Agent skill

Navop

by feigeCode in feigeCode/navop

Use terminal commands to discover and operate resources exposed by a running Navop desktop application through its host-authoritative Public MCP runtime.

Custom licenceAuto-check passedDatabases

Install Navop

skills CLI
$ npx skills add feigeCode/navop --skill navop -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install feigeCode/navop navop --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/feigeCode/navop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/navop .claude/skills/navop && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
navop
GitHub stars
1.8k
Token cost
~1.1k tokens
SKILL.md length
551 words
Files
5 (incl. references)
Skills in repo
8
Repo updated
First seen
Licence
Custom licence

At a glance

Use terminal commands to discover and operate resources exposed by a running Navop desktop application through its host-authoritative Public MCP runtime.

  • Databases work in your project
  • Calls npm

What it does

Navop is an agent skill from feigeCode/navop. Use terminal commands to discover and operate resources exposed by a running Navop desktop application through its host-authoritative Public MCP runtime.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/commands.md`, `references/errors.md` and `references/safety.md`).

It sits in Databases. It works with Model Context Protocol. The repository describes itself as: A native, all-in-one workspace for databases, SSH, SFTP, terminals, remote desktop, monitoring, and AI.

When your agent uses it

  • Databases work in your project

Example prompts

  • “/navop”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit 536b1a6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Navop loads about 1.1k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 40 tokens; SKILL.md has 551 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 551 words (~1,127 tokens).

“Use this Skill when an AI Agent needs to operate Navop resources from a terminal. It keeps a compact workflow in context and loads command help or live schemas only when needed, so the Agent does not carry the complete…”

— opening of SKILL.md by feigeCode, Custom licence
name
navop

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (references) in .codex/skills/navop of feigeCode/navop.

  • SKILL.md
  • references/commands.md
  • references/errors.md
  • references/safety.md
  • references/workflows.md

Open the folder on GitHubat commit 536b1a6

Compare with similar skills

Navop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Navop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Navop this skillfeigeCode/navop1.8k—~1.1kAutomated safety check: PassCustom licence
Hugegraph Schema Designerapache/hugegraph-ai144—~554Automated safety check: PassApache-2.0
Semantic Modeldata-goblin/power-bi-agentic-development1k—~2.8kAutomated safety check: PassGPL-3.0
Experiment Auditwanshuiyin/Auto-claude-code-research-in-sleep17k—~3.2kAutomated safety check: NotesMIT
Agent Tool Builderdavila7/claude-code-templates32k2 repos~417Automated safety check: PassMIT
SEO Monitorcognyai/claude-code-marketing-skills104—~571Automated safety check: PassNone

Similar skills

  • Hugegraph Schema Designer

    apache/hugegraph-ai

    Route HugeGraph MCP schema design, validation, and dry-run preview tasks to stable public tools.

    144 GitHub stars~554 tokensUpdated today
    DatabasesAuto-check passed
  • Semantic Model

    data-goblin/power-bi-agentic-development

    This skill should be used whenever the user mentions a "semantic model", "data model", or "dataset", or asks to "build", "model", "design", "optimize", "review", or "audit" one, or to "add a…

    1k GitHub stars~2.8k tokensUpdated 2 days ago
    DatabasesAuto-check passed
  • Experiment Audit

    wanshuiyin/Auto-claude-code-research-in-sleep

    Audit experiment integrity before claiming results. An agent skill from wanshuiyin/Auto-claude-code-research-in-sleep.

    17k GitHub stars~3.2k tokensUpdated 2 days ago
    DatabasesAuto-check: notes
  • Agent Tool Builder

    davila7/claude-code-templates

    Tools are how AI agents interact with the world. An agent skill from davila7/claude-code-templates.

