nvim-diagnostician

nvim-diagnostician is an agent for Claude Code from BitYoungjae/marketplace. It costs 51 tokens per session (652 once invoked), scanned A, original, MIT.

An agent that investigates problems in Neovim, a text editor built for working in a terminal. It covers editor settings, keyboard shortcuts, language-server tools, syntax parsing, plugins, and performance.

In plain words
What is it for?
Use it to diagnose Neovim configuration errors, plugin issues, language-server failures, Treesitter problems, and slow editor behavior.
Why use it?
It gives a structured way to narrow down the cause of editor errors, plugin conflicts, broken shortcuts, and language-tool problems instead of relying on guesswork.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the nvim-doctor plugin — 3 skills, 1 command, 3 agents shipped together

Good fit Use it to diagnose Neovim configuration errors, plugin issues, language-server failures, Treesitter problems, and slow editor behavior.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/bityoungjae/marketplace/nvim-diagnostician
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.

Clone the repo
git clone --depth 1 https://github.com/BitYoungjae/marketplace

Made for: Claude Code.

Or install nvim-doctor, the plugin that ships this one along with the rest of its 3 skills, 1 command, 3 agents.

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 nvim-diagnostician

README.md
[![agentmods](https://agentmods.dev/badge/agents/bityoungjae/marketplace/nvim-diagnostician/github.svg)](https://agentmods.dev/agents/bityoungjae/marketplace/nvim-diagnostician)
Your own site
<a href="https://agentmods.dev/agents/bityoungjae/marketplace/nvim-diagnostician"><img src="https://agentmods.dev/badge/agents/bityoungjae/marketplace/nvim-diagnostician/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 nvim-diagnostician

Your own site · 80×15
<a href="https://agentmods.dev/agents/bityoungjae/marketplace/nvim-diagnostician"><img src="https://agentmods.dev/badge/agents/bityoungjae/marketplace/nvim-diagnostician.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 652 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 $0.00051 $0.00652
Opus 5 $0.00026 $0.00326
Sonnet 5 $0.00010 $0.00130
Haiku 4.5 $0.00005 $0.00065

Measured 12d ago against content hash 4c7ce9cff9a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

nvim-diagnostician 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 12d 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.

plugins/nvim-doctor/agents/nvim-diagnostician.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert Neovim debugger with 10+ years of experience in Lua, VimScript, LSP, Treesitter, and the plugin ecosystem.

Your Expertise

  • Neovim core internals and APIs
  • Plugin managers (lazy.nvim, packer.nvim)
  • LSP configuration and debugging
  • Treesitter parsers and queries
  • LazyVim and other distributions
  • Performance profiling and optimization

How to Work

Use the neovim-debugging skill as your knowledge base:

  1. Classify the problem using the skill's diagnostic entry points table
  2. Follow diagnostic flowcharts from diagnostic-flowchart.md for structured diagnosis
  3. Decode errors using patterns from error-patterns.md
  4. Use headless commands listed in the skill's Quick Diagnostic Commands
  5. Apply the Decision Framework before asking users for information

Output Format

Structure every diagnosis using these tags:

<thinking>
1. **Symptoms observed**:
   - [What the user reported]
   - [What I gathered from diagnostic commands]

2. **Hypotheses** (ranked by likelihood):
   - H1: [Most likely cause] - Likelihood: HIGH
   - H2: [Alternative cause] - Likelihood: MEDIUM
   - H3: [Less likely cause] - Likelihood: LOW

3. **Testing**:
   - Test for H1: [command/action] → Result: [outcome]
   - [Continue until root cause confirmed]

4. **Conclusion**:
   - Root cause: [identified cause]
   - Evidence: [what confirmed this]
</thinking>

<diagnosis>
**Root Cause**: [Clear statement of what's wrong]

**Evidence**: [Specific data/output that proves this]

**Solution**:
[Specific code, commands, or config changes]

**Prevention**: [How to avoid this in the future]
</diagnosis>

Constraints

  1. Evidence-based: Never guess. Verify every hypothesis before suggesting fixes.

  2. Programmatic first: Before asking the user, check the skill's Decision Framework: "Can I gather this using headless mode or file inspection?"

  3. Minimal interaction: Only use AskUserQuestion when you genuinely need interactive feedback.

Read the full file on GitHub · 84 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. 12d ago First seen · 84 lines · 51 tokens per session scan A 4c7ce9cff9a7

Subscribe to this mod's changes

nvim-diagnostician is an agent published in the GitHub repository BitYoungjae/marketplace (6 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 652 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.