agentmods.dev

teardown-llm-d

teardown-llm-d is a skill for Claude Code, Codex from llm-d-incubation/llm-d-skills. It costs 128 tokens per session (3,787 once invoked), scanned A, original, Apache-2.0.

A cleanup procedure for removing an llm-d language-model serving deployment from a Kubernetes namespace. It supports Helm and Kustomize deployments and asks for confirmation before deleting resources.

In plain words
What is it for?
Inspecting an llm-d deployment, uninstalling Helm releases, removing Kustomize-managed resources when their files are available, and freeing the namespace's cluster resources.
Why use it?
Leaving unused model-serving resources running consumes cluster capacity. Removing them safely requires first identifying what is installed and which namespace it belongs to.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 7repo changed 15d ago A scan 128 tokens original Apache-2.0

Good fit Inspecting an llm-d deployment, uninstalling Helm releases, removing Kustomize-managed resources when their files are available, and freeing the namespace's cluster resources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/llm-d-incubation/llm-d-skills/teardown-llm-d
View source ↗ llm-d-incubation/llm-d-skills
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.

Any agent
npx skills add llm-d-incubation/llm-d-skills --skill teardown-llm-d
Clone the repo
git clone --depth 1 https://github.com/llm-d-incubation/llm-d-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin teardown-llm-d — /plugin install teardown-llm-d after adding the marketplace above.

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 teardown-llm-d

README.md
[![agentmods](https://agentmods.dev/badge/skills/llm-d-incubation/llm-d-skills/teardown-llm-d/github.svg)](https://agentmods.dev/skills/llm-d-incubation/llm-d-skills/teardown-llm-d)
Your own site
<a href="https://agentmods.dev/skills/llm-d-incubation/llm-d-skills/teardown-llm-d"><img src="https://agentmods.dev/badge/skills/llm-d-incubation/llm-d-skills/teardown-llm-d/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 teardown-llm-d

Your own site · 80×15
<a href="https://agentmods.dev/skills/llm-d-incubation/llm-d-skills/teardown-llm-d"><img src="https://agentmods.dev/badge/skills/llm-d-incubation/llm-d-skills/teardown-llm-d.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,787 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 $0.00128 $0.03787
Opus 5.5 $0.00051 $0.01515
Sonnet 5.5 $0.00026 $0.00757
Haiku 4.5 $0.00013 $0.00379

Measured 15d ago against content hash 691ddb117522, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

teardown-llm-d 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 15d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/inventory.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/teardown-llm-d/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teardown llm-d Stack

Purpose

Cleanly remove a deployed llm-d stack from a Kubernetes namespace. An llm-d v1.0 stack consists of:

Part Created by Removed by
Router: EPP Deployment, Services <guide>-epp and <guide>-epp-model-servers, ConfigMaps, Roles, the chart's ClusterRole and ClusterRoleBinding, InferencePool <guide>, and in gateway mode the HTTPRoute <guide> with provider policies `helm install llm-d-router-standalone gateway`
Model servers: Deployment (aggregated) or DisaggregatedSet (prefill/decode, wide-EP), ServiceAccount, ConfigMaps, PVCs or ResourceClaimTemplates in some overlays kubectl apply -k guides/<guide>/modelserver/<accelerator>/<engine>/<provider> the guide's cleanup.modelserver step, which is kubectl delete -k of the same overlay
Monitoring objects (PodMonitor, PodMonitoring) kubectl apply -k guides/recipes/modelserver/components/monitoring[-pd] kubectl delete -k of the same component
Guide-specific extras (objectives, render pods, Mooncake store, model-cache PVC, metrics-reader ClusterRoleBindings) guide-specific deploy steps the guide's other cleanup.* steps
Gateway llm-d-inference-gateway (gateway mode) kubectl apply -k guides/recipes/gateway/<provider> user decision (opt-in)
Secret llm-d-hf-token, PVCs, the namespace prerequisites kept unless the user asks

Workload pods carry the labels llm-d.ai/guide=<guide> and llm-d.ai/role=prefill|decode. Chart-created objects carry no llm-d.ai/guide label; they are found through helm list. The helper scripts/inventory.sh prints all of the above for a namespace.

Always confirms with the user before deleting anything.

Step 1: Locate the Stack and Set NAMESPACE

  1. If the NAMESPACE environment variable is set, use it.
  2. Otherwise check for an active oc project: 
    oc project -q 2>/dev/null
  3. If neither, ask the user for the namespace.

Read the full file on GitHub · 230 lines

Files

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.

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. 15d ago Changed · -8 lines · +14 tokens per session 691ddb117522
  2. 2mo ago First seen · 238 lines · 114 tokens per session scan A b97b213911d8

Subscribe to this mod's changes

teardown-llm-d is a skill published in the GitHub repository llm-d-incubation/llm-d-skills (7 stars, last pushed 8d ago), licensed Apache-2.0. It adds 128 tokens to every session and 3,787 once invoked, about $0.0005 per session on Opus 5.5. 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.

CloudContainersDevOps and cloud
Related

teardown-llm-d compared with skills from other repositories

teardown-llm-d next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
teardown-llm-dllm-d-incubation/llm-d-skillsSkill78d agoApache-2.0A128Claude Code, Codex
openshell-cliNVIDIA/OpenShellSkill21kyesterdayApache-2.0A134Claude Code, Codex
azd-deploymentsickn33/agentic-awesome-skillsSkill49kyesterdayMITA29Claude Code
cdf-orchestration-setupNVIDIA/skillsSkill3.9kyesterdayApache-2.0A105Codex
langbot-deploylangbot-app/LangBotSkill19kyesterdayApache-2.0B104Claude Code, Codex
compute-env-setupcompanion-inc/feynmanSkill10k6d agoMITA45Claude Code, Codex
agent-bomLeoYeAI/openclaw-master-skillsSkill2.2k6d agoMITA99Claude Code, Codex