agentmods.dev

localnest: Skill for Claude Code

.claude/skills/localnest-mcp-runtime/SKILL.md

localnest-mcp-runtime is a skill for Claude Code from wmt-mobile/localnest. It costs 35 tokens per session (375 once invoked), scanned A, original, MIT.

A set of instructions for working on LocalNest's MCP runtime, which is the part that starts its tools and connects them to coding agents.

In plain words
What is it for?
It guides changes to setup, diagnostics, server startup, configuration generation, tool wiring, and runtime compatibility handling.
Why use it?
It helps prevent setup, startup, configuration, and fallback behavior from working in one environment but failing after installation or in another.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is wmt-mobile/localnest's own configuration. It tells Claude Code how to work on localnest 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 localnest configures →

not rated 6repo 4mo ago A scan 35 tokens original MIT
View source ↗ wmt-mobile/localnest wmt-mobile.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to wmt-mobile/localnest. 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/wmt-mobile/localnest/main/.claude/skills/localnest-mcp-runtime/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/wmt-mobile/localnest

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 localnest-mcp-runtime

README.md
[![agentmods](https://agentmods.dev/badge/skills/wmt-mobile/localnest/localnest-mcp-runtime/github.svg)](https://agentmods.dev/skills/wmt-mobile/localnest/localnest-mcp-runtime)
Your own site
<a href="https://agentmods.dev/skills/wmt-mobile/localnest/localnest-mcp-runtime"><img src="https://agentmods.dev/badge/skills/wmt-mobile/localnest/localnest-mcp-runtime/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 localnest-mcp-runtime

Your own site · 80×15
<a href="https://agentmods.dev/skills/wmt-mobile/localnest/localnest-mcp-runtime"><img src="https://agentmods.dev/badge/skills/wmt-mobile/localnest/localnest-mcp-runtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 375 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 $0.00035 $0.00375
Opus 5.5 $0.00014 $0.00150
Sonnet 5.5 $0.00007 $0.00075
Haiku 4.5 $0.00003 $0.00038

Measured 2mo ago against content hash 60403a5a5cd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

localnest-mcp-runtime 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 2mo 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/localnest-mcp-runtime/SKILL.md · 62 lines

What it actually says

LocalNest MCP Runtime

Use this skill when touching:

  • scripts/runtime/
  • src/mcp/
  • src/app/
  • client config generation or setup and doctor flows

Quick Start

  1. Test the installed CLI path, not only the repo source path.
  2. Treat setup, doctor, and server startup as separate runtime surfaces.
  3. Prefer explicit warnings and controlled fallback over raw module errors.

Workflow

1. Reproduce on the runtime surface

Choose the narrowest entry point:

  • localnest setup
  • localnest doctor
  • localnest start
  • MCP tool status and index tools

2. Check import timing

For runtime compatibility bugs, inspect:

  • barrel exports
  • top-level imports in CLI and setup code
  • lazy imports intended to protect optional backends

3. Keep setup honest

Setup should:

  • detect incompatible Node and runtime constraints early
  • choose safe defaults for unsupported environments
  • explain disabled features precisely

4. Keep doctor useful

Doctor and status output should answer:

  • what backend is active
  • why a fallback happened
  • what the user must install or upgrade

Guardrails

  • Never rely on a fallback that can be bypassed by an earlier top-level import.
  • Avoid setup flows that recommend unsupported defaults.
  • Keep user-facing warnings concrete: feature, reason, required version, action.
  • When packaging changes matter, inspect the installed global package as well as local source.

Reference

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. 2mo ago First seen · 62 lines · 35 tokens per session scan A 60403a5a5cd0

Subscribe to this mod's changes

localnest-mcp-runtime is a skill published in the GitHub repository wmt-mobile/localnest (6 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 375 once invoked, about $0.0001 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 2026-08-31.

Backend and APIsBuilding agentslocalnestmcp-servermcp-serversnodeprivacy
Related

localnest-mcp-runtime compared with skills from other repositories

localnest-mcp-runtime next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
localnest-mcp-runtimewmt-mobile/localnestSkill64mo agoMITA35Claude Code
narsilpostrv/narsil-mcpSkill1871mo agoApache-2.0A42Claude Code
n8n-code-toolczlonkowski/n8n-mcpSkill23kyesterdayMITA221Claude Code, Codex
n8n-subworkflowsczlonkowski/n8n-mcpSkill23kyesterdayMITA121Claude Code, Codex
sanity-singletonssanity-io/agent-toolkitSkill19710d agoMITA90Claude Code
sanity-best-practicessanity-io/agent-toolkitSkill19710d agoMITA177Claude Code
tech-specsgriddynamics/rosettaSkill370yesterdayApache-2.0A23Claude Code