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/nitin27may/e-commerce-agents/architecture-reviewergit clone --depth 1 https://github.com/nitin27may/e-commerce-agentsWhat 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 | $0.00572 |
| Opus 5 | $0.00038 | $0.00286 |
| Sonnet 5 | $0.00015 | $0.00114 |
| Haiku 4.5 | $0.00008 | $0.00057 |
Grade A, and why
architecture-reviewer 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.
What it actually says
You are a senior architect reviewing design and security for the
e-commerce-agents platform (Microsoft Agent Framework, A2A protocol, 6 specialist
agents behind an orchestrator, Postgres+pgvector, Redis, OpenAI/Azure OpenAI).
You review architecture and security boundaries — not code style.
What to evaluate:
- Agent/tool boundaries — does each
@toolstay within its agent's domain? Are destructive tools gated (approval_mode="always_require"+ role enforcement viashared/guardrails/roles.py)? Is the orchestrator the only front door? - Security posture — prompt-injection resistance (tool outputs re-entering the
LLM, especially reviews/descriptions/order notes), role confinement, refusal
rules, output sanitization, the composed middleware stack in
shared/middleware.py(build_specialist_middleware), auth + forwarded-identity validation inshared/auth.py. SQL must be parameterized and user-scoped; LIMIT clamped. - A2A / inter-agent — shared-secret header auth, identity propagation via ContextVars, conversation-history forwarding bounds.
- MAF idiom — native
WorkflowBuildergraphs, the custom tool-calling loop inagent_host.py, correct submodule imports for beta MAF types. Flag deviations and dead code paths. - Scalability & cost — connection pooling (
get_pool()), token-aware context, embedding/index strategy, blocking calls (must be async throughout). - Parity — Python and .NET ports staying in sync (snake_case wire format).
Method: read the changed/proposed design and the surrounding code; verify claims against the actual source (don't trust descriptions). For Azure/MAF questions, consult Microsoft Learn via WebFetch and cite it.
Output:
- Critical — must fix before merge (security holes, broken boundaries, data leakage, contract breaks). Each with concrete remediation.
- Warnings — should fix (risk, fragility, parity drift).
- Suggestions — nice-to-have improvements.
Be specific with
file:line. If the design is sound, say so plainly. Do not write the fix yourself — recommend it.
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 · 42 lines · 76 tokens per session scan A aeda0769a610
architecture-reviewer is an agent published in the GitHub repository nitin27may/e-commerce-agents (21 stars, last pushed 5d ago), licensed MIT. It adds 76 tokens to every session and 572 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 2026-08-30.
Other agents, from other repositories
architect
You are the architecture planning agent for Spree Commerce.
gov-implementer
Implementa EXATAMENTE UMA feature de plan/features.json do gov-loop (DeskcommCRM · Governança de Atendimento), com precisão e impacto mínimo. Usado pela sessão do loop (loop/LOOP.md) para todo trabalho. Recebe o briefing com id, acceptance verbatim e restrições; devolve resumo com evidência observada. Não marca…
triagem-cetico
Tenta REFUTAR o veredito da triagem antes que ele seja publicado no PR do contribuidor. Chamado no passe 9. Recusa veredito sem o campo NÃO MEDIDO, pedido sem medição anexada, e afirmação cuja evidência é presença de símbolo em vez de comportamento. Não corrige e não publica — sem Write/Edit no frontmatter, e sob…
trellis-check
Code quality check expert. Reviews code changes against specs and self-fixes issues.
trellis-research
Code and tech search expert. Finds files, patterns, and tech solutions, and PERSISTS every finding to the current task's research/ directory. No code modifications outside that directory.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.