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 skills add odere-pro/claude-aws-architect --skill aws-mcp-routinggit 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/skills/odere-pro/claude-aws-architect/aws-mcp-routing)<a href="https://agentmods.dev/skills/odere-pro/claude-aws-architect/aws-mcp-routing"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-mcp-routing/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/skills/odere-pro/claude-aws-architect/aws-mcp-routing"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-mcp-routing.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 | $0.00049 | $0.01391 |
| Opus 5 | $0.00024 | $0.00696 |
| Sonnet 5 | $0.00010 | $0.00278 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
aws-mcp-routing 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 10d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
Apply this skill any time an agent needs to consult an AWS MCP server. That includes the orchestrator's grounding step, every L3 specialist's MCP call, and any rule that delegates to a server. Do not apply this skill for non-AWS knowledge; use the agent's own reasoning or a non-MCP source.
Trigger conditions:
- The agent must answer a factual AWS question (quota, API shape, region availability, ARN, pricing).
- The agent must validate a CloudFormation or CDK construct.
- The agent must check IAM least-privilege, security findings, or operational metrics.
- The agent's previous MCP call timed out or returned a 5xx and a fallback decision is required.
- The agent is about to issue a tool call whose name might breach the 64-character fully-qualified-tool-name limit; this skill verifies the resolved server key.
Procedure
- Classify the request. Determine which of the six categories the request belongs to: docs, IaC, cost, security review, IAM, or operations. The category determines the server.
- Select the server. Consult
references/selection-rules.mdfor the category-to-server mapping. Use the short identifier (kb,iac,cost,sec,iam,cw) defined in.mcp.json, never the descriptive logical name in tool calls. - Select the tool. Consult the per-server tool catalogue in
references/server-roster.md. Pick the narrowest tool that satisfies the request. Wide tools (e.g. broad documentation search) waste the per-specialist MCP-call budget (8 calls for discovery, 12 for solution-architect, 16 for implementation). - Verify the server is enabled. Before issuing the first call to a server in a session, confirm
mcp__<server>__*tools are present in the available tool list. If not, the server is disabled or pending approval — emitmcp-disabled-<server>perreferences/degraded-modes.mdwith remediation copy (run/mcp, editdisabledMcpjsonServers, or run/aws-doctor) and do not proceed with the call. One marker per server, per session. - Issue the call within the timeout budget. The per-server
timeoutMsvalue in.mcp.jsonis the per-call budget; the agent's MCP-call budget is the per-invocation cap. Both must be respected. - Handle response. On success, capture the result. On timeout or 5xx, consult
references/degraded-modes.mdfor the per-server fallback behaviour and emit the corresponding labelled marker in the agent's output. - Record the citation. Every successful MCP call must be recorded in the grounding ledger via the
aws-grounding-cacheskill, producing a<server>:<short-key>reference for use ingrounded-byfields.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 61 lines · 49 tokens per session scan A fe3898362d4d
aws-mcp-routing is a skill published in the GitHub repository odere-pro/claude-aws-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 1,391 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 2026-08-31.
Other skills, from other repositories
deployment
Hosting, deployment, CI/CD, and going live. Activated when Claude works with deployment configs, Dockerfiles, Vercel/Netlify configs, or deployment-related commands.
ec2
AWS EC2 virtual machine management — instances, security groups, key pairs, AMIs, EBS volumes, Auto Scaling Groups, Spot Instances, Session Manager, placement groups, and instance lifecycle automation. Trigger on ANY of these, even when EC2 isn't named explicitly: - Launching or provisioning: "spin up a server"…
ecs
AWS ECS container orchestration for running Docker containers. Use when deploying containerized applications, configuring task definitions, setting up services, managing clusters, or troubleshooting container issues.
cloudformation
AWS CloudFormation infrastructure as code for stack management. Use when writing templates, deploying stacks, managing drift, troubleshooting deployments, or organizing infrastructure with nested stacks.
cloudwatch
AWS CloudWatch monitoring for logs, metrics, alarms, and dashboards. Use when setting up monitoring, creating alarms, querying logs with Insights, configuring metric filters, building dashboards, or troubleshooting application issues.
eks
AWS EKS Kubernetes management for clusters, node groups, and workloads. Use when creating clusters, configuring IRSA, managing node groups, deploying applications, or integrating with AWS services.