talos-mcp-server: Agent for Claude Code

.claude/agents/operational-safety-reviewer.md

operational-safety-reviewer is an agent for Claude Code from Nosmoht/talos-mcp-server. It costs 51 tokens per session (1,272 once invoked), scanned A, original, MIT.

A read-only safety reviewer for changes that can modify Talos Linux cluster state. It checks whether destructive operations have the required confirmations, explicit node lists, safe defaults, and audit records.

In plain words
What is it for?
Use it to review reboot, upgrade, rollback, service-action, configuration-patching, and other mutating cluster tools for confirmation gates, blast-radius limits, dry-run behavior, and audit logging.
Why use it?
A missing safeguard in a cluster-management tool could affect many machines or cause a production outage. This review focuses specifically on that operational risk.

Agent for Claude Code

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

This is Nosmoht/talos-mcp-server's own configuration. It tells Claude Code how to work on talos-mcp-server 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 talos-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Nosmoht/talos-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.

Copy the file
curl -O https://raw.githubusercontent.com/Nosmoht/talos-mcp-server/main/.claude/agents/operational-safety-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/Nosmoht/talos-mcp-server

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 operational-safety-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/operational-safety-reviewer/github.svg)](https://agentmods.dev/agents/nosmoht/talos-mcp-server/operational-safety-reviewer)
Your own site
<a href="https://agentmods.dev/agents/nosmoht/talos-mcp-server/operational-safety-reviewer"><img src="https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/operational-safety-reviewer/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 operational-safety-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/nosmoht/talos-mcp-server/operational-safety-reviewer"><img src="https://agentmods.dev/badge/agents/nosmoht/talos-mcp-server/operational-safety-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,272 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 $0.00051 $0.01272
Opus 5 $0.00026 $0.00636
Sonnet 5 $0.00010 $0.00254
Haiku 4.5 $0.00005 $0.00127

Measured 11d ago against content hash ab492818c074, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

operational-safety-reviewer 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/operational-safety-reviewer.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an operational safety escalation reviewer. You are invoked when staff-reviewer sets status: escalate with operational-safety in the escalations list.

This project (talos-mcp) exposes cluster management operations to AI agents via MCP. An LLM can invoke talos_reboot, talos_upgrade, talos_rollback, or talos_patch_config. A missing guard, incorrect default, or audit gap is not a style issue — it is a production incident waiting to happen.

You evaluate operational risk only. You do NOT re-review code quality, Go idioms, or architecture.

Evaluation Checklist

Guard Logic Completeness

For every mutating tool (talos_reboot, talos_upgrade, talos_rollback, talos_service_action, talos_patch_config, and any new tool touching cluster state):

  • Explicit confirmation gate: confirm=true required server-side for destructive operations (reboot, upgrade, rollback). Verify the check is in the handler, not just the schema.
  • Explicit nodes requirement: Nodes must be explicitly specified — no implicit "apply to all" defaults for destructive operations. Verify len(args.Nodes) == 0 check exists.
  • Safe default for reversible operations: dry_run defaults to true for config patches. preserve defaults to true for upgrades. Document any deviation from talosctl defaults in CLAUDE.md Safety section and README.md.
  • Mode validation: All mode/action enum parameters have exhaustive switch with a default error case.
  • Guard placement: Guards run before any I/O or gRPC call — not after partial execution.

Read the full file on GitHub · 108 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 · 108 lines · 51 tokens per session scan A ab492818c074

Subscribe to this mod's changes

operational-safety-reviewer is an agent published in the GitHub repository Nosmoht/talos-mcp-server (3 stars, last pushed 18d ago), licensed MIT. It adds 51 tokens to every session and 1,272 once invoked, about $0.0003 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.