generate-embeddings

generate-embeddings is a command for coding agents from rohitg00/awesome-claude-code-toolkit. It costs 0 tokens per session (299 once invoked), scanned A, original, Apache-2.0.

A command that turns text into vector embeddings: lists of numbers representing the text's meaning. It stores those vectors with the original text and metadata in a vector database for similarity searches.

In plain words
What is it for?
Use it to embed text files, database rows, or API responses, create a nearest-neighbor index, verify known similarities, and save the configuration for later regeneration.
Why use it?
It prepares text for meaning-based retrieval instead of exact word matching, while handling batching, retries, dimensions, normalization, and indexing.

Command

Part of the embedding-manager plugin — 2 commands shipped together

About the project

Awesome Claude Code Toolkit is a curated collection of extensions and configuration for Claude Code, including agents, skills, commands, plugins, hooks, rules, templates, MCP configurations, and companion apps. It is for Claude Code users who want ready-made workflows and integrations for different development tasks. The catalogue add-ons are selected components from this toolkit.

rohitg00/awesome-claude-code-toolkit · 2,587 stars · on GitHub

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/rohitg00/awesome-claude-code-toolkit/generate-embeddings
Clone the repo
git clone --depth 1 https://github.com/rohitg00/awesome-claude-code-toolkit

Or install embedding-manager, the plugin that ships this one along with the rest of its 2 commands.

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 generate-embeddings

README.md
[![agentmods](https://agentmods.dev/badge/commands/rohitg00/awesome-claude-code-toolkit/generate-embeddings.svg)](https://agentmods.dev/commands/rohitg00/awesome-claude-code-toolkit/generate-embeddings)
Your own site
<a href="https://agentmods.dev/commands/rohitg00/awesome-claude-code-toolkit/generate-embeddings"><img src="https://agentmods.dev/badge/commands/rohitg00/awesome-claude-code-toolkit/generate-embeddings.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 299 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 $0.00000 $0.00299
Opus 5 $0.00000 $0.00150
Sonnet 5 $0.00000 $0.00060
Haiku 4.5 $0.00000 $0.00030

Measured yesterday against content hash b8c61ee66a45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generate-embeddings 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 yesterday.

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/embedding-manager/commands/generate-embeddings.md · 29 lines

What it actually says

/generate-embeddings - Generate Vector Embeddings

Generate vector embeddings for text data using embedding models.

Steps

  1. Ask the user for the input data: text file, database table, or API responses
  2. Select the embedding model: OpenAI text-embedding-3, Cohere embed, Sentence-BERT, or local model
  3. Preprocess the input text: clean, normalize, truncate to model's max token length
  4. Batch the inputs for efficient API calls (batch size based on model limits)
  5. Generate embeddings with retry logic for API rate limits and transient errors
  6. Validate embedding dimensions match the expected model output
  7. Normalize embeddings to unit length for cosine similarity searches
  8. Store embeddings with their source text and metadata in the vector database
  9. Create an index for efficient nearest-neighbor search
  10. Verify embedding quality by checking similarity of known-similar items
  11. Report: total items embedded, dimensions, storage size, API cost estimate
  12. Save the embedding configuration for future regeneration

Rules

  • Batch API calls to stay within rate limits and reduce costs
  • Implement exponential backoff retry for API failures
  • Truncate text to the model's maximum token length before embedding
  • Normalize embeddings for consistent similarity calculations
  • Store the model name and version with embeddings for reproducibility
  • Cache embeddings to avoid regenerating unchanged content
  • Monitor API costs and set spending alerts for large datasets
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. yesterday First seen · 29 lines · 0 tokens per session scan A b8c61ee66a45

Subscribe to this mod's changes

generate-embeddings is a command published in the GitHub repository rohitg00/awesome-claude-code-toolkit (2,587 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 299 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 2026-09-03.