Borrowing it
Nothing to install: this file belongs to Sarah-Salah/k8s-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Sarah-Salah/k8s-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/Sarah-Salah/k8s-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/sarah-salah/k8s-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/sarah-salah/k8s-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sarah-salah/k8s-mcp-server/claude-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.
<a href="https://agentmods.dev/instructions/sarah-salah/k8s-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sarah-salah/k8s-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.03169 | $0.03169 |
| Opus 5 | $0.01584 | $0.01584 |
| Sonnet 5 | $0.00634 | $0.00634 |
| Haiku 4.5 | $0.00317 | $0.00317 |
Grade C, and why
k8s-mcp-server CLAUDE.md scanned grade C with 1 finding 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 10d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- Local kubeconfig only (`~/.kube/config`) How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file is read by Claude Code at the start of every session. It defines how you (Claude) should work on this project. Read it fully before doing anything else.
1. Project Purpose
Build a production-quality Model Context Protocol (MCP) server that exposes Kubernetes cluster operations to AI assistants (Claude Desktop, Cursor, Claude Code).
The goal: let an AI assistant safely list, inspect, diagnose, and (optionally) modify Kubernetes resources via natural language.
This project will be open-sourced on GitHub as part of the maintainer's portfolio. Code quality, documentation, and security matter as much as functionality.
2. Scope
v1 (MVP — what we are building now)
- 10–12 read-only tools (list / get / describe / logs / events / metrics)
- 3 write tools behind a
--enable-writesflag (scale deployment, rollout restart, delete pod) - stdio transport only (works with Claude Desktop, Cursor, Claude Code)
- Local kubeconfig only (
~/.kube/config) - Single-user, single-cluster
- Python package, distributable via
pip installanduvx
v2 (Future — DO NOT build in v1)
- SSE / HTTP transport
- In-cluster deployment with Helm chart
- ServiceAccount + RBAC
- Multi-cluster support
- Persistent audit log
apply_manifesttool- Custom resource (CRD) support
If you are tempted to build a v2 feature "while you're in there" — stop and ask.
3. Tech Stack (non-negotiable)
| Concern | Choice |
|---|---|
| Language | Python 3.11+ |
| Package manager | uv (not pip directly, not poetry, not pdm) |
| MCP SDK | Official mcp package from Anthropic (NOT FastMCP 2.x) |
| K8s client | Official kubernetes Python client |
| Validation | pydantic v2 |
| Testing | pytest + pytest-asyncio |
| Lint + format | ruff (both) |
| Type checking | mypy --strict |
| CI | GitHub Actions |
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.
- 10d ago First seen · 306 lines · 3,169 tokens per session scan C dbc5aa213482
k8s-mcp-server CLAUDE.md is an instructions file published in the GitHub repository Sarah-Salah/k8s-mcp-server (0 stars, last pushed 3mo ago), licensed MIT. It adds 3,169 tokens to every session, about $0.0158 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).