Borrowing it
Nothing to install: this file belongs to wende/cicada. 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/wende/cicada/main/.cursorrulesgit clone --depth 1 https://github.com/wende/cicadaWrote 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/wende/cicada/cursorrules)<a href="https://agentmods.dev/rules/wende/cicada/cursorrules"><img src="https://agentmods.dev/badge/rules/wende/cicada/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/wende/cicada/cursorrules"><img src="https://agentmods.dev/badge/rules/wende/cicada/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 | $0.00453 | $0.00453 |
| Opus 5.5 | $0.00181 | $0.00181 |
| Sonnet 5.5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00045 | $0.00045 |
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 2mo 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
CICADA - AI Assistant Guidelines
This file contains project-specific instructions for AI assistants working on the CICADA codebase.
Release Process
When creating a new release:
-
Create and push the git tag:
git tag v0.X.Y git push origin v0.X.Y -
Update README.md version references:
- Search for all instances of
@v0.1.1in README.md - Replace with the new version tag
@v0.X.Y - Locations to update:
- Quick Install section (stable release command)
- Try Before Installing section (stable release command)
- Migration tip section
- Search for all instances of
-
Update pyproject.toml version:
- Update the
version = "0.1.1"field to match the new release
- Update the
-
Test the installation:
uv tool install git+https://github.com/wende/[email protected]
Project Context
- Language Support: Currently Elixir only. Python and TypeScript are planned.
- Primary Installation Method: uv tool install (recommended over Python direct install)
- Index Location:
.cicada/directory in project root
Code Style
-
Use
blackfor Python code formatting -
Include type hints where appropriate
-
Write tests for new features
-
Keep functions focused and modular
-
When searching through the Elixir codebase, use the cicada-mcp MCP server tools instead of grep/find commands for better accuracy and context.
-
use make to run tests
Package Management
This project uses uv as the primary Python package manager. Always use uv commands:
- Install dependencies:
uv sync - Add new dependencies:
uv add <package-name> - Run commands:
uv run <command> - Install project:
uv pip install -e . - Tool installation:
uv tool install git+https://github.com/wende/[email protected]
Never use pip directly - always use uv for all Python package management tasks.
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.
- 2mo ago First seen · 58 lines · 453 tokens per session scan A 94ba0f531a02
cursorrules is a cursor rule published in the GitHub repository wende/cicada (41 stars, last pushed 1mo ago), licensed MIT. It adds 453 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 2026-08-30.
cursorrules compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cursorruleswende/cicada | Cursor rule | 41 | 1mo ago | MIT | A | 453 | Cursor |
| docs-governancestainless-code/codemap | Cursor rule | 8 | 5d ago | MIT | A | 10 | Cursor |
| cardano-mcpJimmyh-world/Cardano_MCP | Cursor rule | 1 | 1y ago | MIT | A | 3,030 | Cursor |
| 005_Dynamo_KV_Cache_Management_KVBMAIFlowML/cursor_rules | Cursor rule | 24 | 1y ago | none | A | 22 | 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 |