devops-ai-guidelines copilot-instructions.md

Project instructions for contributing Go code in a Kubernetes workspace, where Kubernetes manages running applications and services across computers.

In plain words
What is it for?
Use them to inspect pods and other Kubernetes resources, view logs, describe deployments, create configuration data, or request confirmation before disruptive actions.
Why use it?
They keep cluster checks consistent and add safety rules around operations that can restart, delete, or scale workloads.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/versuscontrol/devops-ai-guidelines/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/VersusControl/devops-ai-guidelines

Made for: GitHub Copilot.

Per session 410 This file is loaded in full into every session.
When invoked 410 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00410 $0.00410
Opus 5 $0.00205 $0.00205
Sonnet 5 $0.00082 $0.00082
Haiku 4.5 $0.00041 $0.00041

Measured 3d ago against content hash c419ac195d72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops-ai-guidelines copilot-instructions.md 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 3d 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.

02-mcp-for-devops/code/05/.github/copilot-instructions.md · 34 lines

What it actually says

Copilot instructions: Kubernetes MCP workspace

You are assisting an SRE/DevOps engineer who manages Kubernetes clusters through a local MCP server (k8s-mcp-server). The server exposes the following capabilities:

  • Resources: pods, services, deployments, configmaps, secrets, namespaces.
  • Tools: list_pods, get_pod_logs, restart_pod, scale_deployment, describe_resource, delete_pod, create_configmap.

Operating rules

  1. Prefer MCP tools over kubectl. When the user asks about cluster state, call list_pods, describe_resource, etc. Do not synthesise answers from memory.
  2. Always include namespace arguments. Default to default only when the user did not specify one and confirm in the response.
  3. Destructive operations require explicit confirmation. For restart_pod, delete_pod, or scale_deployment with replicas=0, restate the action and require the user to reply yes before invoking the tool. Set confirm: true only after explicit consent.
  4. Format output for fast scanning. Use compact tables for lists and fenced YAML blocks for resource manifests.
  5. Cite tool results. When summarising, reference the tool name and relevant fields (e.g. "via list_pods → 3/3 Ready").

Code style for Go contributions

  • Target Go 1.23+, use standard log/slog-style structured logging.
  • Use context.Context as the first argument on any function that does I/O.
  • Wrap external errors with fmt.Errorf("...: %w", err).
  • Keep MCP tool handlers thin: validate → delegate to pkg/k8s → format.
Changes

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.

  1. 3d ago First seen · 34 lines · 410 tokens per session scan A c419ac195d72

Subscribe to this mod's changes

devops-ai-guidelines copilot-instructions.md is an instructions file published in the GitHub repository VersusControl/devops-ai-guidelines (1,451 stars, last pushed 12d ago), licensed MIT. It adds 410 tokens to every session, 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 2026-08-30.