k8s-troubleshoot-mcp: Instructions file for Claude Code

CLAUDE.md

k8s-troubleshoot-mcp CLAUDE.md is an instructions file for Claude Code from NanaGyamfiPrempeh30/k8s-troubleshoot-mcp. It costs 1,230 tokens per session, scanned A, original, MIT.

A set of project instructions for working on a read-only Kubernetes diagnostics server. Kubernetes is software for running and managing containers, and an MCP server makes tools available to an AI assistant.

In plain words
What is it for?
Use it when modifying or reviewing this Kubernetes diagnostics project, especially its error handling, access permissions, API choices, and per-file test requirements.
Why use it?
It records project rules, security constraints, known design properties, and important warnings so changes can follow the repository's intended behavior. It also identifies claims in a task file that should not be trusted as proof of completed work.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is NanaGyamfiPrempeh30/k8s-troubleshoot-mcp's own configuration. It tells Claude Code how to work on k8s-troubleshoot-mcp 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 k8s-troubleshoot-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NanaGyamfiPrempeh30/k8s-troubleshoot-mcp. 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/NanaGyamfiPrempeh30/k8s-troubleshoot-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/NanaGyamfiPrempeh30/k8s-troubleshoot-mcp

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-troubleshoot-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nanagyamfiprempeh30/k8s-troubleshoot-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/nanagyamfiprempeh30/k8s-troubleshoot-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nanagyamfiprempeh30/k8s-troubleshoot-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nanagyamfiprempeh30/k8s-troubleshoot-mcp/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.

agentmods 80×15 button for k8s-troubleshoot-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nanagyamfiprempeh30/k8s-troubleshoot-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nanagyamfiprempeh30/k8s-troubleshoot-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,230 This file is loaded in full into every session.
When invoked 1,230 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01230 $0.01230
Opus 5 $0.00615 $0.00615
Sonnet 5 $0.00246 $0.00246
Haiku 4.5 $0.00123 $0.00123

Measured 12d ago against content hash f59324f4dc2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

k8s-troubleshoot-mcp CLAUDE.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 12d 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.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project context

Read-only K8s diagnostics MCP server. Security-critical. Spec: requirements.md (68 EARS requirements) Design: design.md (18 correctness properties, P1-P18)

v0.2.0 backlog: migrate get_endpoints from core/v1 Endpoints to discovery.k8s.io/v1 EndpointSlice. Endpoints is deprecated (warning on every read as of 1.33) but still served and independently populated — not urgent. Requires DiscoveryV1Api added to K8sClients plus endpointslices RBAC rule — threat-model-touching change per design.md:184-187, needs deliberate spec review, not a drive-by fix.

reason fields are treated as low-risk/enum-like by default; this is a per-tool tradeoff, not global — re-verify for each new resource type since provisioner/controller-authored reason fields (e.g., PVC, CRDs) may not hold the same guarantee as core K8s controllers.

Do NOT trust .kiro/specs/tasks.md

It falsely claims work was completed that was never written. Ignore it as a source of truth. It can be regenerated later once real progress exists.

Non-negotiable rules

  • Never propagate exceptions to MCP layer — all errors return structured dicts
  • pods/log is a distinct RBAC rule, never folded under pods
  • Events tools use EventsV1Api, never CoreV1Api
  • No kubeconfig fallback — explicit path only, no in-cluster/default chain
  • Run pytest tests/ after every file change
  • Do not mark a task complete until its property test passes

Escaping rule (added after get_pod_events gap)

Any field in design.md's data model containing free-text "message" or "reason" that originates from cluster objects (not fixed K8s enums) must route through serialize_log_content. This applies to node conditions, event messages, and any future tool with similar fields. Do not mark a tool complete without confirming this explicitly.

Two independent mechanisms enforce this rule and neither replaces the other: Property 17 (tests/property/test_p17_escaping_applied.py) poisons every field of every K8s object a tool reads and fails if anything unescaped reaches the response — it catches leakage of fields the model INCLUDES, but is blind to fields the model OMITS, since an omitted field emits no poison and passes silently; the point-of-omission comment rule below covers exactly that blind spot. P17 passing does not mean the omission comments are unnecessary.

Read the full file on GitHub · 96 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. 12d ago First seen · 96 lines · 1,230 tokens per session scan A f59324f4dc2b

Subscribe to this mod's changes

k8s-troubleshoot-mcp CLAUDE.md is an instructions file published in the GitHub repository NanaGyamfiPrempeh30/k8s-troubleshoot-mcp (0 stars, last pushed 18d ago), licensed MIT. It adds 1,230 tokens to every session, about $0.0062 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 2026-08-31.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,126 tokens

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens