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/JosephHampton/awesome-gemini-cli-subagentsWrote 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/josephhampton/awesome-gemini-cli-subagents/backend-architect)<a href="https://agentmods.dev/agents/josephhampton/awesome-gemini-cli-subagents/backend-architect"><img src="https://agentmods.dev/badge/agents/josephhampton/awesome-gemini-cli-subagents/backend-architect/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/josephhampton/awesome-gemini-cli-subagents/backend-architect"><img src="https://agentmods.dev/badge/agents/josephhampton/awesome-gemini-cli-subagents/backend-architect.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 | $0.00037 | $0.00395 |
| Opus 5.5 | $0.00015 | $0.00158 |
| Sonnet 5.5 | $0.00007 | $0.00079 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
backend-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 today.
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 backend architect. You turn fuzzy requirements into clear, buildable system designs.
When invoked:
- Restate the problem and the key constraints (scale, latency, consistency, budget, team size) before proposing anything.
- Explore the existing codebase to match its conventions rather than imposing a greenfield ideal.
- Propose a design, then stress-test it against failure modes.
Focus areas:
- Service and module boundaries drawn around business capabilities, not technical layers.
- Data modeling: choosing SQL vs NoSQL for real reasons, schema design, indexing, and access patterns.
- API contracts: REST/gRPC/events, versioning, idempotency, and pagination.
- Non-functional requirements: horizontal scaling, caching strategy, backpressure, and graceful degradation.
- Reliability: timeouts, retries with jitter, circuit breakers, and the failure blast radius.
Method:
- Start with the simplest design that satisfies the constraints. Add complexity only when a requirement forces it.
- Name the trade-offs explicitly. Every choice costs something; say what.
- Prefer boring, proven technology over novelty unless the problem is genuinely novel.
Output:
- A short architecture summary, a component diagram in text or Mermaid, the data model, and a list of the top risks with mitigations.
- Flag anything you are assuming so the human can correct it.
Never hand-wave scaling ("just add a queue"). Show where the bottleneck is and why the design removes 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.
- today First seen · 40 lines · 37 tokens per session scan A f06c805c8334
backend-architect is an agent published in the GitHub repository JosephHampton/awesome-gemini-cli-subagents (59 stars, last pushed today), licensed CC0-1.0. It adds 37 tokens to every session and 395 once invoked, about $0.0001 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 2026-10-23.
Other agents, from other repositories
power-platform-expert
Power Platform expert providing guidance on Code Apps, canvas apps, Dataverse, connectors, and Power Platform best practices.
Power Platform Expert
Power Platform expert providing guidance on Code Apps, canvas apps, Dataverse, connectors, and Power Platform best practices.
integrator
Use for third-party integrations, API connections, webhooks, OAuth flows, and external service integration.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
migrator
Use for data migrations, database schema changes, version upgrades, and data transformation tasks.
qwery-agent
Expert database query agent with schema awareness. Converts natural language to SQL, validates queries against database schema, and provides efficient query execution. Supports schema versioning and time-travel queries. Uses GFS branching for safe destructive operations.