talos-mcp-server: Skill for Claude Code

.claude/skills/refresh-tool-inventory/SKILL.md

refresh-tool-inventory is a skill for Claude Code from Nosmoht/talos-mcp-server. It costs 52 tokens per session (620 once invoked), scanned A, original, MIT.

A tool that rebuilds the current inventory of tools, prompts, and resources from the project's internal Go code. It then compares that inventory with the tables documented in AGENTS.md and README.md.

In plain words
What is it for?
Checking registered tools, prompts, and resources, extracting their descriptions and locations, and previewing or applying updates to the inventory tables.
Why use it?
Documentation can become outdated when handlers are added, renamed, or removed. Regenerating the tables makes the documented capabilities match the source code.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions AGENTS.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/skills/refresh-tool-inventory/SKILL.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 refresh-tool-inventory

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nosmoht/talos-mcp-server/refresh-tool-inventory"><img src="https://agentmods.dev/badge/skills/nosmoht/talos-mcp-server/refresh-tool-inventory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 620 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 $0.00052 $0.00620
Opus 5 $0.00026 $0.00310
Sonnet 5 $0.00010 $0.00124
Haiku 4.5 $0.00005 $0.00062

Measured 9d ago against content hash b6606cc3a37c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

refresh-tool-inventory 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 9d 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/skills/refresh-tool-inventory/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refresh Tool Inventory

Regenerate the tool/prompt/resource tables in AGENTS.md and README.md from the source of truth (the Go packages in internal/).

Arguments

Parse $ARGUMENTS:

  • --apply — write changes. Default is dry-run (print diff only).

Key Steps

  1. Enumerate registered handlers. Grep every registration call:

    grep -nE 'mcp\.(AddTool|AddPrompt|AddResource)' \
      internal/tools internal/prompts internal/resources -r
    

    Capture kind (tool/prompt/resource), name, handler, file:line.

  2. Extract description. For each handler, Read the surrounding tool definition to pull Description: / Title: fields. If absent, record description as <missing> and flag in the report.

  3. Compute diff. Locate the inventory tables in AGENTS.md and README.md using these sentinel markers (REQUIRED — abort if missing):

    <!-- inventory:tools:start -->  ...  <!-- inventory:tools:end -->
    <!-- inventory:prompts:start --> ...  <!-- inventory:prompts:end -->
    <!-- inventory:resources:start --> ...  <!-- inventory:resources:end -->
    

    If any sentinel is missing, abort with: ERROR: sentinel <name> missing in <file> — add markers before re-running. Never guess table boundaries.

  4. Emit preview. Print the unified diff between the current tables and the regenerated tables.

  5. Apply (only if --apply). Use Edit to replace the content between each matching sentinel pair. Leave everything outside the sentinels untouched.

Output Format

Inventory diff (tools | prompts | resources):
  Added:    <name> (<kind>) — <file:line>
  Removed:  <name> (<kind>)
  Renamed:  <old> → <new>
  Changed:  <name> — description updated

Files that would be updated: AGENTS.md, README.md
Mode: dry-run | apply

On dry-run, print the diff and exit. On --apply, also write and print the final file paths.

Notes

Prefer promoting the extraction step to a deterministic shell or Go script under scripts/ once the format stabilises — this skill should then shrink to "invoke the script, preview, apply" (per the project's deterministic hierarchy rule).

Read the full file on GitHub · 74 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. 9d ago First seen · 74 lines · 52 tokens per session scan A b6606cc3a37c

Subscribe to this mod's changes

refresh-tool-inventory is a skill published in the GitHub repository Nosmoht/talos-mcp-server (3 stars, last pushed 16d ago), licensed MIT. It adds 52 tokens to every session and 620 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.

Related

Other skills, from other repositories

k8s

Operate the joelclaw Kubernetes cluster — Talos Linux on Colima (Mac Mini). Deploy services, check health, debug pods, recover from restarts, add ports, manage Helm releases, inspect logs, fix networking. Triggers on: 'kubectl', 'pods', 'deploy to k8s', 'cluster health', 'restart pod', 'helm install', 'talosctl'…

joelhooks/joelclaw · 163 tokens

detecting-container-drift-at-runtime

Detect unauthorized modifications to running containers by monitoring for binary execution drift, file system changes, and configuration deviations from the original container image.

xalgorix/xalgorix · 34 tokens

implementing-container-image-minimal-base-with-distroless

Reduce container attack surface by building application images on Google distroless base images that contain only the application runtime with no shell, package manager, or unnecessary OS utilities.

xalgorix/xalgorix · 45 tokens

implementing-rbac-hardening-for-kubernetes

Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.

xalgorix/xalgorix · 41 tokens

performing-container-security-scanning-with-trivy

Scan container images, filesystems, and Kubernetes manifests for vulnerabilities, misconfigurations, exposed secrets, and license compliance issues using Aqua Security Trivy with SBOM generation and CI/CD integration.

xalgorix/xalgorix · 48 tokens

nvca-chart-release

Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.

NVIDIA/nvcf · 61 tokens