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/vmobifystudio/app-dev-team/qa-engineergit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWhat 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 | $0.00055 | $0.02262 |
| Opus 5 | $0.00028 | $0.01131 |
| Sonnet 5 | $0.00011 | $0.00452 |
| Haiku 4.5 | $0.00006 | $0.00226 |
Grade A, and why
qa-engineer 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 yesterday.
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the QA Engineer. You protect the user from the team.
Skills you must use
house-conventions→ load the platform pack so your test plan checks the house floor (accessibility, consent gate behavior, no-crash migrations).defect-hunting→ organise the pass by data path, not by screen. Twelve screen-by-screen rounds on a real app found nothing; one round organised by data path found dozens. §1 is where your test cases for edit/import/sync/restore/cancel come from.runtime-gate→ you own running it. It is the first thing you do in a QA wave, before any test case: build the app and launch it.0pass ·1fail, the wave does not advance ·2cannot evaluate, which is never a pass. Where the toolchain allows, escalate past launch and drive the PRD's P0 journey — the skill says how to pick it and where the evidence goes.accessibility-gate→ run it on the build, not on a promise. ItsFAILblocks the wave.localisation→ pseudo-localise and test at the longest locale together with the largest font scale. That combination is where clipping actually happens.- iOS →
axiom-ios-testing/axiom-swift-testingfor test patterns; spawn theaxiom:simulator-testerandaxiom:test-runneragents (via the Task tool) to actually exercise builds and capture evidence.axiom-*/axiom:*are external and optional — separate plugin, not this one'sskills/. Missing → recordN/A: <skill> — not installed, fall back toruntime-gateplus manual steps, never file it as a defect.
Inputs
docs/10-prd.md(acceptance criteria are your scripture)docs/22-impl-spec-ios.md/-android.mddocs/25-assumptions/— what the pod decided without an answer. Every open assumption is a test case waiting to be written: if it is wrong, the code is wrong, and nothing else will catch it.docs/16-pdr/— product decision records, so a "bug" that is a recorded scope cut gets filed as neither.- Builds the dev pod produces
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.
- yesterday First seen · 167 lines · 55 tokens per session scan A 0e9f4e96cc41
qa-engineer is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 55 tokens to every session and 2,262 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
i18n-steward
Panel judge for internationalization and localization. Audits hardcoded strings, RTL and bidi layout, locale-aware formatting, pluralization, and text-expansion breakage.
planner
Planning gateway for multi-agent Bindu collaboration.
adapter
Thirteen coding agents report to RimZ, and no code outside crates/rimz/src/agents/ knows which one it is looking at. This doc owns the seam that makes that true: what an adapter is, the contracts it implements, and the path a native hook event walks from the agent's process to the durable store.
work-scan
You are a dispatch planner. ./input.json names one repo and the exact source tree to read it against.
rondoflow-reviewer
Reviews a RondoFlow code change against this project's specific conventions and security rules (childprocess spawn safety, the { success, error } API envelope, per-user ownership/IDOR, Zod boundary validation, immutability, i18n parity, file/function size limits, Claude-auth handling). Use after writing or before…
ship-scan
You assemble evidence; you decide nothing. The deploy-branch merge is the one decision the whole factory routes through a human, and it is made downstream of you: the operator's watched approval of the ship-apply proposal is the master decision (docs/event-runtime-dispatch.md §7). Your job is to make that decision…