serve

serve is a command for Claude Code from ramdhavepreetam/NervaPack. It costs 0 tokens per session (523 once invoked), scanned A, original, MIT.

A command that opens a browser dashboard for inspecting a knowledge graph, which maps relationships between code and documentation. The dashboard shows graph health, query history, code hotspots, and how the graph changes over time.

In plain words
What is it for?
Use it to run the Nervapack dashboard locally, choose its port, open it without a browser on a server, and explore graph statistics, searches, and query history.
Why use it?
It makes graph structure and usage easier to inspect than command-line output alone. It can reveal missing documentation, highly connected files, and query or cost patterns.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

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 commands/ramdhavepreetam/nervapack/serve
Clone the repo
git clone --depth 1 https://github.com/ramdhavepreetam/NervaPack

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 serve

README.md
[![agentmods](https://agentmods.dev/badge/commands/ramdhavepreetam/nervapack/serve.svg)](https://agentmods.dev/commands/ramdhavepreetam/nervapack/serve)
Your own site
<a href="https://agentmods.dev/commands/ramdhavepreetam/nervapack/serve"><img src="https://agentmods.dev/badge/commands/ramdhavepreetam/nervapack/serve.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 523 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 5.1 $0.00000 $0.00523
Opus 5 $0.00000 $0.00262
Sonnet 5 $0.00000 $0.00105
Haiku 4.5 $0.00000 $0.00052

Measured 5d ago against content hash 3ced27cc6ffb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

serve 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 5d 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.

docs/user-guide/commands/serve.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

nervapack serve

Launch an interactive web dashboard for your knowledge graph — graph health, query analytics, code hotspots, and graph evolution, all in one place.


Synopsis

nervapack serve [OPTIONS]

Options

Option Default Description
--port N / -p N 8501 Port to run the dashboard on
--no-browser off Don't open the browser automatically

Requirements

The dashboard requires optional dependencies:

pip install "nervapack[dashboard]"
# or:
pip install streamlit plotly pandas

Examples

# Launch on default port, open browser
nervapack serve

# Custom port
nervapack serve --port 8080

# Headless (server environments, CI)
nervapack serve --no-browser

Dashboard Tabs

Overview

  • Health score (0–100) with colour indicator
  • Total nodes, edges, doc coverage cards
  • Language distribution bar chart
  • Most connected files table

Analytics

  • Node type and edge type pie charts
  • Degree distribution histogram

Query History

  • Aggregate token savings and cost metrics
  • Top queried keywords
  • Recent query log (requires prior nervapack query runs)

Graph Explorer

  • Node search (by name, type, or file path)
  • Graph density and orphaned node count

Hotspots (v0.5.3+)

  • Files ranked by commit frequency or total churn
  • Time-window filter (All time / 1 year / 6 months / 3 months / 1 month)
  • Interactive Plotly bar chart + table

Graph Evolution (v0.5.3+)

  • Node and edge count over time (recorded per ingest / sync)
  • Health score and documentation coverage trends
  • Sync log table (newest first)

!!! note "Evolution tab" The Graph Evolution timeline is empty on first launch. Snapshots are recorded automatically every time you run nervapack ingest or nervapack sync. The chart fills in as you use NervaPack.


Read the full file on GitHub · 94 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. 5d ago First seen · 94 lines · 0 tokens per session scan A 3ced27cc6ffb

Subscribe to this mod's changes

serve is a command published in the GitHub repository ramdhavepreetam/NervaPack (1 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 523 tokens. 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.