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.
npx agentmods add rules/gustavobarbosab/sage/cursorrulesgit clone --depth 1 https://github.com/gustavobarbosab/sageWhat 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 | $0.00809 | $0.00809 |
| Opus 5 | $0.00404 | $0.00404 |
| Sonnet 5 | $0.00162 | $0.00162 |
| Haiku 4.5 | $0.00081 | $0.00081 |
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 yesterday.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAGE — Cursor Rules
Copy this file to your project root as .cursorrules
── Harness ───────────────────────────────────────────────────────────────────
Fill in your project-specific conventions below.
Run /sage harness init or /sage harness generate to generate this automatically.
[HARNESS]
Stack:
- Language:
- UI Framework:
- DI:
- Architecture:
- State management:
- Navigation:
- Test framework:
Conventions:
- (add naming patterns, architecture rules, required practices)
Avoid:
- (add anti-patterns, deprecated APIs, forbidden patterns)
[/HARNESS]
── SAGE Workflow ─────────────────────────────────────────────────────────────
SAGE is a spec-first, AI-assisted development workflow.
When the user types @sage or references any SAGE command below, follow these rules.
Commands
@sage spec
Two-phase command — do NOT generate files immediately.
Phase 1 — Interview:
- Analyze the description and prepare questions
- Show ALL questions at once with a count: "I have X questions before writing your spec and behavior files."
- Format each: "Question N of X / [Category] / "
- Wait for the user to answer all questions
- Minimum 3, maximum 10 questions
Phase 2 — Generation (after answers received):
- Generate spec.md:
Feature:
What it does / ### Inputs / ### Outputs / ### Acceptance criteria / ### Do NOT
- Immediately generate behavior.md in the same response:
Open Questions (list remaining ambiguities as - [ ] items, or "- No open questions.")
Test Cases (placeholder if questions remain, full BDD scenarios if none)
Never skip the interview. Never generate files before answers are received.
@sage behavior
Read spec.md and generate behavior.md. MANDATORY structure:
SECTION 1 — Open Questions (ALWAYS first): List every ambiguity as: - [ ] If no ambiguities: - No open questions.
SECTION 2 — Test Cases: Output: "> ⚠️ Pending resolution of open questions above." STOP. Wait for user to resolve questions before continuing.
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.
- yesterday First seen · 102 lines · 809 tokens per session scan A f137f53b7785
cursorrules is a cursor rule published in the GitHub repository gustavobarbosab/sage (2 stars, last pushed 2mo ago), licensed MIT. It adds 809 tokens to every session, about $0.0040 per session on Opus 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
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.