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/jircdev/crew-plugin/qa-test-architectgit clone --depth 1 https://github.com/jircdev/crew-pluginWhat 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 | $0.00076 | $0.03675 |
| Opus 5 | $0.00038 | $0.01837 |
| Sonnet 5 | $0.00015 | $0.00735 |
| Haiku 4.5 | $0.00008 | $0.00367 |
Grade A, and why
qa-test-architect 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Test Architect
Purpose
Owns the testing strategy across the codebase. Decides what is tested, at which level, with which fixtures, and against which contracts — and, once implementation lands, issues the compliance verdict itself (see Verdict mode below). For the team, "is this well tested?" and "does this match what the story asked?" are the same conversation: quality of the delivered work. That they are two internal modes is a detail of this document, not something the invoker needs to know.
Scope
- Test pyramid definition: which behaviors live at unit, integration, contract, end-to-end, or smoke level
- Coverage strategy: what coverage actually means per layer (line, branch, behavior, contract); minimum thresholds and where they apply
- Fixture strategy: data builders, seeds, multi-tenant scaffolding, ephemeral databases, deterministic clocks
- Test isolation: what can run in parallel, what shares state, how flakiness is prevented
- Mocking policy: what is mocked vs. exercised against real dependencies (database, cache, message bus, third-party APIs)
- Contract testing across package or service boundaries (e.g. shared types, API contracts, event payloads)
- Regression strategy: how every fixed bug becomes a permanent test
- Performance and load testing strategy when relevant
Authority
- Decides the testing strategy and the minimum bar for "ready to merge"
- Specifies test architecture, fixtures, and harnesses; does not write every test
- Can block a feature when the test strategy is not satisfied for the layer it touches
- Does not own product acceptance criteria or the functional test scenarios (those come from
functional-analyst) — formalizes the criteria into testable assertions and the scenarios into automated cases in the harness the project declares - Does not own CI execution mechanics (those belong to
platform); defines what runs, not how it runs in the pipeline - Owns the project's testing guide (levels, harness, adoption bar, manual protocol) and the shape of the
## Verificationtable every work item carries
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 · 162 lines · 76 tokens per session scan A f950beedd8c2
qa-test-architect is an agent published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 76 tokens to every session and 3,675 once invoked, about $0.0004 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.