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 agentmods add skills/rajitsaha/100xprism/cloud-securitynpx skills add rajitsaha/100xprism --skill cloud-securitygit clone --depth 1 https://github.com/rajitsaha/100xprismWrote 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/rajitsaha/100xprism/cloud-security)<a href="https://agentmods.dev/skills/rajitsaha/100xprism/cloud-security"><img src="https://agentmods.dev/badge/skills/rajitsaha/100xprism/cloud-security.svg" alt="Measured on agentmods" 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 | $0.00056 | $0.03643 |
| Opus 5 | $0.00028 | $0.01821 |
| Sonnet 5 | $0.00011 | $0.00729 |
| Haiku 4.5 | $0.00006 | $0.00364 |
Grade A, and why
cloud-security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Security — Cloud Security & Data Privacy Scan
Covers GCP infrastructure hardening, data privacy (PII/GDPR/CCPA), API security, container security, and compliance.
Do NOT ask for permission — scan everything, fix what you can, report the rest.
Step 0 — Detect cloud config
PROJECT_ROOT=$(git rev-parse --show-toplevel)
INSTRUCTION_FILE=$(for f in CLAUDE.md AGENTS.md .cursorrules; do [ -f "$PROJECT_ROOT/$f" ] && echo "$PROJECT_ROOT/$f" && break; done)
GCP_PROJECTS=$(grep -rh "GCP_PROJECT\|GOOGLE_CLOUD_PROJECT\|gcloud.*--project" ${INSTRUCTION_FILE:-/dev/null} .env.example terraform/ 2>/dev/null | grep -oE '[a-z][a-z0-9-]{4,28}' | sort -u | grep -v "^--" || true)
HAS_DOCKER=$(ls Dockerfile docker-compose.yml 2>/dev/null | head -1 || true)
HAS_TERRAFORM=$(ls terraform/*.tf infra/*.tf 2>/dev/null | head -1 || true)
Section 1 — GCP IAM & Access Control
For each GCP project detected:
for PROJECT in $GCP_PROJECTS; do
echo "=== IAM: $PROJECT ==="
gcloud projects get-iam-policy "$PROJECT" --format=json 2>/dev/null \
| python3 -c "
import sys,json
p=json.load(sys.stdin)
bad=['roles/editor','roles/owner','roles/iam.securityAdmin','roles/storage.admin']
[print('[HIGH]',b['role'],m) for b in p.get('bindings',[]) for m in b['members'] if b['role'] in bad and ('serviceAccount' in m or 'allUsers' in m)]"
gcloud iam service-accounts list --project="$PROJECT" --format="value(email)" 2>/dev/null \
| while read SA; do
n=$(gcloud iam service-accounts keys list --iam-account="$SA" --filter="keyType=USER_MANAGED" --format="value(KEY_ID)" 2>/dev/null | wc -l)
[ "$n" -gt 0 ] && echo "[HIGH] $SA: $n user-managed key(s) — use Workload Identity instead"
done
gcloud projects get-iam-policy "$PROJECT" --format=json 2>/dev/null | grep -E "allUsers|allAuthenticatedUsers" && echo "[CRITICAL] Public IAM binding found" || true
done
Section 2 — GCP Network & Firewall
for PROJECT in $GCP_PROJECTS; do
echo "=== Network: $PROJECT ==="
gcloud compute firewall-rules list --project="$PROJECT" --format=json 2>/dev/null \
| python3 -c "
import sys,json
sp={'22','3389','5432','6379','3306','27017','6443'}
[print('[CRITICAL] Firewall',r['name'],'port',p,'open to 0.0.0.0/0') for r in json.load(sys.stdin) if '0.0.0.0/0' in r.get('sourceRanges',[]) or '::/0' in r.get('sourceRanges',[]) for a in r.get('allowed',[]) for p in a.get('ports',[]) if str(p) in sp]"
gcloud sql instances list --project="$PROJECT" --format=json 2>/dev/null \
| python3 -c "
import sys,json
for i in json.load(sys.stdin):
n,ip=i['name'],i.get('settings',{}).get('ipConfiguration',{})
[print('[CRITICAL] Cloud SQL',n,'public IP open to',net['value']) if net.get('value') in ('0.0.0.0/0','::/0') else print('[MEDIUM] Cloud SQL',n,'public IP enabled') for net in ip.get('authorizedNetworks',[])] if ip.get('ipv4Enabled') else None
print('[HIGH] Cloud SQL',n,'SSL not required') if not ip.get('requireSsl') and ip.get('sslMode','')!='ENCRYPTED_ONLY' else print('[PASS] Cloud SQL',n,'SSL enforced')
print('[HIGH] Cloud SQL',n,'backups disabled') if not i.get('settings',{}).get('backupConfiguration',{}).get('enabled') else None"
done
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.
- 4d ago First seen · 239 lines · 56 tokens per session scan A f98cbf3e32c2
cloud-security is a skill published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 3,643 once invoked, about $0.0003 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
kubernetes-operator
Deploy and manage applications on Kubernetes. Covers deployments, services, ingress, HPA, secrets, and production-grade cluster configuration.
terraform-builder
Build infrastructure as code with Terraform. Covers module design, state management, AWS/GCP/Azure resources, and production-grade practices.
data-pipeline
Professional Data Pipeline Expert skill. Build robust, automated deployment pipelines and configure cloud infrastructure as code.
auto-scaler
Professional Auto Scaler Expert skill. Build robust, automated deployment pipelines and configure cloud infrastructure as code.
aws-architect
Professional Aws Architect skill. Build robust, automated deployment pipelines and configure cloud infrastructure as code.
azure-developer
Professional Azure Developer skill. Build robust, automated deployment pipelines and configure cloud infrastructure as code.