fully-automated-prompt-optimization: Agent for Claude Code

.claude/agents/k8s-manager.md

k8s-manager is an agent for Claude Code from cisco-foundation-ai/fully-automated-prompt-optimization. It costs 83 tokens per session (1,703 once invoked), scanned A, original, Apache-2.0.

A Kubernetes namespace operator. Kubernetes is a system for running and managing containerized applications, while a namespace is an isolated workspace within a cluster.

In plain words
What is it for?
Use it to review pods, deployments, services, and storage claims; check pod health and usage; clean up stale resources; and launch workloads in a namespace.
Why use it?
It gives one place to inspect application resources, check whether workloads are healthy, track their resource use, remove stale items, and start workloads. It also checks that the correct namespace and cluster connection are available first.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is cisco-foundation-ai/fully-automated-prompt-optimization's own configuration. It tells Claude Code how to work on fully-automated-prompt-optimization itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fully-automated-prompt-optimization configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cisco-foundation-ai/fully-automated-prompt-optimization. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cisco-foundation-ai/fully-automated-prompt-optimization/main/.claude/agents/k8s-manager.md
Clone the repo
git clone --depth 1 https://github.com/cisco-foundation-ai/fully-automated-prompt-optimization

Made for: Claude Code.

Wrote 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.

agentmods badge for k8s-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/cisco-foundation-ai/fully-automated-prompt-optimization/k8s-manager/github.svg)](https://agentmods.dev/agents/cisco-foundation-ai/fully-automated-prompt-optimization/k8s-manager)
Your own site
<a href="https://agentmods.dev/agents/cisco-foundation-ai/fully-automated-prompt-optimization/k8s-manager"><img src="https://agentmods.dev/badge/agents/cisco-foundation-ai/fully-automated-prompt-optimization/k8s-manager/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.

agentmods 80×15 button for k8s-manager

Your own site · 80×15
<a href="https://agentmods.dev/agents/cisco-foundation-ai/fully-automated-prompt-optimization/k8s-manager"><img src="https://agentmods.dev/badge/agents/cisco-foundation-ai/fully-automated-prompt-optimization/k8s-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,703 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00083 $0.01703
Opus 5 $0.00042 $0.00851
Sonnet 5 $0.00017 $0.00341
Haiku 4.5 $0.00008 $0.00170

Measured 11d ago against content hash 45c203726ee3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

k8s-manager 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 11d 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.

.claude/agents/k8s-manager.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

K8s Namespace Manager Agent

You manage Kubernetes resources within a single namespace. You inspect pods, deployments, services, and PVCs; clean up stale resources; launch known and arbitrary workloads; and track resource usage.

Prerequisites

Run these checks on every invocation before doing anything else.

  1. Source .envrc: run source .envrc from the project root. If the file is not present in the current worktree, check the main worktree as a fallback (the user uses direnv).
  2. Verify $NAMESPACE: if $NAMESPACE is not set after sourcing, ask the user and stop.
  3. Verify cluster connectivity: run kubectl --namespace "$NAMESPACE" cluster-info. If it fails, report the error and stop.

Critical rule

Every kubectl command MUST include --namespace $NAMESPACE. Never use -A or --all-namespaces. Never omit the namespace flag.

Capabilities

1. Namespace health overview

When asked for status, overview, or health, gather and present:

  • Pods: kubectl --namespace $NAMESPACE get pods -o wide (name, status, age, restarts)
  • Resource usage: kubectl --namespace $NAMESPACE top pods (fall back to parsing resource requests/limits from pod specs via kubectl --namespace $NAMESPACE get pods -o json if metrics-server is unavailable)
  • Deployments: kubectl --namespace $NAMESPACE get deployments (ready/desired replicas)
  • Services: kubectl --namespace $NAMESPACE get services
  • PVCs: kubectl --namespace $NAMESPACE get pvc
  • Stale resource flags: classify pods per the staleness table below
  • Aggregate resources: sum CPU/memory requests and limits across all running pods

Present results as a clear summary table. Flag any stale or unhealthy resources prominently.

2. Resource inspection

For detailed inspection of a single resource:

  • kubectl --namespace $NAMESPACE describe pod <name>
  • kubectl --namespace $NAMESPACE logs <name> --tail=100
  • kubectl --namespace $NAMESPACE top pod <name>

Read the full file on GitHub · 150 lines

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. 11d ago First seen · 150 lines · 83 tokens per session scan A 45c203726ee3

Subscribe to this mod's changes

k8s-manager is an agent published in the GitHub repository cisco-foundation-ai/fully-automated-prompt-optimization (107 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 1,703 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 2026-08-30.