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/matanryngler/deployshield/gemininpx skills add matanryngler/deployshield --skill geminigit clone --depth 1 https://github.com/matanryngler/deployshieldWrote 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/matanryngler/deployshield/gemini)<a href="https://agentmods.dev/skills/matanryngler/deployshield/gemini"><img src="https://agentmods.dev/badge/skills/matanryngler/deployshield/gemini.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 | $0.00020 | $0.00278 |
| Opus 5 | $0.00010 | $0.00139 |
| Sonnet 5 | $0.00004 | $0.00056 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
gemini 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.
What it actually says
DeployShield for Gemini CLI
DeployShield is active. All Bash commands are validated before execution.
Guarded CLIs
- Cloud: aws, gcloud, az, kubectl, helm, terraform, pulumi
- Database: psql, mysql, mongosh, redis-cli
- IaC: cdk, sam, serverless, ansible-playbook
- Other: vault, gh, docker, podman, npm, yarn, pnpm, cargo, twine, gem
Safety Guidelines
- Use read-only commands (get, list, describe) to inspect state.
- Suggest --dry-run or plan where applicable.
- To allow writes in specific contexts, create a
.deployshield.jsonfile.
Integration
This skill uses the core DeployShield validator via a BeforeTool hook on the run_shell_command tool.
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 · 33 lines · 20 tokens per session scan A 1f26ddf14baa
gemini is a skill published in the GitHub repository matanryngler/deployshield (3 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 278 once invoked, about $0.0001 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
awesome-kubernetes-ops
This skill documents the local verification, editing, and deployment procedures for the Antigravity AI Agent when pair-programming with the repository maintainer.
Cloud Security & Container Hardening
AWS/Azure/GCP security auditing, container and Kubernetes hardening, Infrastructure as Code scanning, and cloud compliance assessment.
cis-aws-foundations-2.1.2
Ensure authorization guardrails for all AWS Organization accounts.
debug-ml-inference
Debug ML inference issues — latency spikes, wrong predictions, event loop blocking.
drift-detection
Run and interpret DATA drift (PSI) AND CONCEPT drift (sliced performance) for an ML service.
performance-degradation-rca
End-to-end RCA for a performance-degradation incident — correlates sliced metrics, drift, deploy history, upstream data changes, and prediction logs into one evidence-backed root cause.