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-kb-navigatorgit 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-kb-navigator)<a href="https://agentmods.dev/skills/odere-pro/claude-aws-architect/aws-kb-navigator"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-kb-navigator/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-kb-navigator"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-kb-navigator.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 | $0.00056 | $0.01627 |
| Opus 5 | $0.00028 | $0.00813 |
| Sonnet 5 | $0.00011 | $0.00325 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
aws-kb-navigator 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 12d 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 — 66 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 must answer a read-only AWS knowledge question that does not produce SDLC artefacts. Use it when the user asks "what is X", "show me the CLI for X", "compare A vs B", "onboard me to X", "what should I learn next about X", or "is X available in region Y". Do not apply this skill when the prompt names an SDLC artefact (requirements, design, tasks, threat model, ROM); route those to the orchestrator's full-depth path instead.
Trigger conditions:
- The agent must answer a factual AWS question that maps to a documentation page (service overview, capability, quota, ARN shape, region availability, API verb).
- The agent must surface an AWS CLI command reference or a recipe-style SOP for a stated task.
- The agent must compare two AWS services or two configurations of the same service on a stated dimension.
- The agent must produce an onboarding pointer for a service or a learning track around a topic.
- The agent must recommend related or next-step topics tied to a previous lookup recorded in the grounding ledger.
- The previous KB call timed out, returned 5xx, or exhausted the 6-call budget — a degraded-mode decision is required.
Procedure
- Classify intent. Read the user prompt and any explicit flag (
--cli,--compare,--onboard,--next,--deep). Choose one of the six intents inreferences/intents.md:lookup,cli,compare,onboard,next,region-q. Default when no flag fires and the prompt is a verb-of-inquiry:lookup. - Pick the narrowest KB tool. Apply the
aws-mcp-routingskill against the chosen intent's tool sequence. The intent → tool map is inreferences/intents.md. Use the short server keykbexclusively; never call other servers from this skill. - Cache pre-check. For every planned
kbcall, queryaws-grounding-cachefirst. Acached-freshhit short-circuits the live call and reuses its citation. Acached-staleormissingentry proceeds to the live call. - Issue the call within the per-call timeout declared by
kbin.mcp.json. Decrement the per-turn budget on every issued call. The per-turn budget is 6 KB calls. The seventh required call triggersbudget-exhaustedand returns control to the agent's caller. - Persist to the ledger via
aws-grounding-cache. TTL classes by intent:immutablefor service-overview and CLI-reference reads,regionforlist_regions/get_regional_availability,api-shapefor SOP retrievals fromretrieve_agent_sop. Apply the redaction policy on insert; on a redaction failure abort the write and emitredaction-failed. - Assemble the response under the fixed five-section template enforced by
aws-kb-response.instructions.md: a one- or two-sentence Answer, exactly one of (3–7 bullets OR a short code/CLI block), a Citations line carrying the<server>:<short-key>references, an up-to-five-item Related list, and an up-to-three-item Next list. Default ceiling is 250 words;--deeplifts it to 600. - Surface degraded markers when emitted.
grounding-deferred,budget-exhausted, andredaction-failedare returned to the agent's caller verbatim and never absorbed.
What ships with it
2 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.
- 12d ago First seen · 66 lines · 56 tokens per session scan A 32653fab1556
aws-kb-navigator is a skill published in the GitHub repository odere-pro/claude-aws-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 1,627 once invoked, about $0.0003 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.