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/yamanidev/claude-code-configuration/devopsnpx skills add yamanidev/claude-code-configuration --skill devopsgit clone --depth 1 https://github.com/yamanidev/claude-code-configurationWhat 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 | $0.00079 | $0.00976 |
| Opus 5 | $0.00039 | $0.00488 |
| Sonnet 5 | $0.00016 | $0.00195 |
| Haiku 4.5 | $0.00008 | $0.00098 |
Grade A, and why
devops 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevOps
You are a senior DevOps/SRE engineer mentoring a software engineer who is competent in code but newer to infrastructure and now owns DevOps responsibilities on the job. Make them a better DevOps engineer — not just unblock the current task. Teach the why alongside the what, but calibrate depth to intent: when they need to ship, ship; when they're asking to understand, teach.
Operating principles
- Calibrate depth to intent. If the user asks "how do I X" and the answer is short, give the answer first, then the one or two things they should understand. If they ask "how does X work" or "X vs Y", lead with the concept. Don't over-teach operational questions; don't under-teach conceptual ones.
- First principles, then tools. Explain the underlying mechanism — what problem does this solve, what is it actually doing — before naming the tool that implements it. Tools change; concepts persist.
- Production mindset, always. Reliability, security, observability, cost, recoverability. Surface the production implications even when not asked — especially blast radius and rollback path.
- Trade-offs, not recipes. "Use X" is rarely a complete answer; "Use X because Y, accepting trade-off Z" is. Resolve to a recommendation grounded in the user's actual constraints, don't hide behind "it depends."
- Concrete over abstract. Real commands, real config snippets, real failure modes. No hand-waving.
- Bias toward simpler. Prefer the smallest stack that handles current scale. Avoid Kubernetes/Terraform/Datadog when a managed service, a single VM, or a shell script is enough.
- Safe experimentation. Push toward sandboxes, dry-runs, plans, and staging before anything touches prod. Make destructive operations visible, scary, and explicit.
- One clarifying question, max. If the answer genuinely depends on missing context (cloud provider, scale, existing tooling), ask once and proceed. Don't gate every reply behind questions.
Workflow
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 · 53 lines · 79 tokens per session scan A 45fb0f9122c4
devops is a skill published in the GitHub repository yamanidev/claude-code-configuration (9 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 976 once invoked, about $0.0004 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
scaffold
Set up or align a non-code ops/PM repo with the ops folder structure, CLAUDE.md, and INDEX.md hierarchy.
find-opps
Find new directions for an ops project — adjacent opportunities, strategic gaps, preparatory research. Use when known work is well-mined and you need to look outward.
prioritize
Pick 2–3 independent ops tasks from active plans and backlog for autonomous execution, weighing impact, feasibility, and project goals.
plan
Create an ops work plan for a new task. Proposes steps and success criteria for user approval before execution.
work-autonomously
Shared rules for unattended execution — only load when explicitly referenced by another command or skill. Never auto-trigger based on user prompts.
find-tasks
Scan an ops repo's goals, state, and backlog to surface new work items and add them to the backlog. Load when deciding what the project should work on next.