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 alexei-led/cc-thingz --skill operating-infragit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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/alexei-led/cc-thingz/operating-infra)<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/operating-infra"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/operating-infra/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/alexei-led/cc-thingz/operating-infra"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/operating-infra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00119 | $0.01078 |
| Opus 5 | $0.00060 | $0.00539 |
| Sonnet 5 | $0.00024 | $0.00216 |
| Haiku 4.5 | $0.00012 | $0.00108 |
Grade A, and why
operating-infra 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 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.
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operate Infrastructure
Boundary
- Work from files, plans, logs, and read-only commands before changing anything.
- Do not run apply, delete, destroy, or rollback until identity, exact resources, blast radius, and plan/diff/inventory are shown and the user confirms.
- If the task is deployment, rollout, rollback, or production apply, use
deploying-infra. - If the task is only shell scripts, generic command pipelines, or the shell body
inside a GitHub Actions
run:step, usewriting-shell. - For GitHub Actions, workflow structure, triggers, jobs, permissions, runners,
actions, environments, secrets, caching, concurrency, and policy stay here.
Mixed workflow and shell-body changes compose with
writing-shell.
Role behavior
- Write-capable: make minimal file changes and run safe validation. Stop before live mutation unless the user confirmed exact resources.
- Read-only: apply nothing; return proposed file changes, evidence, and validation commands.
Load references
Load every matching reference:
- Terraform/OpenTofu files, modules, state, or plans → terraform.md
- Kubernetes manifests or
kustomization.yaml→ kubernetes.md Chart.yaml, Helm values, or chart templates → helm.md- GitHub workflow YAML outside pure
run:shell bodies → github-actions.md Dockerfileor container image build/release concerns → dockerfile.md- AWS CLI, EC2, ECS, Lambda, S3, RDS, IAM, or CloudWatch → aws.md
- GCP CLI, GCS, Compute Engine, IAM, quotas, or Cloud Logging → gcp.md
- Cloud Run services, revisions, traffic, or logs → cloud-run.md
- BigQuery queries, tables, datasets, or cost checks → bigquery.md
- Linux services, hosts, processes, disks, or networks → linux.md
Mixed stacks: load all matching references. Unknown stack: use the workflow below only.
What ships with it
12 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.
- .agentbundler/targets/claude.json 854 B
- references/aws.md 1.8 KB
- references/bigquery.md 1.9 KB
- references/cloud-run.md 1.3 KB
- references/dockerfile.md 1.2 KB
- references/gcp.md 1.6 KB
- references/github-actions.md 1.7 KB
- references/helm.md 1.3 KB
- references/kubernetes.md 1.9 KB
- references/linux.md 1.3 KB
- references/terraform.md 2.1 KB
- scripts/bq-cost-check.py 5.0 KB runs code
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 · 85 lines · 119 tokens per session scan A 2df87eee1256
operating-infra is a skill published in the GitHub repository alexei-led/cc-thingz (35 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 1,078 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
gemini-review
Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration.
ci-review
Audit CI workflow architecture and effectiveness without modifying it. Use when triggers, jobs, commands, quality gates, caches, artifacts, matrices, permissions, release paths, or deployment automation may be stale, redundant, unsafe, or unjustified.
execution/infra-executor
Internal: Infrastructure Executor. Implements deployment, CI/CD, container, IaC, and environment configuration changes. Write evidence on completion.
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.