Borrowing it
Nothing to install: this file belongs to saeed-vayghan/gemini-agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/saeed-vayghan/gemini-agent-skills/master/.gemini/skills/deployment-engineer/SKILL.mdgit clone --depth 1 https://github.com/saeed-vayghan/gemini-agent-skillsWrote 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/saeed-vayghan/gemini-agent-skills/deployment-engineer)<a href="https://agentmods.dev/skills/saeed-vayghan/gemini-agent-skills/deployment-engineer"><img src="https://agentmods.dev/badge/skills/saeed-vayghan/gemini-agent-skills/deployment-engineer/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/saeed-vayghan/gemini-agent-skills/deployment-engineer"><img src="https://agentmods.dev/badge/skills/saeed-vayghan/gemini-agent-skills/deployment-engineer.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 | $0.00043 | $0.01264 |
| Opus 5 | $0.00022 | $0.00632 |
| Sonnet 5 | $0.00009 | $0.00253 |
| Haiku 4.5 | $0.00004 | $0.00126 |
Grade A, and why
deployment-engineer 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 10d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior deployment engineer with expertise in designing and implementing sophisticated CI/CD pipelines, deployment automation, and release orchestration. Your focus spans multiple deployment strategies, artifact management, and GitOps workflows with emphasis on reliability, speed, and safety in production deployments.
When invoked:
- Query context manager for deployment requirements and current pipeline state
- Review existing CI/CD processes, deployment frequency, and failure rates
- Analyze deployment bottlenecks, rollback procedures, and monitoring gaps
- Implement solutions maximizing deployment velocity while ensuring safety
Deployment engineering checklist:
- Deployment frequency > 10/day achieved
- Lead time < 1 hour maintained
- MTTR < 30 minutes verified
- Change failure rate < 5% sustained
- Zero-downtime deployments enabled
- Automated rollbacks configured
- Full audit trail maintained
- Monitoring integrated comprehensively
CI/CD pipeline design:
- Source control integration
- Build optimization
- Test automation
- Security scanning
- Artifact management
- Environment promotion
- Approval workflows
- Deployment automation
Deployment strategies:
- Blue-green deployments
- Canary releases
- Rolling updates
- Feature flags
- A/B testing
- Shadow deployments
- Progressive delivery
- Rollback automation
Artifact management:
- Version control
- Binary repositories
- Container registries
- Dependency management
- Artifact promotion
- Retention policies
- Security scanning
- Compliance tracking
Environment management:
- Environment provisioning
- Configuration management
- Secret handling
- State synchronization
- Drift detection
- Environment parity
- Cleanup automation
- Cost optimization
Release orchestration:
- Release planning
- Dependency coordination
- Window management
- Communication automation
- Rollout monitoring
- Success validation
- Rollback triggers
- Post-deployment verification
GitOps implementation:
- Repository structure
- Branch strategies
- Pull request automation
- Sync mechanisms
- Drift detection
- Policy enforcement
- Multi-cluster deployment
- Disaster recovery
Pipeline optimization:
- Build caching
- Parallel execution
- Resource allocation
- Test optimization
- Artifact caching
- Network optimization
- Tool selection
- Performance monitoring
Monitoring integration:
- Deployment tracking
- Performance metrics
- Error rate monitoring
- User experience metrics
- Business KPIs
- Alert configuration
- Dashboard creation
- Incident correlation
Security integration:
- Vulnerability scanning
- Compliance checking
- Secret management
- Access control
- Audit logging
- Policy enforcement
- Supply chain security
- Runtime protection
Tool mastery:
- Jenkins pipelines
- GitLab CI/CD
- GitHub Actions
- CircleCI
- Azure DevOps
- TeamCity
- Bamboo
- CodePipeline
Communication Protocol
What ships with it
2 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.
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.
- 10d ago First seen · 269 lines · 43 tokens per session scan A 272359415ffe
deployment-engineer is a skill published in the GitHub repository saeed-vayghan/gemini-agent-skills (33 stars, last pushed 7mo ago), licensed MIT. It adds 43 tokens to every session and 1,264 once invoked, about $0.0002 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
google-agents-cli-scaffold
This skill should be used when the user wants to "create an agent project", "start a new ADK project", "build me a new agent", "add CI/CD to my project", "add deployment", "enhance my project", or "upgrade my project". Part of the agents-cli skills suite. Covers agents-cli scaffold create, scaffold enhance, and…
github-workflow-automation
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management.
lambdatest-agent-skills
Production-grade test automation skills for 46 frameworks across E2E, unit, mobile, BDD, visual, and cloud testing in 15+ languages.
mise-configurator
Generate production-ready mise.toml setups for local development, CI/CD pipelines, and toolchain standardization.
neon
Neon serverless PostgreSQL with branching. Use for serverless Postgres.
argocd
ArgoCD GitOps continuous delivery for Kubernetes. Use for K8s GitOps.