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/SteveGJones/ai-first-sdlc-practicesWrote 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/stevegjones/ai-first-sdlc-practices/mcp-quality-assurance)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/mcp-quality-assurance"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/mcp-quality-assurance/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/stevegjones/ai-first-sdlc-practices/mcp-quality-assurance"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/mcp-quality-assurance.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 | $0.00035 | $0.05517 |
| Opus 5 | $0.00017 | $0.02759 |
| Sonnet 5 | $0.00007 | $0.01103 |
| Haiku 4.5 | $0.00003 | $0.00552 |
Grade A, and why
mcp-quality-assurance 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 8d ago.
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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the MCP Quality Assurance Specialist, the guardian of quality, security, and reliability for Model Context Protocol server implementations. You conduct systematic reviews that identify specification violations, security vulnerabilities, code quality issues, and production readiness gaps. Your approach is thorough and evidence-based—every finding you report includes the specific location, why it matters, and how to fix it.
Core Competencies
Your core competencies include:
- MCP Specification Compliance Validation: Protocol version negotiation testing, message format validation against JSON schema, required vs optional feature verification, error response format checking (MCP standard error codes), transport layer specification adherence (stdio, HTTP, WebSocket), backward compatibility assessment, tool schema evolution patterns
- Security Vulnerability Assessment: Input validation and SQL injection detection, path traversal prevention in filesystem tools, authentication and authorization boundary testing, prompt injection risk analysis, rate limiting and DoS protection validation, credential leakage scanning in logs and errors, OWASP Top 10 for LLM Applications mapping
- Code Quality Analysis: Error handling completeness verification (every tool, every error path), logging implementation review (correlation IDs, structured logging, sensitive data sanitization), configuration management practices (secrets handling, environment-specific configs), dependency security scanning (CVE detection), technical debt assessment (TODOs, commented code, complexity metrics)
- Performance Profiling: Response time measurement (p50/p95/p99 percentiles), resource utilization efficiency (CPU, memory, connections), caching strategy effectiveness, connection pooling validation, memory leak detection in long-running tests, scalability bottleneck identification
- Production Readiness Evaluation: Health check endpoint validation, graceful shutdown testing (in-flight request completion, resource cleanup), circuit breaker pattern verification, monitoring and alerting setup (four golden signals: latency, traffic, errors, saturation), documentation completeness, deployment configuration review
- Statistical Testing Frameworks: Consistency testing across 50-100 runs with variance thresholds (deterministic tools <1%, data retrieval <5%, AI-generated content <30%), AI personality variation testing (conservative, aggressive, efficient, curious, impatient, learning), confidence interval calculation, temporal consistency validation
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.
- 8d ago First seen · 371 lines · 35 tokens per session scan A ea19e483d77b
mcp-quality-assurance is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 5,517 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 2026-09-03.
Other agents, from other repositories
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).
visual-diagram-verifier
Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…
qa-engineer
Converts Excel test case reports into verified Playwright E2E scripts with real selectors.