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 catpilotai/catpilot-ai-guardrails --skill cloud-cli-safetygit clone --depth 1 https://github.com/catpilotai/catpilot-ai-guardrailsWrote 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/catpilotai/catpilot-ai-guardrails/cloud-cli-safety)<a href="https://agentmods.dev/skills/catpilotai/catpilot-ai-guardrails/cloud-cli-safety"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/cloud-cli-safety/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/catpilotai/catpilot-ai-guardrails/cloud-cli-safety"><img src="https://agentmods.dev/badge/skills/catpilotai/catpilot-ai-guardrails/cloud-cli-safety.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 | $0.00092 | $0.04639 |
| Opus 5.5 | $0.00037 | $0.01856 |
| Sonnet 5.5 | $0.00018 | $0.00928 |
| Haiku 4.5 | $0.00009 | $0.00464 |
Grade A, and why
cloud-cli-safety 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 1mo 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 — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Baseline
Applies when: Before invoking a mutating az, aws, gcloud/gsutil, kubectl, helm, or terraform command, or a custom deploy wrapper (./deploy.sh, make deploy), especially against production-heuristic targets.
Always:
- Query current state (read-only) and show the relevant fields before any mutating command.
- Show the full command and affected targets; preserve env/secret references and never expand credentials into chat, logs, or history.
- Enumerate fields that will change (env vars, IAM bindings, replica counts, CPU/memory, probes).
- Get explicit confirmation (a literal "yes") before executing; do not infer consent.
- Prepare a rollback command before executing the forward command.
- Know which flags merge and which replace:
az containerapp update --set-env-varsadds or updates only the named variables and keeps the rest;--replace-env-varsand--yamlreplace the whole set;aws lambda update-function-configuration --environmentreplaces the whole map. - Verify after execution by re-running the read-only query and diffing against the pre-change snapshot.
Never:
az containerapp update --yaml <partial>— overwrites all unspecified fields;--replace-env-varsremoves unspecified variables too.aws lambda update-function-configuration --environment "Variables={ONLY_ONE=value}"— replaces, does not merge.aws s3 rm s3://bucket --recursivewithout prioraws s3 lsand explicit confirmation.gcloud projects set-iam-policy PROJECT policy.json— wipes existing bindings; useadd-iam-policy-bindinginstead.terraform apply -auto-approve/terraform destroy -auto-approveanywhere production is plausible.kubectl delete namespace productionorkubectl delete pods --all -n <ns>against a non-dev namespace.
Open the full component before acting: it has the examples, the remediation steps, and the detection patterns.
Why
This skill exists because of a specific outage.
An AI assistant was asked to update the liveness probe on an Azure Container
App. It generated a small YAML file containing only the probes: block and
ran:
What ships with it
1 file 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.
- 1mo ago Changed · +45 lines b133b8b59c92
- 1mo ago Changed · +11 lines 98fe8294b711
- 1mo ago First seen · 378 lines · 92 tokens per session scan A 2e9b76c1091b
cloud-cli-safety is a skill published in the GitHub repository catpilotai/catpilot-ai-guardrails (2 stars, last pushed 12d ago), licensed MIT. It adds 92 tokens to every session and 4,639 once invoked, about $0.0004 per session on Opus 5.5. 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
torchtitan
Pretrain LLMs at scale with PyTorch 4D parallelism.
modal
Serverless GPU cloud for ML jobs and model APIs.
cloudflare-temporary-deploy
Deploy a Worker live, no account, via wrangler --temporary.
publish-site
Versioned site deploys to GitHub/Cloudflare/Netlify Pages.
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.