auk-rules

A generated set of coding rules for the auk tool, an AI context-management platform. The rules cover naming, architecture boundaries, test-file names, and code areas that should be changed carefully.

In plain words
What is it for?
Use it to guide naming and import decisions, follow test-file conventions, and avoid creating additional violations or unstable changes in heavily used code.
Why use it?
It gives an agent concrete project conventions and warns about existing high-impact code. The file also records that it should be regenerated by auk instead of edited by hand.

Cursor rule for Cursor

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/sandeepshekhar26/develop-anything/auk-rules
Clone the repo
git clone --depth 1 https://github.com/sandeepshekhar26/develop-anything

Made for: Cursor.

Per session 1,103 This file is loaded in full into every session.
When invoked 1,103 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 $0.01103 $0.01103
Opus 5 $0.00551 $0.00551
Sonnet 5 $0.00221 $0.00221
Haiku 4.5 $0.00110 $0.00110

Measured 2d ago against content hash a16d2b2b5d59, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auk-rules 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.

.cursor/rules/auk-rules.mdc · 60 lines

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.

Generated by auk — AI Context Engineering Platform

https://github.com/sandeepshekhar26/develop-anything

Generated: 2026-06-11T17:08:30.055Z

Context Health: 100%

DO NOT EDIT MANUALLY — regenerate with: auk compile

🔴 architecture-no-utility-to-model: Utility layer should not import from Model layer. 1 existing violation is known tech debt — don't add more.

🔴 naming-functions-camelcase: All function names use camelCase naming convention.

🔴 naming-classes-pascalcase: All class and interface names use PascalCase naming convention.

🔴 testing-naming-test: Test files follow the *.test.ts / *.test.js naming convention.

🟡 architecture-hotspot-tests-helpers-expect-ts-expect: expect (tests/helpers/expect.ts) is called from 105 places — changes here have a high blast radius. Keep its signature and behavior stable.

🟡 architecture-hotspot-src-utils-logger-ts-info: info (src/utils/logger.ts) is called from 22 places — changes here have a high blast radius. Keep its signature and behavior stable.

🟡 architecture-hotspot-src-utils-logger-ts-success: success (src/utils/logger.ts) is called from 21 places — changes here have a high blast radius. Keep its signature and behavior stable.

🟡 architecture-god-class-src-utils-cli-ts-Command: Command (src/utils/cli.ts) has 18 methods and 24 inbound calls — it is becoming a god object. Don't add more responsibilities; split it instead.

🟡 architecture-god-class-tests-helpers-expect-ts-Expectation: Expectation (tests/helpers/expect.ts) has 15 methods and 2 inbound calls — it is becoming a god object. Don't add more responsibilities; split it instead.

🟡 architecture-hub-src-types-rules-ts: src/types/rules.ts has 32 connections — it may be becoming a god object. Consider breaking it into smaller modules.

🟡 architecture-hub-src-utils-logger-ts: src/utils/logger.ts has 31 connections — it may be becoming a god object. Consider breaking it into smaller modules.

🟡 architecture-hub-src-types-analysis-ts: src/types/analysis.ts has 30 connections — it may be becoming a god object. Consider breaking it into smaller modules.

Read the full file on GitHub · 60 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 · 60 lines · 1,103 tokens per session scan A a16d2b2b5d59

Subscribe to this mod's changes

auk-rules is a cursor rule published in the GitHub repository sandeepshekhar26/develop-anything (17 stars, last pushed 2mo ago), licensed MIT. It adds 1,103 tokens to every session, about $0.0055 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.