Borrowing it
Nothing to install: this file belongs to KyaniteLabs/DialectOS. 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/KyaniteLabs/DialectOS/main/.cursorrulesgit clone --depth 1 https://github.com/KyaniteLabs/DialectOSWrote 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/kyanitelabs/dialectos/cursorrules)<a href="https://agentmods.dev/rules/kyanitelabs/dialectos/cursorrules"><img src="https://agentmods.dev/badge/rules/kyanitelabs/dialectos/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/kyanitelabs/dialectos/cursorrules"><img src="https://agentmods.dev/badge/rules/kyanitelabs/dialectos/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 | $0.00507 | $0.00507 |
| Opus 5.5 | $0.00203 | $0.00203 |
| Sonnet 5.5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- windsurfrules — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KyaniteLabs — AI Agent Instructions
Organization
- Org: KyaniteLabs, owner: simongonzalezdc
- All repos use issue-driven development — contributions enter as GitHub issues, not direct PRs
- Pipeline runs every 30 min: triage → fix → review → merge
- All main/master branches are protected (no direct push, CI required)
Code Quality
- Formatter: ruff (Python), prettier (JS/TS)
- Linter: ruff (Python), eslint (JS/TS)
- Config: pyproject.toml (Python), pnpm (Node)
- Pin exact dependency versions
- No orphaned code — every function called, every file imported
- No commented-out code blocks
Security
- No
shell=Truewith user input - No hardcoded secrets/tokens/API keys
- Validate file paths (no path traversal)
- Use HTTPS for external calls
- Parameterized queries for databases
Testing
- Test behavior, not implementation
- Test the unhappy path (API down, file missing, bad input)
- Integration tests over mocks for external systems
- One assertion per concept
Git
- Commits tell why, not what
- PRs under 400 lines
- Rebase, don't merge on feature branches
- Never skip CI
Git Workspace Hygiene
- Delete feature branches after merge — no stale branches
- Remove worktrees when done — no orphaned worktrees
- Prune stale remote references (
git remote prune origin) - Clean working directory when task is done (
git statusclean) - Delete abandoned branches — don't leave dead work behind
- Main branch is the only permanent artifact — everything else is temporary
Epoch Data Tracking
- Use Epoch for time estimation before starting tasks (MCP, REST API, or CLI)
- Record actual time after completing tasks (
record_actual) - Every project feeds data to Epoch — it's how the system learns
- Epoch only works if everyone contributes estimate-vs-actual data
Local LLM
- Use local inference at localhost:1234 before cloud APIs
- Check loaded models first, don't touch models you didn't load
- Unload when done
- CPU thread pool: 10, flash attention: on, KV cache: Q8
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 First seen · 60 lines · 507 tokens per session scan A 30e9ecb2fdee
cursorrules is a cursor rule published in the GitHub repository KyaniteLabs/DialectOS (4 stars, last pushed 14d ago), licensed Apache-2.0. It adds 507 tokens to every session, about $0.0020 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.
Other cursor rules, from other repositories
i1n
This project uses i1n for managing translations.
docs-i18n-parity
Guide docs must stay in sync across all VitePress locales (en + pt-BR, es, zh-CN, hi-IN).
russian-wording
Russian wording for agent-related text (UI dictionaries, documentation, answers).
surface-parity
CLI, MCP, and share must pass the same format opts (tz, locale, flags).
hatch3r-i18n
Internationalization, localization, and RTL support conventions for the project.
main
Cursor rule "main" from amxv/terminal-mcp, covering terminal mcp project instructions, what this project does, key features, how it works and key components.