rebuild-index

rebuild-index is a command for Claude Code from RobThePCGuy/Claude-Patent-Creator. It costs 17 tokens per session (288 once invoked), scanned A, original, MIT.

A command that rebuilds the MPEP search index. MPEP is the U.S. patent examination manual used by patent examiners.

In plain words
What is it for?
Use it after updating MPEP PDFs, fixing a damaged index, changing the text-embedding model, or enabling a GPU, then check that the index is healthy.
Why use it?
It restores or updates the files that power keyword and meaning-based searches when the source PDFs or search setup changes.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-patent-creator-standalone plugin — 17 skills, 16 commands, 13 agents, 2 hooks shipped together

Good fit Use it after updating MPEP PDFs, fixing a damaged index, changing the text-embedding model, or enabling a GPU, then check that the index is healthy.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add RobThePCGuy/Claude-Patent-Creator
Claude Code
/plugin install claude-patent-creator-standalone

Made for: Claude Code.

Or install claude-patent-creator-standalone, the plugin that ships this one along with the rest of its 17 skills, 16 commands, 13 agents, 2 hooks.

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 rebuild-index

README.md
[![agentmods](https://agentmods.dev/badge/commands/robthepcguy/claude-patent-creator/rebuild-index/github.svg)](https://agentmods.dev/commands/robthepcguy/claude-patent-creator/rebuild-index)
Your own site
<a href="https://agentmods.dev/commands/robthepcguy/claude-patent-creator/rebuild-index"><img src="https://agentmods.dev/badge/commands/robthepcguy/claude-patent-creator/rebuild-index/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 rebuild-index

Your own site · 80×15
<a href="https://agentmods.dev/commands/robthepcguy/claude-patent-creator/rebuild-index"><img src="https://agentmods.dev/badge/commands/robthepcguy/claude-patent-creator/rebuild-index.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 288 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 $0.00017 $0.00288
Opus 5 $0.00009 $0.00144
Sonnet 5 $0.00003 $0.00058
Haiku 4.5 $0.00002 $0.00029

Measured 10d ago against content hash 711ebdfc4746, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rebuild-index 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 10d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

commands/rebuild-index.md · 48 lines

What it actually says

Rebuild MPEP Index

Rebuild the hybrid search index (FAISS + BM25) from MPEP PDFs.

Instructions

  1. Verify MPEP PDFs are present (${CLAUDE_PLUGIN_ROOT}/pdfs)
  2. Run rebuild command
  3. Wait for completion (5-15 min GPU, 35-65 min CPU)
  4. Verify index health

Command

cd ${CLAUDE_PLUGIN_ROOT}
patent-creator setup --rebuild

What This Does

  • Deletes existing index files
  • Re-extracts text from all MPEP PDFs
  • Generates embeddings (BGE-base-en-v1.5)
  • Builds FAISS vector index
  • Builds BM25 keyword index
  • Creates metadata mappings
  • Verifies index integrity

When to Rebuild

  • MPEP PDFs updated
  • Index corruption detected
  • Slow or irrelevant search results
  • After changing embedding model
  • GPU newly available (for faster building)

Time Estimates

  • RTX 3060 GPU: 5-10 minutes
  • RTX 4090 GPU: 3-5 minutes
  • CPU only: 35-65 minutes
  • Apple Silicon (M1/M2): 15-25 minutes
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. 10d ago First seen · 48 lines · 17 tokens per session scan A 711ebdfc4746

Subscribe to this mod's changes

rebuild-index is a command published in the GitHub repository RobThePCGuy/Claude-Patent-Creator (180 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 288 once invoked, about $0.0001 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.