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.
git clone --depth 1 https://github.com/edochi/mdvsWrote 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.
[](https://agentmods.dev/commands/edochi/mdvs/build)<a href="https://agentmods.dev/commands/edochi/mdvs/build"><img src="https://agentmods.dev/badge/commands/edochi/mdvs/build/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.
<a href="https://agentmods.dev/commands/edochi/mdvs/build"><img src="https://agentmods.dev/badge/commands/edochi/mdvs/build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.02314 |
| Opus 5.5 | $0.00000 | $0.00926 |
| Sonnet 5.5 | $0.00000 | $0.00463 |
| Haiku 4.5 | $0.00000 | $0.00231 |
Grade A, and why
build 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.
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
build
Validate, embed, and write the search index.
Usage
mdvs build [path] [flags]
Flags
| Flag | Default | Description |
|---|---|---|
path |
. |
Directory containing mdvs.toml |
--set-model |
Change embedding model (requires --force) |
|
--set-revision |
Pin model to a specific HuggingFace revision (requires --force) |
|
--set-chunk-size |
Change max chunk size in characters (requires --force) |
|
--force |
Confirm config changes or trigger a full rebuild | |
--no-update |
Skip auto-update before building |
Global flags (-o, -v, --logs) are described in
Configuration.
What it does
build creates (or updates) the search index in .mdvs/. The pipeline:
- Read config — parse
mdvs.toml. If[embedding_model],[chunking], or[search]sections are missing, they're added with defaults and written back.
By default, build auto-updates the schema before building (see
[build].auto_update). Use --no-update to
validate against the committed schema (deterministic CI). The auto chain is
cheap on unchanged corpora — no model load, no Lance write.
- Scan — walk the directory and extract frontmatter.
- Validate — check frontmatter against the schema (same as check). If violations are found, the build aborts.
- Classify — compare scanned files against the existing index to determine what needs embedding, what to retain, and what to drop.
- Load model — download or load the cached embedding model. Skipped if nothing needs embedding.
- Embed — chunk and embed new/edited files.
- Write index — branches on the change set: skip (nothing changed and
not a full rebuild), full overwrite (first build or
--force), or incremental (delete the rows for new/edited/removed files, append the new chunks, refresh metadata, optimize). The Lance dataset is always at.mdvs/index.lance/with one row per chunk; a full-text BM25 index onchunk_textis rebuilt with the table; a cosine IVF-PQ vector index onembeddingis created only above 10,000 chunks (smaller vaults rely on LanceDB's exact flat scan).
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.
- 10d ago First seen · 225 lines · 0 tokens per session scan A 9b2b0df91ca4
build is a command published in the GitHub repository edochi/mdvs (27 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,314 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 2026-10-05.
Other commands, from other repositories
landing-publish
Use this command to publish landing pages to the seite site as pages.
publish-draft
Publish a draft article from content/ by removing the draft: true flag, building the site, and optionally deploying.
recall
Recall past Claude Code, Codex, and Cursor sessions about a topic and return a decision-focused brief.
setup
Guided session-recall setup — language, embedder, optional team mode.
prompts
Work with MCP prompt templates for memory operations.
slop-chop
Clean AI writing tells from a file or pasted text with slop-chop.