agentmods.dev

navigravity: Skill for Claude Code

.agent/skills/mcp-development/SKILL.md

mcp-development is a skill for Claude Code, Codex from miziodel/navigravity. It costs 21 tokens per session (645 once invoked), scanned A, original, MIT.

Development guidance for building and maintaining Navidrome MCP tools and resources. Navidrome is music-server software, and MCP is a standard way for an agent to use external tools and data.

In plain words
What is it for?
Use it when implementing or updating Navidrome MCP server tools and resources.
Why use it?
It gives developers consistent rules for logging, input validation, error handling, search fallbacks, and keeping documentation aligned with code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is miziodel/navigravity's own configuration. It tells Claude Code and Codex how to work on navigravity 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 navigravity configures →

not rated 1repo 5mo ago A scan 21 tokens original MIT
View source ↗ miziodel/navigravity
Reuse

Borrowing it

Nothing to install: this file belongs to miziodel/navigravity. 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/miziodel/navigravity/main/.agent/skills/mcp-development/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/miziodel/navigravity

Made for: Claude Code, Codex.

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 mcp-development

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/miziodel/navigravity/mcp-development"><img src="https://agentmods.dev/badge/skills/miziodel/navigravity/mcp-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 645 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 $0.00021 $0.00645
Opus 5.5 $0.00008 $0.00258
Sonnet 5.5 $0.00004 $0.00129
Haiku 4.5 $0.00002 $0.00064

Measured 2mo ago against content hash 3180a0fc5962, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-development 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.

.agent/skills/mcp-development/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Development Standards

This skill defines the technical standards for the Navidrome MCP ecosystem.

1. Professional Logging (Local JSON)

We use a structured local JSON logging system. Do NOT use standard print() or basic logging.info().

  • Implementation: Use the @log_execution decorator for all tools.
  • Pattern:
    • logger.info("Message", extra={"key": "value"})
    • Fields: timestamp, level, name, message, tool, inputs, duration_ms, result_summary.
  • Level: Use DEBUG for verbose tech details, INFO for tool execution success, ERROR for failures with exc_info=True.

2. Safety & Validation

  • ID Validation: All Navidrome IDs should be validated as 32-character hex strings where possible.
  • Fail Fast: If a dependency (like Navidrome connection) is down, the tool should return a structured error JSON instead of crashing.
  • Fuzzy Fallback: For search tools, if a strict search returns no results, implement a secondary "fuzzy" search or broader query before giving up.

3. Code-to-Doc Synchronization (CRITICAL)

Architectural decisions in documentation MUST be mirrored in the MCP server resources.

  • If docs/architecture/curator_manifesto.md is updated, the CURATOR_MANIFESTO_TEXT constant in src/navidrome_mcp_server.py MUST be updated in the same task.
  • Ensure usage_guide() prompt in code reflects all current tools available in the server.

4. Tool Protocol

  • Naming: Use lowercase with underscores (e.g., get_smart_candidates).
  • Descriptions: Must be clear and describe parameters accurately for LLM consumption.
  • Returns: Always return a JSON-stringified object or list for structured parsing.

4. TDD Workflow

Every bug fix or new tool MUST follow this cycle:

  1. Create a tests/test_filename.py.
  2. Write a test that reproduces the bug or defines the desired behavior.
  3. Verify the test fails.
  4. Implement the fix/feature in src/navidrome_mcp_server.py.
  5. Verify the test passes.

Read the full file on GitHub · 49 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. 2mo ago First seen · 49 lines · 21 tokens per session scan A 3180a0fc5962

Subscribe to this mod's changes

mcp-development is a skill published in the GitHub repository miziodel/navigravity (1 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 645 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.

Building agentsantigravity-idemcp-servernavidrome
Related

mcp-development compared with skills from other repositories

mcp-development next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-developmentmiziodel/navigravitySkill15mo agoMITA21Claude Code, Codex
opik-diagnosecomet-ml/opik-mcpSkill225yesterdayApache-2.0A187Claude Code
ue-mcp-epic-routingdb-lyon/ue-mcpSkill480yesterdayMITA81Claude Code, Codex
qa-knowledgegriddynamics/rosettaSkill373yesterdayApache-2.0A32Claude Code, Codex
apitapn1byn1kt/apitapSkill13118d agoApache-2.0A0Claude Code, Codex
frontmcp-setupagentfront/frontmcpSkill1482d agoApache-2.0A176Claude Code, Codex
x-use-reviewihuzaifashoukat/x-useSkill1815d agoMITA56Claude Code