cursorrules

cursorrules is a cursor rule for Cursor from varunajaytawde28-design/smm-sync. It costs 391 tokens per session, scanned A, original, MIT.

A coordination setup for multiple AI agents working on the same codebase. It creates shared instruction files from one source configuration and tracks which agent owns each file area.

In plain words
What is it for?
Use it to compile CLAUDE.md, .cursorrules, and AGENTS.md files from smm.toml, while coordinating simultaneous work through Tuple Space.
Why use it?
It reduces conflicting edits and keeps all agents aligned with the same project rules.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Install

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.

agentmods
npx agentmods add rules/varunajaytawde28-design/smm-sync/cursorrules
Clone the repo
git clone --depth 1 https://github.com/varunajaytawde28-design/smm-sync

Made for: Cursor.

Wrote 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.

agentmods badge for cursorrules

README.md
[![agentmods](https://agentmods.dev/badge/rules/varunajaytawde28-design/smm-sync/cursorrules.svg)](https://agentmods.dev/rules/varunajaytawde28-design/smm-sync/cursorrules)
Your own site
<a href="https://agentmods.dev/rules/varunajaytawde28-design/smm-sync/cursorrules"><img src="https://agentmods.dev/badge/rules/varunajaytawde28-design/smm-sync/cursorrules.svg" alt="Measured on agentmods" height="20"></a>
Per session 391 This file is loaded in full into every session.
When invoked 391 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00391 $0.00391
Opus 5 $0.00196 $0.00196
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 5d ago against content hash adaf2c1178d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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 5d 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.

.cursorrules · 29 lines

What it actually says

.cursorrules — smm-sync

Generated by smm-sync. Edit smm.toml then run smm compile.

Project

Coordination layer for simultaneous AI agents working on the same codebase. Automatically compiles shared context (CLAUDE.md, .cursorrules, AGENTS.md) from a single source of truth (smm.toml) and coordinates file ownership using Tuple Space protocol.

Stack: python 3.11+, click, jinja2, tomllib (stdlib), filelock

Hard Constraints (always enforce)

  • Python 3.11+ only — tomllib is stdlib in 3.11+
  • No network calls in Weekend 1 scope
  • coordinator.py must work on macOS and Linux (POSIX-atomic os.rename)
  • state.json must be human-readable JSON, never binary

Danger Zones (never touch without reason)

  • Do not use os.rename() across filesystems — only atomic within the same filesystem
  • state.json LWW merge uses wall clock — clock skew between machines can cause wrong winner
  • Templates in src/smm_sync/templates/ are package data — must be listed in pyproject.toml package-data or they will be missing from installs
  • Do not write derived or computed fields into smm.toml — it is the source of truth, not a cache

Conventions

  • Every public function must have a docstring with Args and Returns
  • No network calls anywhere in Weekend 1 scope
  • All .smm/ writes use FileLock when filelock is available, fallback to direct write
  • Comments crediting axiom-hub: # adapted from axiom-hub/src/...

Active Task

Weekend 1: Core CLI + Compiler + Coordinator + State: Implement smm init, compile, status, claim, release. Get to pip install -e . + all tests passing.

Changes

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.

  1. 5d ago First seen · 29 lines · 391 tokens per session scan A adaf2c1178d7

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository varunajaytawde28-design/smm-sync (1 stars, last pushed 5mo ago), licensed MIT. It adds 391 tokens to every session, about $0.0020 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.