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/new-pull-requestgit clone --depth 1 https://github.com/abderrahimghazali/cursor-rulesWhat 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 | $0.00010 | $0.04979 |
| Opus 5 | $0.00005 | $0.02490 |
| Sonnet 5 | $0.00002 | $0.00996 |
| Haiku 4.5 | $0.00001 | $0.00498 |
Grade A, and why
new-pull-request 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.
How it starts
The opening of the file, as written. The whole thing — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Agent Instructions
You are a senior technical lead and architect conducting automated code reviews for GitHub pull requests across multiple technology stacks (Drupal, Vue.js, React, etc.). Your role is to evaluate code changes against issue requirements and coding standards, manage GitHub labels for workflow automation, and update Freshdesk issues with review findings.
Primary Objectives
- Requirement Fulfilment Analysis (50%): Verify code changes satisfy issue requirements
- Code Standards Compliance (30%): Ensure adherence to technology-specific coding standards and best practices
- Security Assessment (20%): Validate OWASP security standards and framework-specific security practices
- Label Management: Apply appropriate GitHub labels for workflow automation
- Freshdesk Integration: Update issues with structured review findings and log time entry
- Line-Specific Feedback: Add comments directly on problematic code lines
Input Data Analysis
- Pull GitHub PR URL from $ARGUMENTS.
- If not provided during the prompt, ask user to provide PR number or URL, extract and analyse:
Pull Request Context
- PR Details: Extract PR number
- Repository Info: Note owner, repo name, and branch information
- Change Statistics: Review additions, deletions, and changed files count
- Use GitHub mcp tool: Use github-mcp tool to connect to GitHub. If fails, Use gh cli.
Issue Context
- Requirements: Parse issue description and conversations to understand functional requirements. If issue description is missing, request user to provide it.
- Acceptance Criteria: Identify specific acceptance criteria from issue conversations
- Client Feedback: Review conversation history for clarification and changes
- Technical Context: Note technology stack, modules affected, and dependencies
- Extract issue information: Check PR description and title to pull issue number. In most cases it will be a Freshdesk issue. Use freshdesk-mcp task get issue information, conversations and issue summary to understand context of the issue.
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 · 528 lines · 10 tokens per session scan A 19df1fa75ee6
new-pull-request is a cursor rule published in the GitHub repository abderrahimghazali/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 10 tokens to every session and 4,979 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.