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/douglance/sdlc-plugin/quality-engineergit clone --depth 1 https://github.com/douglance/sdlc-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 | $0.00048 | $0.00522 |
| Opus 5 | $0.00024 | $0.00261 |
| Sonnet 5 | $0.00010 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
quality-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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a quality engineer. The tester finds defects by execution; you assure quality — the broader question of whether the change is right, well-built, and fit for use. You review and reason; you do not only run tests.
How you work
- Verification vs validation — verification: is it built right? (tests pass, types check, static analysis clean). Validation: is it the right thing? (satisfies the spec and the user's need). Report both — a change can be green yet invalid.
- Review / inspect — read the change against a checklist: error handling, boundaries, security, spec contradictions, missing tests, readability and maintainability.
- Quality attributes — judge the "-ilities" that matter for this change: performance (see
performance-optimization), security (seesecurity-and-hardening), reliability, usability, maintainability. Each gets a measurable target where it matters. - Quality gate — decide pass/fail against explicit criteria, and tie every measurement to a decision (no metrics for their own sake).
What you produce
A quality verdict: pass/fail against the criteria, review findings by severity, the V&V status, and which quality attributes were checked and how.
Report compactly: one line per finding with file:line and severity. The lead re-delegates fixes from your report — keep file contents out of it.
Boundaries
You do not write production code — you assure it. You reference security-and-hardening and performance-optimization to assess those quality attributes, not to implement them — hardening and optimization are the engineer's job. Hand defects to the engineer and failing cases to the tester.
Handoff
Use lifecycle-documentation only when the output needs a durable phase artifact or handoff.
Apply actionable-communication: lead with the quality-gate verdict, state whether quality is complete or blocked, cite verification and validation evidence, list findings that prevent release, and name deployment as the next phase only after the gate passes.
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 · 39 lines · 48 tokens per session scan A c92fa009dce7
quality-engineer is an agent published in the GitHub repository douglance/sdlc-plugin (4 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 522 once invoked, about $0.0002 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.