What is klustr AGENTS.md?

Repository guidance for Klustr, a desktop application for managing Kubernetes clusters. Kubernetes is software for running and managing containerised applications, and Klustr connects to it through the user's existing configuration.

Use it when working on cluster contexts, resource updates, logs, command execution, port forwarding, permissions, custom resources, Helm, Argo CD, or the desktop interface.

It explains the application's architecture and live-data patterns so an agent can debug or extend cluster views without guessing how state and Kubernetes resources are handled.

How SametKUM/klustr configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to SametKUM/klustr. 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/SametKUM/klustr/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/SametKUM/klustr

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sametkum/klustr/agents-md/github.svg)](https://agentmods.dev/instructions/sametkum/klustr/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/sametkum/klustr/agents-md"><img src="https://agentmods.dev/badge/instructions/sametkum/klustr/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sametkum/klustr/agents-md"><img src="https://agentmods.dev/badge/instructions/sametkum/klustr/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,785 This file is loaded in full into every session.

When invoked 2,785 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02785	$0.02785
Opus 5.5	$0.01114	$0.01114
Sonnet 5.5	$0.00557	$0.00557
Haiku 4.5	$0.00279	$0.00279

Measured 3d ago against content hash b6b8dcde37f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

klustr AGENTS.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.

AGENTS.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Klustr

Cross-platform Kubernetes desktop client: multi-context cluster management with live resource lists, logs, exec, port-forwarding and RBAC-aware views of every built-in kind. Beyond the core API, Klustr gives widely used ecosystem tools first-class support — dedicated views and actions instead of raw YAML — and growing that set is the product's main direction. Any CRD without a dedicated integration is still browsable generically. Klustr is a pure client — it drives the Kubernetes API with the user's kubeconfig and installs nothing in the cluster. The one exception is the opt-in metrics-server install, which Klustr can remove again by the label it stamps.

Layout

internal/kube/ holds everything that talks to a cluster and imports nothing from Wails, so it stays testable with plain go test; doc.go has the package overview. Files are split per sidebar group: informers_<group>.go (list types and listers), details_<group>.go (detail builders), manager_<group>.go (ClientManager forwarders).
app/ is the thin Wails binding layer over ClientManager — the only part a CLI or web mode would replace. App is a Wails v3 service; main.go builds the application and its one window.
frontend/src/lib/wails/bindings/ and frontend/src/lib/api.generated.ts are generated: change the Go side and run wails3 task bindings (wails3 dev does it on every Go change) instead of editing them; CI fails while the bindings are stale. frontend/src/lib/api.ts is only for bindings that need real normalization on top. frontend/src/lib/integrationCatalog.generated.ts is generated from the Go integration catalog (see below).
frontend/src/lib/wailsCall.ts gives the generated bindings the shapes the frontend relies on: slices and maps typed non-null, and a rejected call carrying the Go error's message as a string. frontend/src/lib/runtime.ts wraps the Wails runtime (events, browser, clipboard); import it, not @wailsio/runtime.
The landing site and user guides live in SametKUM/klustr.dev. When a change alters behavior a guide describes, point it out so the guide can be updated there in its own pull request.

Read the full file on GitHub · 83 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.

3d ago Changed · +4 lines · +278 tokens per session b6b8dcde37f6
23d ago Changed · +6 lines · +422 tokens per session 6ab5a772b15f
1mo ago Changed · +34 tokens per session 7542b00eb953
1mo ago Changed · -411 lines · -7,697 tokens per session scan C → A 672d6c234286
1mo ago Changed · -49 lines · -1,658 tokens per session 657e7832d2fe
1mo ago Changed · +50 lines · +1,746 tokens per session 9112cc338707
2mo ago First seen · 483 lines · 9,660 tokens per session scan C 4fe4d54aefe2

Subscribe to this mod's changes

klustr AGENTS.md is an instructions file published in the GitHub repository SametKUM/klustr (184 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,785 tokens to every session, about $0.0111 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 2026-08-30.

DevOps and cloud argocd cloud-native cncf desktop-app gateway-api

klustr AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
klustr AGENTS.mdSametKUM/klustr	Instructions file	184	4d ago	Apache-2.0	A	2,785	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

klustr: Instructions file for Codex