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.
npx agentmods add rules/abderrahimghazali/cursor-rules/pull-request-changelist-instructionsgit clone --depth 1 https://github.com/abderrahimghazali/cursor-rulesWrote 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.
[](https://agentmods.dev/rules/abderrahimghazali/cursor-rules/pull-request-changelist-instructions)<a href="https://agentmods.dev/rules/abderrahimghazali/cursor-rules/pull-request-changelist-instructions"><img src="https://agentmods.dev/badge/rules/abderrahimghazali/cursor-rules/pull-request-changelist-instructions.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00018 | $0.01118 |
| Opus 5 | $0.00009 | $0.00559 |
| Sonnet 5 | $0.00004 | $0.00224 |
| Haiku 4.5 | $0.00002 | $0.00112 |
Grade A, and why
pull-request-changelist-instructions 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: Updated guidelines for creating consistent pull request changelists in markdown format, ensuring strict raw markdown code block formatting and proper structure. globs: "*.md" alwaysApply: false
Pull Request Changelist Format
This document outlines strict standards for creating and formatting pull request changelists in markdown. Following these guidelines ensures that the output remains as raw markdown (unrendered) and prevents any issues with Cursor’s markdown rendering.
actions:
-
type: suggest message: |
Updated Pull Request Changelist Guidelines
To guarantee clarity and consistency, please adhere to the following time-tested, unambiguous guidelines when requesting a PR changelist from Cursor:
1. Request Format
Always explicitly request raw markdown output in a code block using one of these exact phrases:
- "Return markdown as code"
- "Return as code inside markdown as code (one block)"
- "Provide the markdown in a code block"
- "Return the content as a markdown code block, not as formatted text"
- "Generate the PR changelist in a markdown code block"
Avoid ambiguous wording that could lead to a rendered (formatted) output.
2. Expected Response Format
Cursor should always respond with a raw markdown code block that looks like:
```markdown # Summary of Changes ## Category Name - Change item### 3. Handling Incorrect Format If the response is rendered markdown rather than a raw code block, prompt with one of the following: - "Please provide the exact markdown in a code block using triple backticks, not as formatted text." - "I require the raw markdown syntax; reformat your response with triple backticks." - "Reformat your output as a code block enclosed in triple backticks." ### 4. Changelist Structure - **Main Heading:** Must begin with `# Summary of Changes` - **Categories:** Use `##` headings to group related changes. - **Changes:** List each change with a bullet (`-`), starting with a past tense verb (e.g., Added, Updated, Removed). - **Code/Variables:** Enclose module names or configuration settings in backticks (e.g., `module_name`). ### 5. Content Requirements - Be specific about what changed and why. - Group similar changes under the appropriate category headings. - For configuration changes, include both the setting name and its new value. - Keep each entry concise but descriptive. ### 6. Example Command To request a changelist from Cursor, try:Prepare a PR changelist based on these changes. Return the markdown in a code block with triple backticks.
Adhering to these traditional, time-tested formatting guidelines not only prevents ambiguity but also paves the way for future improvements in automated changelist generation. -
type: validate conditions:
- pattern: "^```\smarkdown\s\n#\s+Summary\s+of\s+Changes" message: "The changelist must be a raw markdown code block starting with '# Summary of Changes'. Ensure the use of triple backticks and correct heading structure."
- pattern: "-\s+(Added|Updated|Removed)\b" message: "Each bullet point must begin with a past tense verb: 'Added', 'Updated', or 'Removed'."
examples:
-
input: | Request: "Create a PR changelist for my changes. Return markdown code as code."
Good Response from Cursor:
# Summary of Changes ## Environment Configuration - Updated `STAGE_FILE_PROXY_URL` to data.safeworkaustralia.gov.au - Updated `LOCALDEV_URL` to dataswa.docker.amazee.io ## Module Changes - Removed `page_cache` module - Added `stage_file_proxy` moduleoutput: | This is the correct format for Cursor to return a changelist – as a raw markdown code block enclosed in triple backticks.
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.
- 3d ago First seen · 119 lines · 18 tokens per session scan A 5783479bbdcd
pull-request-changelist-instructions is a cursor rule published in the GitHub repository abderrahimghazali/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 18 tokens to every session and 1,118 once invoked, about $0.0001 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.
Other cursor rules, from other repositories
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
cursorrules
You are a disciplined senior engineer working with someone who may be a domain expert, not a programmer. Build it correctly and safely, not just fast.
cursorrules
Cursor rule "cursorrules" from BlueBirdBack/godot-cursorrules, covering godot 4.4 game development .cursorrules, core development guidelines, code style, naming conventions and scene organization.
new_feature
You are an expert Product Owner and Technical Lead focused on helping users define and plan new features through collaborative discovery and structured documentation.
new_project
You are an expert Product Owner focused on helping users define new software projects through collaborative vision creation.