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 abel30567/fermi-mcp --skill aws-cdk-disciplinegit clone --depth 1 https://github.com/abel30567/fermi-mcpWrote 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/abel30567/fermi-mcp/aws-cdk-discipline)<a href="https://agentmods.dev/skills/abel30567/fermi-mcp/aws-cdk-discipline"><img src="https://agentmods.dev/badge/skills/abel30567/fermi-mcp/aws-cdk-discipline/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/abel30567/fermi-mcp/aws-cdk-discipline"><img src="https://agentmods.dev/badge/skills/abel30567/fermi-mcp/aws-cdk-discipline.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 | $0.00032 | $0.00469 |
| Opus 5 | $0.00016 | $0.00234 |
| Sonnet 5 | $0.00006 | $0.00094 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
aws-cdk-discipline 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.
What it actually says
AWS CDK-only discipline (fermi-agentcore)
The policy (non-negotiable)
ALL AWS infrastructure changes for fermi-agentcore go through CDK: edit the
constructs, commit, push to main → CI (typecheck/lint/test/synth) →
cdk deploy --all to ca-central-1 via the OIDC deploy role. Creating, updating
or deleting AWS resources directly (console or API) is a LAST RESORT only after
confirming no CDK path exists. Applies to IAM roles, DynamoDB tables, Lambdas,
Gateway targets — everything.
Fermi's AWS access is READ-ONLY
SigV4-signed verification calls only, using {{secret:AWS_ACCESS_KEY_ID}} +
{{secret:AWS_SECRET_ACCESS_KEY}} (allowed_hosts: *.amazonaws.com). Use them
to confirm deployed state (GetGateway, ListGatewayTargets,
DescribeLogGroups, ...) — never to mutate. For bedrock-agentcore control-plane
calls, sign with service name bedrock-agentcore (NOT
bedrock-agentcore-control) against host
bedrock-agentcore-control.{region}.amazonaws.com.
Secrets
Runtime secrets for AgentCore go through the AgentCore secrets-set tool (its own store), never by writing AWS Secrets Manager directly.
Repo facts
- Repo: your-org/your-repo, region ca-central-1.
- 6 stacks: Identity, Gateway, Memory, Storage, Compute, Observability.
- When live state and CDK source disagree, fix the CDK to match intent and
deploy; verify with
cdk diffshowing zero unexpected changes. - Claude.ai loads only ~30 of the gateway's tools (client cap, issue #13) — consolidate tools (op params) rather than adding more.
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 · 37 lines · 32 tokens per session scan A 07538fc7b24c
aws-cdk-discipline is a skill published in the GitHub repository abel30567/fermi-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 469 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
alchemy-infra
Sets up Alchemy (alchemy-run/alchemy, Infrastructure-as-TypeScript) in any codebase — new project scaffold OR add to existing app. Wires Cloudflare/AWS providers, state backend, secrets, and binding types end-to-end with strict secret hygiene. USE THIS SKILL whenever the user mentions "alchemy", "alchemy.run"…
terraform-iac
Terraform and OpenTofu infrastructure as code best practices - generate HCL configurations, module patterns, state management, CI/CD workflows, and cloud provider templates for AWS, GCP, Azure.
terraform-builder
Build infrastructure as code with Terraform. Covers module design, state management, AWS/GCP/Azure resources, and production-grade practices.
aws-collector-tool
AWS infrastructure collector. Fetches ECS status, CloudWatch logs, and metrics. Use when: checking ECS health, inspecting CloudWatch error logs, pulling infra metrics, or monitoring AWS resources.
cdkd
Install cdkd and use it safely from an AWS CDK project. Use when bootstrapping, synthesizing, diffing, deploying, inspecting, rolling back, migrating, or destroying dev/test stacks with cdkd.
deploy
Deploy the current project to the cloud using Defang. Guides through CLI setup, authentication, compose file creation, stack selection, config management, and deployment.