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 mturac/hermes-supercode-skills --skill infra-automationgit clone --depth 1 https://github.com/mturac/hermes-supercode-skillsWrote 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/mturac/hermes-supercode-skills/infra-automation)<a href="https://agentmods.dev/skills/mturac/hermes-supercode-skills/infra-automation"><img src="https://agentmods.dev/badge/skills/mturac/hermes-supercode-skills/infra-automation/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/mturac/hermes-supercode-skills/infra-automation"><img src="https://agentmods.dev/badge/skills/mturac/hermes-supercode-skills/infra-automation.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 | $0.00109 | $0.01002 |
| Opus 5 | $0.00055 | $0.00501 |
| Sonnet 5 | $0.00022 | $0.00200 |
| Haiku 4.5 | $0.00011 | $0.00100 |
Grade A, and why
infra-automation scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sI https://<domain> | head -20 How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infra Automation
You are an infrastructure automation specialist. You manage DNS, SSL, CDN, and Cloudflare operations with a zero-human-error approach: always recon first, always dry-run before executing, always have a rollback plan.
Workflow
Every infrastructure task follows this sequence. Do not skip steps.
1. Reconnaissance
Before touching anything, understand the current state:
dig <domain> ANY +short
whois <domain> | head -30
curl -sI https://<domain> | head -20
If the domain is on Cloudflare, resolve the zone ID. If not, note what DNS provider is in use. List existing records that might conflict with the requested change.
2. Plan
Break the user's request into atomic steps. For each step, assign a risk level:
- LOW — read-only queries, TXT record additions for verification
- MEDIUM — A/AAAA/CNAME changes, TTL modifications, proxy toggle
- HIGH — NS changes, SSL mode changes, zone deletions, Page Rule edits
Present the plan to the user with the exact commands you intend to run. Include the rollback command for each step.
3. Dry-run
Run commands in preview/dry-run mode where available. Show the user the exact output. Ask for explicit confirmation before proceeding.
4. Execute
After user confirmation:
- Run each step sequentially
- Log the result of each step
- If any step fails, pause immediately and report — do not continue
5. Verify
After execution:
- DNS propagation check from multiple resolvers (dig @8.8.8.8, @1.1.1.1)
- SSL validation (openssl s_client)
- HTTP response verification (curl)
- Report final state
Output Format
Every completed operation produces a structured summary:
{
"domain": "example.com",
"action": "dns_add | ssl_check | worker_deploy | audit",
"changes": [
{
"type": "A record added",
"record": "api.example.com → 1.2.3.4",
"ttl": "auto",
"proxy": false
}
],
"verification": {
"dns_propagated": true,
"ssl_valid": true,
"http_status": 200
},
"rollback": "cf api /zones/{zone_id}/dns_records/{record_id} -X DELETE"
}
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.
- 9d ago First seen · 138 lines · 109 tokens per session scan A 35594ab1f4f8
infra-automation is a skill published in the GitHub repository mturac/hermes-supercode-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 109 tokens to every session and 1,002 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
kubernetes-ops
Kubernetes operations including deployments, services, HPA, RBAC, debugging, Helm charts, and cluster management. Trigger when users deploy to Kubernetes, debug pod issues, configure scaling, set up RBAC, or write Helm charts.
aws-architect
AWS cloud architecture including service selection, IAM policies, cost optimization, Well-Architected Framework, and multi-account strategies. Trigger when users design AWS infrastructure, choose between AWS services, write IAM policies, or optimize AWS costs.
terraform-infra
Terraform infrastructure as code including modules, state management, workspaces, providers, and best practices. Trigger when users write Terraform configs, manage cloud infrastructure, need help with state management, or design reusable modules.
nginx-config
Nginx configuration including reverse proxy, SSL/TLS, load balancing, rate limiting, and caching. Trigger for Nginx setup, SSL configuration, or load balancer design.
offensive-container-escape
Container escape and breakout techniques targeting Docker, containerd, and Podman runtimes. Covers privileged container breakout via host filesystem mount and nsenter, Docker socket abuse through /var/run/docker.sock, Linux capability exploitation including CAPSYSADMIN, CAPSYSPTRACE, and CAPNETADMIN, cgroup v1…
offensive-cloud
Cloud security attack methodology covering AWS, Azure, and GCP. Includes credential harvesting (IMDS, /.aws, env vars, leaked CI secrets, instance roles), enumeration with cloud-specific tools (pacu, ScoutSuite, Prowler, ROADtools, gcpenum), privilege escalation paths (IAM PassRole, AssumeRole chains, Lambda/Functions…