    32k GitHub starsUsed in 2 repos~417 tokens
    DatabasesAuto-check passed
  • SEO Monitor

    cognyai/claude-code-marketing-skills

    Monitor SEO rankings, queries, and indexing via Search Console MCP

    104 GitHub stars~571 tokensUpdated 3 mo ago
    DatabasesAuto-check passed
  • Troubleshoot Cassandra

    Kilo-Org/kilo-marketplace

    A skill your agent uses when diagnosing issues with Apache Cassandra: gc death spiral, compaction death spiral, tombstone storm, disk space exhaustion, or hint overflow.

    190 GitHub stars~2.5k tokensUpdated 10 days ago
    DatabasesAuto-check passed

More from feigeCode/navop

All 8 skills in this repo
  • Connection Import Wasm

    feigeCode/navop

    A skill your agent uses when implementing, debugging, packaging, or host-enabling onetcli WASM connection importers such as DBeaver, Navicat, Navicat Lite, Termius, connection-import.wit components…

    1.8k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Gpui Component

    feigeCode/navop

    How to use the gpui-component UI library in GPUI applications, and the normative Design and Coding Guides that govern it.

    1.8k GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Ipc Driver Development

    feigeCode/navop

    A skill your agent uses when designing, implementing, reviewing, or debugging onetcli IPC database drivers, driver.json manifests, extension-protocol wire methods, schema metadata, DDL builders…

    1.8k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Navop Release Notes

    feigeCode/navop

    A skill your agent uses when working in the Navop repository on CHANGELOG.md, version-tag preparation, GitHub Releases, or R2 updater release notes, especially when bilingual Chinese and English…

    1.8k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Ssh Connection Import

    feigeCode/navop

    A skill your agent uses when implementing or debugging onetcli SSH connection importers, including OpenSSH config, knownhosts, candidate file manifests, local composite installs, SSH authmethod JSON…

    1.8k GitHub stars~1.2k tokensUpdated today
    Auto-check: warnings
  • Gpui

    feigeCode/navop

    GPUI framework knowledge covering actions/keybindings, async/background tasks, context management (App/Window/Context<T/AsyncApp), custom elements (low-level Element trait), entity state management…

    1.8k GitHub stars~768 tokensUpdated today
    Auto-check passed

Categories

Questions about Navop

What does Navop do?

Use terminal commands to discover and operate resources exposed by a running Navop desktop application through its host-authoritative Public MCP runtime. Navop is an agent skill from feigeCode/navop. Use terminal commands to discover and operate resources exposed by a running Navop desktop application through its host-authoritative Public MCP runtime.

When should I use Navop?

Navop fits situations like: databases work in your project.

How do I install Navop in Claude Code?

Run `npx skills add feigeCode/navop --skill navop -a claude-code`. Or copy the skill folder (.codex/skills/navop in feigeCode/navop) into .claude/skills/navop in your project. Claude Code loads it when a task matches its description.

How do I install Navop in Codex?

Run `npx skills add feigeCode/navop --skill navop -a codex`. Or copy the skill folder (.codex/skills/navop in feigeCode/navop) into .agents/skills/navop in your project. Codex loads it when a task matches its description.

Can I use Navop in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add feigeCode/navop --skill navop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/navop, .gemini/skills/navop, .github/skills/navop and .opencode/skills/navop in your project.

What does Navop need to run?

Going by SKILL.md and its folder, Navop needs the command-line tools its instructions call (npm). Our summary lists: Node.js.

Does Navop access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Navop safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Navop use?

Navop has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Navop use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.2k tokens, read only when the agent opens those files.

What are the alternatives to Navop?

Skills that share tags, products or a category with Navop: Hugegraph Schema Designer (apache/hugegraph-ai, 144 stars), Semantic Model (data-goblin/power-bi-agentic-development, 1k stars), Experiment Audit (wanshuiyin/Auto-claude-code-research-in-sleep, 17k stars) and Agent Tool Builder (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Navop?

feigeCode (a GitHub user) maintains it in feigeCode/navop, which has 1,820 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 9, 2026.

Source: feigeCode/navop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.