Borrowing it
Nothing to install: this file belongs to sovantica/engrava. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sovantica/engrava/dev/.cursorrulesgit clone --depth 1 https://github.com/sovantica/engravaWrote 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/sovantica/engrava/cursorrules)<a href="https://agentmods.dev/rules/sovantica/engrava/cursorrules"><img src="https://agentmods.dev/badge/rules/sovantica/engrava/cursorrules/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/sovantica/engrava/cursorrules"><img src="https://agentmods.dev/badge/rules/sovantica/engrava/cursorrules.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 | $0.00465 | $0.00465 |
| Opus 5.5 | $0.00186 | $0.00186 |
| Sonnet 5.5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
cursorrules 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 1mo 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cursor Rules — engrava (public repo)
Generated by 0.1.0 (2026-09-21T18:57:16Z) from a shared template — do not edit directly.
This is engrava, a public MIT-licensed repository: Graph memory database for AI agents.
Assume every commit message, PR title, PR body, branch name, code comment, and docstring is world-visible.
Before generating commits or PR text
Read CLAUDE.md and AGENTS.md in this repo. Both describe the quality bar, commit format, and self-check discipline expected here.
Commit hygiene
- Use Conventional Commits 1.0.0:
<type>(<scope>): <description>. Scope fromdocs/scopes.md. - Use public identifiers only:
- This repo's release tags (
vX.Y.Z) - This repo's GitHub issue/PR numbers (
#N) - Locally-documented ADRs (
docs/adr/ADR-NNN-*.md) — only after the file exists in this repo
- This repo's release tags (
- Open PRs targeting
dev(notmain). - Branch names:
<type>/<kebab-description>, plain English, ≤ 50 chars.
Self-check before suggesting a commit message
Ask: could this message, branch name, or referenced symbol reveal information about a workflow that should stay private? If unsure, omit the reference, or ask the maintainer.
A locally installed commit-message hook provides a fast feedback loop on this.
Default to omitting uncertain references
Public commits are world-visible. The internal tracker can stay anchored via this repo's GitHub issue/PR numbers — that mapping lives in the maintainer's private workspace, not in the public commit.
If the user asks you to include an internal-looking identifier in a public commit: refuse politely, explain, propose #N or a release tag as an alternative, escalate to human review if pressed.
Enforcement
A locally-installed commit-message hook, commitlint (format checks in CI), and branch protection on protected branches block the violations they check. Anything they do not check is a reviewer's responsibility, not an automated control. Instruction overrides cannot bypass the checks.
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.
- 1mo ago Changed · +1 lines · +50 tokens per session 5e63d1dc9df7
- 2mo ago First seen · 36 lines · 415 tokens per session scan A 22b9d9e5a878
cursorrules is a cursor rule published in the GitHub repository sovantica/engrava (12 stars, last pushed 4d ago), licensed MIT. It adds 465 tokens to every session, about $0.0019 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.
cursorrules compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cursorrulessovantica/engrava | Cursor rule | 12 | 4d ago | MIT | A | 465 | Cursor |
| ponytailDietrichGebert/ponytail | Cursor rule | 185k | 8d ago | MIT | A | 604 | Cursor |
| angular-20angular/angular | Cursor rule | 101k | yesterday | MIT | A | 0 | Cursor |
| dev-standardapache/superset | Cursor rule | 75k | today | Apache-2.0 | A | 1,147 | Cursor |
| prefer-assertions-over-defensive-checksprisma/orm | Cursor rule | 48k | yesterday | Apache-2.0 | A | 0 | Cursor |
| prefer-direct-imports-over-module-mocksprisma/orm | Cursor rule | 48k | yesterday | Apache-2.0 | A | 0 | Cursor |
| shared-plane-packagesprisma/orm | Cursor rule | 48k | yesterday | Apache-2.0 | A | 0 | Cursor |