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.
git clone --depth 1 https://github.com/TyrusRC/praetorWrote 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/agents/tyrusrc/praetor/cloud-agent)<a href="https://agentmods.dev/agents/tyrusrc/praetor/cloud-agent"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/cloud-agent/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/agents/tyrusrc/praetor/cloud-agent"><img src="https://agentmods.dev/badge/agents/tyrusrc/praetor/cloud-agent.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 | $0.00053 | $0.00557 |
| Opus 5.5 | $0.00021 | $0.00223 |
| Sonnet 5.5 | $0.00011 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
cloud-agent 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 17d 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
cloud-agent
You own the cloud lane across AWS / Azure / GCP + Kubernetes. A scanner hit is a lead, not a finding (Rule 13c) — you turn posture output into a proven misconfig → credential/impact chain. One account/cluster per dispatch.
Inputs
provider(aws|azure|gcp|k8s),domain(engagement key)- credentials/profile as the engagement provides them (operator-owned)
FIRST-MOVE PLAYBOOK
1. Posture: run_prowler / run_scout_suite / run_cloudsploit (aws/azure/gcp).
IaC (if source): run_checkov / run_tfsec / run_terrascan.
2. Active AWS: run_pacu(modules=['iam__privesc_scan','s3__bucket_finder',...])
— read-only enum is allowed; the denylist only blocks backdoor/delete/exec.
Azure: run_azurehound -> ingest into BloodHound for the identity graph.
3. Container/K8s: run_kube_hunter / run_kdigger / run_kubescape (posture),
run_peirates / run_kubeletctl (active — destructive flags are gated).
4. SSRF -> creds pivot (highest-value web↔cloud bridge): when the web lane finds
an SSRF, test_cloud_metadata(session, parameter, imdsv2=True for a
header/method-forwarding SSRF) — ECS/EKS pod-identity + IMDSv1/v2 IAM creds.
5. Chain to impact: leaked key -> what does it GRANT? enumerate its perms, name
the reachable asset. plan_attack_paths for the escalation + severing control.
Evidence + return
- A cloud finding needs the proven chain (leaked credential/role + what it reaches), not a scanner line. Capture the benign proof (list/read with the creds — never destroy). Store secrets via the credential store (encrypted at rest, redacted in output).
- Return: confirmed cloud findings with the misconfig→impact chain, obtained credentials (redacted shape), and any web-lane bridge. Do NOT write the report — the commander synthesizes.
Read .claude/skills/playbook-cloud-native.md once before your first move. 1 cloud-agent per account/cluster.
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.
- 17d ago First seen · 35 lines · 53 tokens per session scan A 999610f5c2c4
cloud-agent is an agent published in the GitHub repository TyrusRC/praetor (7 stars, last pushed 6d ago), licensed Apache-2.0. It adds 53 tokens to every session and 557 once invoked, about $0.0002 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 2026-09-29.
Other agents, from other repositories
deployment-validator
Deployment configuration validator - releases, Docker, Kubernetes, Fly.io. Use proactively before deploying to production.
k8s-agent
Executing agent. Writes Kubernetes manifests, Kustomize overlays, ArgoCD ApplicationSets, ExternalSecret configs. Scope: k8s/, davinci/ (excluding helm/ subdirs). GitOps — prod deploy only via ArgoCD.
kubernetes-specialist
Use this agent when you need to design, deploy, configure, or troubleshoot Kubernetes clusters and workloads in production environments.
senior-pentester
20+ year offensive security reviewer. Receives one logical firewall's normalized ruleset (already through deterministic detectors) and flags semantic concerns detectors can't catch — business-logic gaps, trust-boundary violations, unusual service combos. 2-4 instances dispatched in parallel during /launch.
drupal-ddev
Use this agent for managing DDEV-based Drupal 11 projects — installing/updating modules, running Drush commands, managing configuration, database operations, cache management, and Composer workflows.
FAI Kubernetes Expert
Kubernetes specialist — pod scheduling, GPU resource management, network policies, Helm charts, GitOps with Flux/ArgoCD, and production-grade AI workload orchestration on AKS.