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/rules/edochi/mdvs/cursor-rules)<a href="https://agentmods.dev/rules/edochi/mdvs/cursor-rules"><img src="https://agentmods.dev/badge/rules/edochi/mdvs/cursor-rules/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/rules/edochi/mdvs/cursor-rules"><img src="https://agentmods.dev/badge/rules/edochi/mdvs/cursor-rules.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 | $0.00452 | $0.00452 |
| Opus 5.5 | $0.00181 | $0.00181 |
| Sonnet 5.5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
cursor-rules 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.
What it actually says
mdvs knowledge base
This project uses mdvs to manage a markdown knowledge base with a schema defined in mdvs.toml. When working with files in this KB:
- Prefer
mdvs search "<query>"overGrep/Globfor content lookups. mdvs runs semantic / hybrid / SQL-filtered search over the KB — usually a better fit than literal pattern matching for finding notes by meaning. Filter by frontmatter with--where "field = 'value'"and pick the mode with--mode semantic|fulltext|hybrid. mdvs checkvalidates frontmatter against the schema. ApostToolUsehook may surface violations to you automatically as a markdown block underadditionalContextin the hook output. Treat that block as a warning, not a block — the agent's edit already landed; the warning is for you to act on next.- When a violation reaches you, decide:
- Mistake (a typo, the wrong type by accident, a dropped required field) → fix the file in the next turn.
- Intentional deviation (the KB is evolving, a category genuinely needs a new variant, a field is shifting type) → surface the deviation to the user and propose updating
mdvs.tomlto absorb the change. Do not silently fix the file; the user decides whether the schema or the file is wrong.
The schema is meant to evolve with the KB. Enforcement follows the KB's shape, it does not freeze it. Whenever you propose a schema update, also explain why — which file(s) drove the change and what convention the user might want to standardise on.
Full mdvs documentation: https://edochi.github.io/mdvs/.
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 · 22 lines · 452 tokens per session scan A 6f0fc0fc10dc
cursor-rules is a cursor rule published in the GitHub repository edochi/mdvs (27 stars, last pushed 11d ago), licensed MIT. It adds 452 tokens to every session, about $0.0018 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 cursor rules, from other repositories
database
Database, embeddings, and chunking patterns for Textrawl.
frontend-architecture
Cursor rule "frontend-architecture" from tomasz-tomczyk/crit, covering frontend architecture, two-paradigm page fork, module pattern, shared modules (used by both modes) and code-review modules (used only by code-review mode).
frontend-css
Cursor rule "frontend-css" from tomasz-tomczyk/crit, covering css rules, responsive & touch and selectors.
templates
Tera template variables, blocks, and theme conventions.
features
Built-in site features (highlighting, homepage content, math, diagrams, search).
write-migration
Author an idempotent, state-detecting migration under scripts/migrations/ for a breaking llm-wiki-memory change. Use when shipping a breaking change to the engine, or when asked to write a migration / upgrade path. Replaces the retired release-runbook flow.