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/.windsurfrulesgit 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/windsurfrules)<a href="https://agentmods.dev/rules/kyanitelabs/dialectos/windsurfrules"><img src="https://agentmods.dev/badge/rules/kyanitelabs/dialectos/windsurfrules.svg" alt="Measured on agentmods" 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 | $0.00253 | $0.00253 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
windsurfrules 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 today.
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.
This is a copy
100% identical to cursorrules — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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.
- today First seen · 60 lines · 507 tokens per session scan A 30e9ecb2fdee
windsurfrules is a cursor rule published in the GitHub repository KyaniteLabs/DialectOS (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 507 tokens to every session, about $0.0025 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cursorrules, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
atmos-rules
This is a Golang CLI project using Cobra for command structure and Viper for configuration management. The project maintains high code quality standards through golangci-lint and aims for maximum test coverage. The repository also includes the website source code for https://atmos.tools.
workflow
BDD-style workflow, UI screenshots in the PR, HTTP OpenAPI and config schema sync before lint, final checks.
hatch3r-dynamic-stack-verification
Runtime-evidence gates for stacks with no static type layer (plain-JS Vue, dynamic persistence) — smoke-mount changed components, dormant-collection-read ratchet, runtime smoke evidence on module-boundary changes; a green lint+build+mock-suite proves a layer, not the system.
mcpnuke-development
Core mcpnuke development standards and superpowers workflow integration.
mcpnuke-tests
Test conventions for mcpnuke — enforces TDD workflow.
python-code-validator
Validate generated Python at every step, not once at the end.