What is auto-implementation?

A documentation-driven implementation workflow that reads project specifications and checks whether the described files and components exist. It treats documentation as the source for proposing or creating implementation work.

Use it to inspect architecture and technical specifications, identify missing pages or components, and propose implementation based on those documents.

It connects written requirements with the codebase and helps reveal missing implementation described by architecture or technical documents.

auto-implementation — Cursor rule by elirancv

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/elirancv/cursormd/auto-implementation

Clone the repo

git clone --depth 1 https://github.com/elirancv/CursorMD

Made for: Cursor.

Per session 1,586 This file is loaded in full into every session.

When invoked 1,586 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.

Model	Per session	Once invoked
Fable 5	$0.01586	$0.01586
Opus 5	$0.00793	$0.00793
Sonnet 5	$0.00317	$0.00317
Haiku 4.5	$0.00159	$0.00159

Measured yesterday against content hash f6e62e5dfeca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-implementation 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.

.cursor/rules/auto-implementation.mdc · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto-Implementation from Documentation

Core Principle: Specification Drives Implementation

"Proper specification is 50% of the work" - Once the specification is perfect, the system should automatically know what to build. Like an autopilot, the system reads the documentation and implements accordingly.

Auto-Implementation System

Automatic Detection

When documentation exists, automatically:

Scan documentation files - Read ARCHITECTURE_OVERVIEW.md, TECH_SPEC_MVP.md, SYSTEM_COMPONENTS.md, etc.
Identify what needs to be built - Extract requirements, components, and specifications
Detect missing implementation - Check what code/files are missing vs. what's specified
Propose implementation - Suggest creating missing code/files based on documentation
Implement automatically - Create code/files according to specifications

Implementation Detection Rules

When ARCHITECTURE_OVERVIEW.md exists:

Check for: HTML pages, CSS files, component structure
If missing: Propose creating HTML structure, CSS files, component files
Action: Read architecture doc and create corresponding code structure

When TECH_SPEC_MVP.md exists:

Check for: Implementation files matching technical specs
If missing: Propose creating code files according to tech spec
Action: Read tech spec and implement accordingly

When SYSTEM_COMPONENTS.md exists:

Check for: Component files (HTML components, CSS modules, etc.)
If missing: Propose creating component files
Action: Read components doc and create component implementations

When PRD_MVP.md exists:

Check for: Features and functionality specified in PRD
If missing: Propose implementing features
Action: Read PRD and implement features

Implementation Mapping

Documentation → Code Mapping

ARCHITECTURE_OVERVIEW.md →

HTML page structure
CSS file organization
Component files
File structure

TECH_SPEC_MVP.md →

HTML markup according to spec
CSS styles according to spec
Technical implementation details
Code structure

Read the full file on GitHub · 212 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.

yesterday First seen · 212 lines · 1,586 tokens per session scan A f6e62e5dfeca

Subscribe to this mod's changes

auto-implementation is a cursor rule published in the GitHub repository elirancv/CursorMD (1 stars, last pushed 9mo ago), licensed MIT. It adds 1,586 tokens to every session, about $0.0079 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.

Planning Productivity Writing and docs cursor cursor-ai cursorrules md

create-rule-agent

This rule is responsible for creating and updating Cursor rules. Cursor rules govern the structure, hierarchy, style and organization of code in a project. This rule should be invoked in Agent mode when: 1. a user wants to create a new cursor rule, 2. a user wants to update or change an existing rule, 3. user wants…

usrrname/cursorrules · 3,429 tokens

auto-implementation