gsd

A set of required development rules for using the Aura command-line tool while changing code.

In plain words
What is it for?
Checking project status, planning features, tracing logic, reviewing pull requests, validating behavior, and applying automatic fixes.
Why use it?
It adds checkpoints for understanding existing code, planning larger changes, reviewing work, and recording why commits were made.

Cursor rule

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/naridon-inc/aura/gsd
Clone the repo
git clone --depth 1 https://github.com/Naridon-Inc/aura
Per session 619 This file is loaded in full into every session.
When invoked 619 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 $0.00619 $0.00619
Opus 5 $0.00309 $0.00309
Sonnet 5 $0.00124 $0.00124
Haiku 4.5 $0.00062 $0.00062

Measured 2d ago against content hash 15791aef8385, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gsd 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 2d 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.

integrations/cursor-rules/cursor-rules/gsd.mdc · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aura — Mandatory Agent Workflow

You have access to the aura CLI. These commands are NOT optional. Use them as described below.

HARD RULES — Follow These, No Exceptions

Before you write ANY code

  1. Run aura status to see what's tracked (logic nodes, checkpoints).
  2. If the task involves 3+ files or a new feature, run aura plan "objective". Review the gray areas, lock decisions, then follow the wave plan. Do NOT skip this — it prevents you from building on wrong assumptions.

While writing code

  1. Before editing a file, think about which specific functions need to change. Run aura prove --goal "what you're trying to achieve" to understand the existing logic paths.
  2. Run aura pr-review --base main periodically to catch layer violations and bugs as you go.
  3. Before every commit, run aura log-intent "1-2 sentence description of WHY". The gatekeeper matches your words to AST changes.

After completing work

  1. Run aura pr-review --base main. Fix any invariant violations or security issues it finds.
  2. Run aura prove --goal "user-facing behavior". If it returns warnings, investigate.
  3. If the review found violations, run aura fix to auto-resolve them.

When context is getting large

  1. Run aura handover cursor. It generates a compressed XML payload. Ask the user to start fresh with this payload — saves ~90% of tokens.

Command Quick Reference

Trigger Command What it does
Planning a feature aura plan "objective" Gray areas + locked wave plan
Executing a plan aura execute or aura execute --auto Run waves (--auto skips confirmations)
Something broke aura rewind <function> <file> Revert one function to last safe state
Verify a feature aura prove --goal "..." Mathematical proof via AST tracing
Before a commit aura log-intent "why" Bind reasoning to AST changes
Before a merge aura pr-review --base main Semantic diff + bug/security scan
Auto-fix violations aura fix Shadow branch auto-correction
Screenshot to code aura design-copy img.png Gemini vision generates React/HTML/Vue
Context too big aura handover <agent> Compress to XML handover payload

Read the full file on GitHub · 42 lines

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. 2d ago First seen · 42 lines · 619 tokens per session scan A 15791aef8385

Subscribe to this mod's changes

gsd is a cursor rule published in the GitHub repository Naridon-Inc/aura (45 stars, last pushed 12d ago), licensed Apache-2.0. It adds 619 tokens to every session, about $0.0031 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 2026-08-30.