auto-coder-rules

auto-coder-rules is a cursor rule for Cursor from mondweep/remote-mcp-creation-foundation. It costs 7 tokens per session (4,053 once invoked), scanned A, original, MIT.

A collection of rules for Auto-Coder mode, including the required format for applying text replacements to code. It also lists common mistakes when writing those replacements.

In plain words
What is it for?
Guiding automated code changes and checking replacement blocks before they are applied.
Why use it?
It reduces failed code edits caused by incorrect markers, incomplete replacements, or text that does not match the target file.

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/mondweep/remote-mcp-creation-foundation/auto-coder-rules
Clone the repo
git clone --depth 1 https://github.com/mondweep/remote-mcp-creation-foundation

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 auto-coder-rules

README.md
[![agentmods](https://agentmods.dev/badge/rules/mondweep/remote-mcp-creation-foundation/auto-coder-rules.svg)](https://agentmods.dev/rules/mondweep/remote-mcp-creation-foundation/auto-coder-rules)
Your own site
<a href="https://agentmods.dev/rules/mondweep/remote-mcp-creation-foundation/auto-coder-rules"><img src="https://agentmods.dev/badge/rules/mondweep/remote-mcp-creation-foundation/auto-coder-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,053 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00007 $0.04053
Opus 5 $0.00003 $0.02027
Sonnet 5 $0.00001 $0.00811
Haiku 4.5 $0.00001 $0.00405

Measured 3d ago against content hash e8cb6fb830d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-coder-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 3d 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/auto-coder-rules.mdc · 531 lines

How it starts

The opening of the file, as written. The whole thing — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preventing apply_diff Errors

CRITICAL: When using apply_diff, never include literal diff markers in your code examples

CORRECT FORMAT for apply_diff:

<apply_diff>
  <path>file/path.js</path>
  <diff>
    <<<<<<< SEARCH
    // Original code to find (exact match)
    =======
    // New code to replace with
    >>>>>>> REPLACE
  </diff>
</apply_diff>

COMMON ERRORS to AVOID:

  1. Including literal diff markers in code examples or comments
  2. Nesting diff blocks inside other diff blocks
  3. Using incomplete diff blocks (missing SEARCH or REPLACE markers)
  4. Using incorrect diff marker syntax
  5. Including backticks inside diff blocks when showing code examples

When showing code examples that contain diff syntax:

  • Escape the markers or use alternative syntax
  • Use HTML entities or alternative symbols
  • Use code block comments to indicate diff sections

SAFE ALTERNATIVE for showing diff examples:

// Example diff (DO NOT COPY DIRECTLY):
// [SEARCH]
// function oldCode() {}
// [REPLACE]
// function newCode() {}

ALWAYS validate your diff blocks before executing apply_diff

  • Ensure exact text matching
  • Verify proper marker syntax
  • Check for balanced markers
  • Avoid nested markers

Code Editing Guidelines

apply_diff

<apply_diff>
  <path>File path here</path>
  <diff>
    <<<<<<< SEARCH
    Original code
    =======
    Updated code
    >>>>>>> REPLACE
  </diff>
</apply_diff>

Required Parameters:

  • path: The file path to modify
  • diff: The diff block containing search and replace content

Common Errors to Avoid:

  • Incomplete diff blocks (missing SEARCH or REPLACE markers)
  • Including literal diff markers in code examples
  • Nesting diff blocks inside other diff blocks
  • Using incorrect diff marker syntax
  • Including backticks inside diff blocks when showing code examples

Best Practices:

  • Always verify the file exists before applying diffs
  • Ensure exact text matching for the search block
  • Use read_file first to confirm content before modifying
  • Keep diff blocks simple and focused on specific changes

Read the full file on GitHub · 531 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. 3d ago First seen · 531 lines · 7 tokens per session scan A e8cb6fb830d5

Subscribe to this mod's changes

auto-coder-rules is a cursor rule published in the GitHub repository mondweep/remote-mcp-creation-foundation (0 stars, last pushed 1y ago), licensed MIT. It adds 7 tokens to every session and 4,053 once invoked, about $0.0000 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.