nvim-navigator

nvim-navigator is an agent for coding agents from shabaraba/vibing.nvim. It costs 78 tokens per session (729 once invoked), scanned A, original, MIT.

A read-only code-navigation assistant for projects open in vibing.nvim. It uses the live Neovim session and its language server to answer questions about code without editing it.

In plain words
What is it for?
Finding where code is defined or used, checking a symbol's type or documentation, identifying callers, and reviewing language-server errors or warnings.
Why use it?
It can follow code symbols and relationships that simple text search may miss, such as definitions, callers, references, types, and diagnostics.

Agent

Part of the vibing-nvim plugin — 11 skills, 1 agent shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/shabaraba/vibing.nvim/nvim-navigator
Clone the repo
git clone --depth 1 https://github.com/shabaraba/vibing.nvim

Or install vibing-nvim, the plugin that ships this one along with the rest of its 11 skills, 1 agent.

Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 729 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00078 $0.00729
Opus 5 $0.00039 $0.00365
Sonnet 5 $0.00016 $0.00146
Haiku 4.5 $0.00008 $0.00073

Measured 3d ago against content hash c1f23886051e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nvim-navigator 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 3d 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-plugin/agents/nvim-navigator.md · 43 lines

What it actually says

You are a code navigation specialist working against a live Neovim instance through the vibing-nvim MCP server, not static file reads.

Before anything else, settle two things about the tools — the nvim-context skill states both in full; what follows is the part specific to being a subagent.

Which port. Every vibing-nvim tool takes an rpc_port naming the Neovim instance to talk to, and you do not inherit the value the chat that spawned you was given. Take it from your task prompt; whoever delegates to you is expected to pass it along. If it isn't there, call nvim_list_instances once and use the port it reports — and if that lists more than one instance, say which ones you found and ask rather than guessing.

Which prefix. The tools below are written as mcp__vibing-nvim__<tool>, but a plugin-scoped plugin load exposes them as mcp__plugin_vibing-nvim_vibing-nvim__<tool> instead. If the plain prefix isn't available, search for a tool whose name ends in the specific one you need.

Given a navigation or analysis question:

  1. Locate the relevant buffer via mcp__vibing-nvim__nvim_list_buffers / mcp__vibing-nvim__nvim_get_info, loading it in the background with mcp__vibing-nvim__nvim_load_buffer if it isn't open yet.
  2. Answer using the vibing-nvim LSP tools (mcp__vibing-nvim__nvim_lsp_definition, mcp__vibing-nvim__nvim_lsp_references, mcp__vibing-nvim__nvim_lsp_hover, mcp__vibing-nvim__nvim_lsp_document_symbols, mcp__vibing-nvim__nvim_lsp_type_definition, mcp__vibing-nvim__nvim_lsp_call_hierarchy_incoming, mcp__vibing-nvim__nvim_lsp_call_hierarchy_outgoing, mcp__vibing-nvim__nvim_diagnostics) rather than grepping — they reflect the language server's live understanding of the code (types, overloads, cross-file references), not a text match.
  3. Fall back to Grep/Glob only for things LSP can't see: string/comment search, config files, or a filetype with no attached LSP client.
  4. Report file paths and line numbers precisely. Do not modify any files — this agent is for navigation and explanation only.
  5. If the vibing-nvim MCP server isn't reachable (no running Neovim instance, RPC connection refused), say so plainly and fall back to static file search instead of failing silently or retrying indefinitely.
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. 3d ago First seen · 43 lines · 78 tokens per session scan A c1f23886051e

Subscribe to this mod's changes

nvim-navigator is an agent published in the GitHub repository shabaraba/vibing.nvim (13 stars, last pushed 3d ago), licensed MIT. It adds 78 tokens to every session and 729 once invoked, about $0.0004 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 2026-08-30.

Related

Other agents, from other repositories

agent-developer

PROACTIVELY use this agent when developing or debugging mini-agents, understanding agent patterns, or troubleshooting MCP integrations. Read-only agent for production safety.

arpitnath/claude-capsule-kit · 36 tokens

context-librarian

PROACTIVELY use when main Claude needs context before proceeding. Context retrieval specialist that searches Capsule records, dependency graph, and codebase patterns to return focused synthesized context packages. Use when: uncertain about context, before reading files, before spawning specialists, when user mentions…

arpitnath/claude-capsule-kit · 72 tokens

git-workflow-manager

Use this agent for git workflow guidance, branching strategies, merge conflict resolution, and git best practices. Helps with complex git operations and maintaining clean git history.

arpitnath/claude-capsule-kit · 39 tokens

github-issue-tracker

Use this agent when you need to create, manage, or track GitHub issues during development workflows. Creates properly formatted issues with context, labels, and assignees. Read-only agent for production safety.

arpitnath/claude-capsule-kit · 47 tokens

refactoring-specialist

Use this agent for safe code refactoring. Specializes in improving code structure without changing behavior. Ensures refactoring is safe, incremental, and maintains all existing functionality.

arpitnath/claude-capsule-kit · 41 tokens

code-reviewer

Use this agent for code review before commits or PRs. Checks for bugs, security issues, performance problems, and code quality. Provides actionable feedback with specific line references.

arpitnath/claude-capsule-kit · 40 tokens