github-code-quality-cursorrules-prompt-file

A set of rules for GitHub-related development and coding-agent responses. It includes instructions about verifying information, making file-by-file changes, avoiding certain phrases, and not inventing unrequested changes.

In plain words
What is it for?
Use it to guide code changes and responses in projects hosted on GitHub, especially when changes should be made one file at a time.
Why use it?
It gives the agent a fixed response and change process for GitHub work. The description does not specify any GitHub API or repository automation.

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/patrickjs/awesome-cursorrules/github-code-quality-cursorrules-prompt-file
Clone the repo
git clone --depth 1 https://github.com/PatrickJS/awesome-cursorrules
Per session 913 This file is loaded in full into every session.
When invoked 913 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 $0.00913 $0.00913
Opus 5 $0.00456 $0.00456
Sonnet 5 $0.00183 $0.00183
Haiku 4.5 $0.00091 $0.00091

Measured 2d ago against content hash a9ea60d39fa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-code-quality-cursorrules-prompt-file 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.

rules/github-code-quality-cursorrules-prompt-file.mdc · 90 lines

What it actually says

{ "rules": [ { "name": "Verify Information", "pattern": "(?i)\b(assume|assumption|guess|speculate)\b", "message": "Always verify information before presenting it. Do not make assumptions or speculate without clear evidence." }, { "name": "File-by-File Changes", "pattern": "// MULTI-FILE CHANGE:", "message": "Make changes file by file and give me a chance to spot mistakes" }, { "name": "No Apologies", "pattern": "(?i)\b(sorry|apologize|apologies)\b", "message": "Never use apologies" }, { "name": "No Understanding Feedback", "pattern": "(?i)\b(understand|understood|got it)\b", "message": "Avoid giving feedback about understanding in comments or documentation" }, { "name": "No Whitespace Suggestions", "pattern": "(?i)\b(whitespace|indentation|spacing)\b", "message": "Don't suggest whitespace changes" }, { "name": "No Summaries", "pattern": "(?i)\b(summary|summarize|overview)\b", "message": "Don't summarize changes made" }, { "name": "No Inventions", "pattern": "(?i)\b(suggest|recommendation|propose)\b", "message": "Don't invent changes other than what's explicitly requested" }, { "name": "No Unnecessary Confirmations", "pattern": "(?i)\b(make sure|confirm|verify|check)\b", "message": "Don't ask for confirmation of information already provided in the context" }, { "name": "Preserve Existing Code", "pattern": "(?i)\b(remove|delete|eliminate|destroy)\b", "message": "Don't remove unrelated code or functionalities. Pay attention to preserving existing structures." }, { "name": "Single Chunk Edits", "pattern": "(?i)\b(first|then|next|after that|finally)\b", "message": "Provide all edits in a single chunk instead of multiple-step instructions or explanations for the same file" }, { "name": "No Implementation Checks", "pattern": "(?i)\b(make sure|verify|check|confirm) (it's|it is|that) (correctly|properly) implemented\b", "message": "Don't ask the user to verify implementations that are visible in the provided context" }, { "name": "No Unnecessary Updates", "pattern": "(?i)\b(update|change|modify|alter)\b.\bno changes\b", "message": "Don't suggest updates or changes to files when there are no actual modifications needed" }, { "name": "Provide Real File Links", "pattern": "(?i)\b(file|in)\b.\b(x\.md)\b", "message": "Always provide links to the real files, not x.md" }, { "name": "No Previous x.md Consideration", "pattern": "(?i)\b(previous|earlier|last)\b.*\bx\.md\b", "message": "Do not consider any previous x.md files in your memory. Complain if the contents are the same as previous runs." }, { "name": "No Current Implementation", "pattern": "(?i)\b(current|existing)\s+(implementation|code)\b", "message": "Don't show or discuss the current implementation unless specifically requested" }, { "name": "Check x.md Content", "pattern": "(?i)\b(file|content|implementation)\b", "message": "Remember to check the x.md file for the current file contents and implementations" } ] }

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 · 90 lines · 0 tokens per session scan A a9ea60d39fa0

Subscribe to this mod's changes

github-code-quality-cursorrules-prompt-file is a cursor rule published in the GitHub repository PatrickJS/awesome-cursorrules (40,694 stars, last pushed 3mo ago), licensed CC0-1.0. It adds 913 tokens to every session, about $0.0046 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.