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-spec-groundinggit 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-spec-grounding)<a href="https://agentmods.dev/skills/odere-pro/claude-aws-architect/aws-spec-grounding"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-spec-grounding/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-spec-grounding"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-aws-architect/aws-spec-grounding.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 | $0.00065 | $0.01171 |
| Opus 5 | $0.00032 | $0.00585 |
| Sonnet 5 | $0.00013 | $0.00234 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
aws-spec-grounding 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 — 57 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 writes, edits, or reviews an AWS spec artefact: requirements.md, design.md, tasks.md, component contracts, or ADRs. The orchestrator and discovery agent invoke it at draft time; reviewers invoke it before accepting. Do not apply this skill to non-AWS prose or to internal scratch notes that never reach a spec file.
Trigger conditions:
- The agent is about to assert a factual AWS detail (quota, API shape, pricing, region availability, service-to-service compatibility, ARN format).
- The agent is about to recommend a design (data store, async vs sync, region strategy, identity boundary, instance class).
- The agent is reviewing a draft spec and needs to find un-grounded claims.
- The agent is asked to explain why a recommendation was made and the spec's rationale section is empty.
Procedure
- Classify the claim. For each sentence the agent is about to write, decide: is it a factual claim about AWS or a design opinion about how to use AWS? Consult
references/opinion-vs-fact.mdfor the boundary cases. - For factual claims. Attach at least one
grounded-by: <server>:<short-key>citation. The citation must reference a ledger entry produced by a prior MCP call. Format rules inreferences/cite-format.md. - For design opinions. Attach a one-paragraph rationale that names a Well-Architected pillar, a documented principle, or a stated trade-off. A bare "this is best practice" is not a rationale. Rules in
references/grounded-by-rules.md. - Detect missing grounding. A claim with no citation and no rationale is a violation. Emit it as a
grounding-deferredmarker so the orchestrator surfaces the gap; do not silently let it pass. - Detect mismatched grounding. A factual claim with only a rationale (no citation) is also a violation — facts need sources, not philosophy. A design opinion with only a citation (no rationale) is a violation — opinions need reasoning, not just a doc link.
- Record the audit. Each violation is logged so reviewers can see which claims were flagged and which were resolved before the spec was accepted.
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 · 57 lines · 65 tokens per session scan A aa420478ddaa
aws-spec-grounding is a skill published in the GitHub repository odere-pro/claude-aws-architect (1 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,171 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.