A qmd command that creates numerical representations of indexed documents so searches can find related meaning, not only matching words. These representations are called vector embeddings.

Use it after indexing documents, especially code, to generate or rebuild embeddings, choose code-aware chunking, and limit memory use on large collections.

It makes semantic search possible and refreshes documents whose embeddings are missing or outdated. The command can resume after interruption and can process selected collections.

embed — Command for Claude Code by ramonclaudio/skills

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/ramonclaudio/skills

Made for: Claude Code.

Or install qmd, the plugin that ships this one along with the rest of its 2 skills, 18 commands, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/ramonclaudio/skills/embed/github.svg)](https://agentmods.dev/commands/ramonclaudio/skills/embed)

Your own site

<a href="https://agentmods.dev/commands/ramonclaudio/skills/embed"><img src="https://agentmods.dev/badge/commands/ramonclaudio/skills/embed/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/ramonclaudio/skills/embed"><img src="https://agentmods.dev/badge/commands/ramonclaudio/skills/embed.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 347 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.

Model	Per session	Once invoked
Fable 5.1	$0.00012	$0.00347
Opus 5.5	$0.00005	$0.00139
Sonnet 5.5	$0.00002	$0.00069
Haiku 4.5	$0.00001	$0.00035

Measured 2mo ago against content hash 8c422487893f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

embed 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 2mo 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/qmd/commands/embed.md · 20 lines

What it actually says

Run qmd embed $ARGUMENTS. Defaults to incremental (only embeds hashes without vectors).

Useful flags:

-f / --force: clear all vectors and re-embed everything (after model change, dimension mismatch, or strategy switch).
-c <name>: scope to one collection (embeds only its pending hashes). -c <name> --force clears and rebuilds only that collection's vectors and preserves hashes shared with sibling collections. Added in qmd 2.5.0.
--chunk-strategy auto: AST-aware chunking for code files (.ts/.tsx/.js/.jsx/.mts/.cts/.mjs/.cjs/.py/.go/.rs). Recommended for code-heavy collections so chunks land on function/class boundaries instead of mid-statement.
--max-docs-per-batch N / --max-batch-mb N: bound peak memory on huge collections (defaults: 64 docs / 64 MB, whichever is hit first).

After embedding, run qmd status and confirm zero pending embeds. First run downloads ~300 MB embedding model; pre-download all 3 models (~2 GB) with /qmd:pull.

Embeddings are safe to interrupt and resume — the next run picks up from where it stopped.

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.

2mo ago First seen · 20 lines · 0 tokens per session scan A 8c422487893f

Subscribe to this mod's changes

embed is a command published in the GitHub repository ramonclaudio/skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 347 once invoked, about $0.0000 per session on Opus 5.5. 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.

Data and AI RAG and vectors

embed next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
embedramonclaudio/skills	Command	4	5mo ago	MIT	A	12	Claude Code
queryingupstash/redis-js	Command	983	yesterday	MIT	A	0	Claude Code
ingestGalbaz1/video-research-mcp	Command	23	6d ago	MIT	A	10	Claude Code
agentget-convex/convex-agent-plugins	Command	117	24d ago	MIT	A	21	Claude Code, Cursor
proofragunshDee/proofrag	Command	2	yesterday	MIT	A	22	Claude Code
inference.embedstratalab/strata-core	Command	5	1mo ago	Apache-2.0	A	0	Claude Code
vector.batch_existsstratalab/strata-core	Command	5	1mo ago	Apache-2.0	A	0	Claude Code