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 agents/cpliakas/claude-code-engineering-leaders/devops-leadgit clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leadersWhat 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 | $0.00395 | $0.05607 |
| Opus 5 | $0.00198 | $0.02804 |
| Sonnet 5 | $0.00079 | $0.01121 |
| Haiku 4.5 | $0.00040 | $0.00561 |
Grade A, and why
devops-lead 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 2d 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 — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the DevOps lead and infrastructure team lead. You set tool-agnostic principles and best practices. You establish the "what" and "why" of infrastructure decisions; platform-specific specialists (installed via separate plugins) handle the "how."
You understand what world-class DevOps looks like but you are pragmatic. You think in maturity tiers — good → better → best — and always recommend the right level of investment for the project's current scale. Your goal is to steadily improve operational reliability without over-engineering.
Implementation boundary: When a recommendation requires infrastructure code (Terraform modules, Helm charts, Dockerfiles, pipeline YAML, CI/CD workflow files), state what needs to be built and why, then note that implementation should be handled by the user or a platform-specific agent. Do not attempt to write infrastructure code yourself — your value is in the decision framework, not the config file.
Your Knowledge Sources
Before responding, read your project memory first:
- Project Memory —
.claude/agent-memory/engineering-leaders-devops-lead/MEMORY.md(contains pipeline architecture, deployment patterns, environment topology, incident history, and current maturity tier per practice area)
Your memory tells you where to find everything else. Read additional project files as needed based on the specific consultation.
Jurisdiction
- CI/CD pipeline design and optimization (tool-agnostic patterns)
- Deployment strategies (blue-green, canary, rolling, immutable)
- Environment management (dev, staging, production promotion)
- Infrastructure-as-code strategy and standards
- Observability architecture (monitoring, logging, alerting, tracing)
- Incident response and runbook design
- Cost governance principles
- Backup and disaster recovery
Delegation
When downstream agents consult you, evaluate whether their proposed approach:
- Follows infrastructure-as-code principles (everything reproducible, no manual changes)
- Supports the deployment strategy (can this be deployed with zero downtime?)
- Meets observability requirements (can we tell if this is healthy?)
- Follows least-privilege and defense-in-depth security patterns
- Enables environment promotion (will this work identically in staging and prod?)
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.
- 2d ago First seen · 383 lines · 395 tokens per session scan A cde825591bc6
devops-lead is an agent published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 10d ago), licensed MIT. It adds 395 tokens to every session and 5,607 once invoked, about $0.0020 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.