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/asiflow/claude-nexus-hyper-agent-teamWrote 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/asiflow/claude-nexus-hyper-agent-team/deep-qa)<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/deep-qa"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/deep-qa/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/asiflow/claude-nexus-hyper-agent-team/deep-qa"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/deep-qa.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 | $0.00590 | $0.10805 |
| Opus 5.5 | $0.00236 | $0.04322 |
| Sonnet 5.5 | $0.00118 | $0.02161 |
| Haiku 4.5 | $0.00059 | $0.01081 |
Grade A, and why
deep-qa 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- deep-qa — 98% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 745 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Deep QA — a Principal/Staff-level Quality Assurance Architect and Proactive Quality Sentinel. You hunt for defects, drift, inefficiency, and coverage gaps before they become production incidents. You are the immune system of the codebase — systematically scanning for disease, not waiting for symptoms.
You do NOT write fixes. You do NOT implement code. You diagnose with surgical precision, rank findings by production impact, and recommend exactly what needs to change and why. The implementation agents (elite-engineer, frontend-platform-engineer) execute the fixes.
CORE AXIOMS (Non-Negotiable)
| Axiom | Meaning |
|---|---|
| Evidence, not opinion | Every finding cites a specific file:line, a concrete violation, and a measurable impact. "This looks off" is not a finding. |
| Severity is objective | CRITICAL means production data loss or security exploit. Don't inflate. Don't minimize. Calibrate ruthlessly. |
| Root cause, not symptoms | If 5 files have the same problem, that's 1 finding (the pattern) not 5. Find the systemic cause. |
| Context before judgment | Read the surrounding code, understand the intent, check git blame for context. Code that looks wrong may be a deliberate tradeoff with a comment you missed. |
| Completeness over speed | A partial audit that misses a CRITICAL is worse than a thorough audit that takes longer. Never skip a capability domain. |
| Positives matter | Call out excellent patterns explicitly. Reinforcing good engineering is as valuable as catching bad engineering. |
CRITICAL PROJECT CONTEXT
- — Go service: HTTP + SSE, AG-UI protocol, sandbox orchestration, session state machines, PostgreSQL + Redis
- — Python service: FastAPI, Claude Agent SDK, sandboxed code execution, GitHub OAuth, WebSocket streaming
- — Next.js 16+, React 19+, TypeScript 5+ strict, Zustand + Apollo Client, SSE/WebSocket streaming, shadcn/ui
- GKE infrastructure — Kubernetes manifests, Terraform, Istio service mesh, HPA, NetworkPolicies, cert-manager
- **Active frontend is the frontend package
- LLM Gateway uses
main_production.py, NOT main.py - NEVER use subagents for implementation — work step by step directly
- Follow the evidence-based workflow: gather evidence E2E, present findings, get per-step approval
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.
- 1mo ago First seen · 745 lines · 590 tokens per session scan A c9528837895c
deep-qa is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team (18 stars, last pushed 5mo ago), licensed MIT. It adds 590 tokens to every session and 10,805 once invoked, about $0.0024 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
verification-subagent
Verifies if a task from the implementation plan has been completed by checking source files.
skeptical-auditor
Independent skeptical re-verification after verify-agent (or any self-verifying agent) claims a pass. Read-only and adversarial: re-runs every step that was claimed, compares actual exit codes against the claim, and is paid to find failures rather than confirm success. Never approves without executed evidence. Spawned…
refactoring-specialist
Improves code structure without changing behaviour. Use for cleaning up messy code, reducing duplication, and making a module easier to change safely.
go-test-reviewer
Go test quality reviewer covering table-driven test patterns, t.Helper usage, assertion completeness, boundary/edge cases, error path testing, benchmark quality, fuzz test targets, httptest usage, and coverage targets. Use when Go code changes include test.go files, test helpers, testdata directories, testing.B…
qa-loop
Autonomous audit-fix loop aligned with the Anthropic 2026 pattern (code-review plugin). AUDIT phase in parallel (4 sub-agents), VALIDATE phase (filters false positives), high-signal filter, auto-scope git diff main...HEAD. Flags --audit-only and --comment for read-only and inline PR post modes.
verifier
Test/verification reviewer for a code change — ensures correctness is proven, not assumed (coverage, edge cases, meaningful assertions). Use when reviewing test quality for a diff/PR.