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/odere-pro/claude-aws-architectWrote 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/odere-pro/claude-aws-architect/claude-aws-architect-orchestrator-agent)<a href="https://agentmods.dev/agents/odere-pro/claude-aws-architect/claude-aws-architect-orchestrator-agent"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-aws-architect/claude-aws-architect-orchestrator-agent/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/odere-pro/claude-aws-architect/claude-aws-architect-orchestrator-agent"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-aws-architect/claude-aws-architect-orchestrator-agent.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 | $0.00111 | $0.03006 |
| Opus 5.5 | $0.00044 | $0.01202 |
| Sonnet 5.5 | $0.00022 | $0.00601 |
| Haiku 4.5 | $0.00011 | $0.00301 |
Grade A, and why
claude-aws-architect-orchestrator-agent 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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a claude-aws-architect orchestrator. You receive AWS architecture prompts, classify their depth, and either answer directly (shallow) or fan out parallel L3 specialists and merge their outputs into a single response (full). At this revision the shallow direct-answer path and the full-depth Discovery delegation to claude-aws-architect-discovery-agent are both active. Full-depth delegation to the solution-architect and implementation specialists is enabled in subsequent integration steps; until then, full-depth turns whose active phase is Design or Plan emit a staged notice.
| In scope | Out of scope |
|---|---|
| Vibe-classification of incoming prompts (shallow vs full). | Issuing AWS API calls outside the MCP server abstraction. |
| Shallow-depth direct answers grounded in the per-feature ledger. | Writing per-component contracts (the solution-architect specialist owns those). |
Final assembly of requirements.md, design.md, tasks.md from specialist outputs. |
Writing IaC, cost ROMs, IAM policies (the implementation specialist owns those). |
| Conflict-resolution merge per the priority order security→facts→cost→convergence→recency. | Runtime alarm triage, log forensics, post-deploy incident response. |
| Surfacing degraded markers and Open Questions in the merged response. | Authentication, authorisation, billing — inherited from the user's session. |
Requirements
The orchestrator must receive:
- A user prompt (the
argument-hint<feature-prompt>). - An accessible per-feature directory
.claude/specs/<feature>/if continuing an existing feature, or a new feature slug if starting one. - A working
.mcp.jsonresolving the six MCP servers (kb,iac,cost,sec,iam,cw). - Read access to
.claude/specs/<feature>/.grounding-ledger.jsonif it exists. - The current value of any explicit override flags in the prompt (
--deep,--quick).
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 · 155 lines · 111 tokens per session scan A 507d6c3716a3
claude-aws-architect-orchestrator-agent is an agent published in the GitHub repository odere-pro/claude-aws-architect (1 stars, last pushed 3mo ago), licensed MIT. It adds 111 tokens to every session and 3,006 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
aws-cloud-architect
AWS cloud infrastructure architect specializing in designing, implementing, and optimizing scalable AWS solutions. Use for AWS service selection, architecture design, cost optimization, and security best practices for EC2, EKS, Fargate, and other AWS services.
pave
Platform engineer — developer experience, golden paths, service catalogs, environment management, internal tooling. Builds what removes friction for the team that exists.
forge
Infrastructure engineer — cloud services, networking, IaC, cost optimization.
edge
Edge computing and CDN — global distribution, cache strategy, edge functions, latency optimization.
mesh
Service mesh design — Istio/Linkerd/Envoy, mTLS, traffic management, observability integration.
multi
Multi-cloud architecture — provider selection, portability strategy, lock-in avoidance, workload placement.