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.
npx skills add edochi/mdvs --skill skillgit 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/skills/edochi/mdvs/skill)<a href="https://agentmods.dev/skills/edochi/mdvs/skill"><img src="https://agentmods.dev/badge/skills/edochi/mdvs/skill/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/skills/edochi/mdvs/skill"><img src="https://agentmods.dev/badge/skills/edochi/mdvs/skill.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 | $0.00093 | $0.07293 |
| Opus 5.5 | $0.00037 | $0.02917 |
| Sonnet 5.5 | $0.00019 | $0.01459 |
| Haiku 4.5 | $0.00009 | $0.00729 |
Grade A, and why
mdvs 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 — 624 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mdvs — Markdown Validation & Search
A CLI that treats a markdown directory as a database: schema inference, typed frontmatter validation, and semantic / full-text / hybrid search with SQL filters. Single binary, no external services. Full documentation at https://edochi.github.io/mdvs/.
Usage
mdvs init [path] # infer schema, write mdvs.toml
mdvs init [path] --dry-run # preview inference
mdvs init [path] --force # overwrite existing config
mdvs init [path] --from-jsonschema <file> # import schema from JSON Schema 2020-12
mdvs init [path] --ignore-bare-files # exclude files with no frontmatter
mdvs check [path] # validate frontmatter against mdvs.toml
mdvs check [path] --jsonschema <file> # override [fields] for this run
mdvs check [path] --no-update # skip auto-update before validating
mdvs update [path] # detect and add new fields
mdvs update reinfer <field> [path] # re-infer type and constraints
mdvs update reinfer <field> [path] --dry-run # preview reinfer
mdvs update reinfer <field> [path] --with=<categorical|range|none>
mdvs build [path] # validate + chunk + embed → Lance index
mdvs build [path] --force # full rebuild (ignore incremental cache)
mdvs search "<query>" [path] # hybrid search (default)
mdvs search "<query>" [path] --mode <semantic|fulltext|hybrid>
mdvs search "<query>" [path] --where "<SQL>" # frontmatter filter
mdvs search "<query>" [path] --limit <N> # default 10
mdvs search "<query>" [path] -v # show matching chunk text
mdvs search "<query>" [path] --no-build # fail if no index exists
mdvs search "<query>" [path] --no-update # skip auto-update before build
mdvs info [path] # config + index status
mdvs info [path] -v # full field detail
mdvs clean [path] # delete .mdvs/
mdvs export-jsonschema [path] # emit canonical JSON Schema
mdvs export-jsonschema [path] --format <json|toml>
mdvs export-jsonschema [path] --output-file <file>
mdvs scaffold skill [--platform <name>] # this skill file
mdvs scaffold snippet [--platform <name>] # AGENTS.md / CLAUDE.md snippet
mdvs scaffold hook --platform <name> # PostToolUse hook config (JSON snippet)
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 · 624 lines · 93 tokens per session scan A 6d6652e371e8
mdvs is a skill published in the GitHub repository edochi/mdvs (27 stars, last pushed 11d ago), licensed MIT. It adds 93 tokens to every session and 7,293 once invoked, about $0.0004 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 2026-10-05.
Other skills, from other repositories
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
crystalline-schema
Use when a Crystalline domain wants structure for one of its engram types - authoring a Picoschema schema engram, running inferschema to bootstrap one from what is already captured, or validateengrams to check conformance.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…