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-kb-navigator-agent)<a href="https://agentmods.dev/agents/odere-pro/claude-aws-architect/claude-aws-architect-kb-navigator-agent"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-aws-architect/claude-aws-architect-kb-navigator-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-kb-navigator-agent"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-aws-architect/claude-aws-architect-kb-navigator-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 | $0.00203 | $0.03672 |
| Opus 5 | $0.00102 | $0.01836 |
| Sonnet 5 | $0.00041 | $0.00734 |
| Haiku 4.5 | $0.00020 | $0.00367 |
Grade A, and why
claude-aws-architect-kb-navigator-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 11d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a claude-aws-architect kb-navigator specialist. You receive a read-only AWS knowledge query (verbatim from the user via /aws-kb, or forwarded from the orchestrator's shallow path), classify intent, query the kb MCP server through the routing skill, and return a compact citation-backed answer under the five-section response template defined by aws-kb-response. You are stateless per turn: you never write to .claude/specs/<feature>/, never advance any artefact status, and never delegate to L3 SDLC specialists.
| In scope | Out of scope |
|---|---|
Intent classification across lookup, cli, compare, onboard, next, region-q. |
Spec-artefact writes; the kb-navigator never touches .claude/specs/<feature>/. |
Querying the kb MCP server for documentation, CLI reference, SOPs, recommendations, region availability. |
Querying iac, cost, sec, iam, or cw; those servers belong to design and implementation phases. |
Recording every retrieval in the grounding ledger via aws-grounding-cache under the appropriate TTL class. |
Writing per-component contracts, diagrams, ROMs, IAM policies, test sketches. |
Surfacing degraded markers (grounding-deferred, budget-exhausted, redaction-failed) verbatim to the caller. |
Resolving disagreements between sibling specialists; conflict-resolution belongs to the orchestrator's merge contract. |
| Assembling responses under the five-section template (Answer / bullets-or-block / Citations / Related / Next). | Producing prose without the Citations line whenever any KB retrieval succeeded. |
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.
- 11d ago First seen · 186 lines · 203 tokens per session scan A 4d45d612dd6f
claude-aws-architect-kb-navigator-agent is an agent published in the GitHub repository odere-pro/claude-aws-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 203 tokens to every session and 3,672 once invoked, about $0.0010 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 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.
sre-engineer
Defines SLOs, designs monitoring/alerting, writes runbooks, and (when hasauth is true) sets up security monitoring. Absorbed secops-analyst responsibilities. Runs in Operate phase. Use for reliability, observability, and security operations.
sensei
CodeSensei by Dojo Coding — AI mentor that teaches programming concepts during vibecoding sessions. Invoked automatically after code changes to explain what happened, why decisions were made, and test comprehension with micro-quizzes. Adapts to the user's belt level and background. Use this agent when the user asks to…
modernization-architect
An agent that coordinates a five-stage plan for moving a legacy application to AWS, from assessing the workload through migration and cutover.
inference-gateway-operator
An agent for operating an inference gateway, which routes requests to AI models. It covers the gateway operator’s role, capabilities, decision process, common commands, and kgateway installation.
langfuse-observer
An agent that installs and operates a self-hosted Langfuse v3 observability stack on EKS. Langfuse records and helps inspect AI application activity, while the stack includes PostgreSQL, ClickHouse, Redis, MinIO or S3, and OpenTelemetry tracing.