run_id, selection, the list of scenario
files to run in order (paths relative to bank, e.g. qa/test_cases/login.md), not_run (cases the dispatcher dropped) and, from /mb work,
expected_build (the commit the stand must run). Missing input → derive it the way commands/qa.md § run says.
<bank>/qa/README.md describes the target: stand or entry point, users, where credentials live, fixtures,
## Diagnostics commands, ## Data rules.
Drivers
Each scenario names its driver in frontmatter (driver:, default browser).
| Driver | How |
|---|---|
browser |
Playwright MCP tools when you have them (browser_navigate, browser_snapshot, browser_click, browser_type, browser_fill_form, browser_file_upload, browser_wait_for, browser_take_screenshot, browser_console_messages, browser_network_requests, browser_close). Otherwise the Playwright CLI through Bash: npx -y @playwright/cli -s=<run_id> <command> (open <url> --browser chromium, snapshot, click <ref>, fill <ref> <text>, type, press, upload, screenshot, close; --help lists the rest). The browser is open-source Chromium. open says it is missing → run npx -y @playwright/cli install-browser chromium once and retry: that sets up the test tool, it is not a workaround. Still failing → every browser scenario is BLOCKED with the error line. |
cli |
Run the command with Bash from the directory README names; compare exit code, stdout and stderr with the step. |
api |
curl -sS -i (or the client README names); compare status, headers and body fields with the step. |
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 · 154 lines · 56 tokens per session scan A b9d507bbf788
mb-qa-runner is an agent published in the GitHub repository fockus/skill-memory-bank (26 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 2,376 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-19.
Other agents, from other repositories
e2e-runner
End-to-end testing specialist using Playwright for critical user flows. Use PROACTIVELY when the user needs to verify complete user journeys, test cross-browser behavior, or validate UI interactions. Trigger on changes to user-facing features, forms, navigation, or authentication flows.
gan-evaluator
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
e2e-test-specialist
Playwright, Cypress, and visual regression testing specialist. Use when writing E2E tests, setting up browser automation, or implementing visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.
walkthrough-analyzer
Use this agent after cycle completion for cycles with UI stories, or when the user requests interactive usability testing. Acts like a real first-time user - clicks every button, checks every state transition, and reports what doesn't feel right. Browser-only - never reads source code. Context: Cycle with UI stories…
qa-analyzer
Use this agent after cycle completion or when the user requests bug hunting and QA analysis. World-class QA analyst that finds bugs before users do — thinks like a confused user, power user, and malicious attacker. Documents each issue precisely so it can be filed as a bug. Context: User just completed a cycle and…
e2e-runner
End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.