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.
git clone --depth 1 https://github.com/ivangrynenko/cursorrulesWrote 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/commands/ivangrynenko/cursorrules/gh-issue-create)<a href="https://agentmods.dev/commands/ivangrynenko/cursorrules/gh-issue-create"><img src="https://agentmods.dev/badge/commands/ivangrynenko/cursorrules/gh-issue-create/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ivangrynenko/cursorrules/gh-issue-create"><img src="https://agentmods.dev/badge/commands/ivangrynenko/cursorrules/gh-issue-create.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01548 |
| Opus 5.5 | $0.00000 | $0.00619 |
| Sonnet 5.5 | $0.00000 | $0.00310 |
| Haiku 4.5 | $0.00000 | $0.00155 |
Grade A, and why
gh-issue-create 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 1mo 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Custom Command: GitHub Issue Create
Command Usage
/gh-issue-create <description>
Everything after /gh-issue-create is treated as a single argument containing the user's description of what they want to achieve.
Instructions
You are implementing a command that intelligently creates GitHub issues based on user descriptions. This task must avoid any code changes.
Think harder and follow these steps thoroughly:
1. Parse and Understand Context
- Extract Requirements: Identify core functionality from the original request, accept the full text after the command as the user's description, analyse the current working directory to understand the project context; Identify the Git repository and its remote origin.
- Define Test Cases: Create specific, measurable test scenarios
- Specify Expected Outcomes: Clear success and failure criteria
- Structure for Implementation: Organize prompt for red-green-refactor cycle
- Include Edge Cases: Don't forget boundary conditions and error scenarios
2. Codebase Analysis
- Explore the relevant parts of the codebase mentioned in the description
- Look for:
- Related existing code
- Configuration files
- Documentation (README, docs/, wiki references)
- Similar patterns or implementations
- Dependencies that might be affected
3. Issue Classification
Determine the issue type based on the description:
- Bug: Something is broken or not working as expected
- Feature: New functionality that doesn't exist
- Enhancement: Improvement to existing functionality
- Task: Technical work, refactoring, or maintenance
4. TDD Prompt Structure
1. Objective Statement
Clear, concise description of what needs to be built
2. Test Specifications
GIVEN: [Initial state/context]
WHEN: [Action performed]
THEN: [Expected outcome]
5. Break Down Into Tasks
Decompose the description into specific, actionable tasks:
- Each task should be atomic and testable
- Think to consider technical dependencies
- Include both implementation and testing tasks
- Think about documentation updates needed
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.
- 1mo ago First seen · 241 lines · 0 tokens per session scan A e0cc601c6d19
gh-issue-create is a command published in the GitHub repository ivangrynenko/cursorrules (88 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,548 tokens. 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.
Other commands, from other repositories
implement
Execute tasks from a track's implementation plan following TDD workflow.
ponytail-debt
Harvest shortcut: comments into a tracked debt ledger.
manage
Manage track lifecycle: archive, restore, delete, rename, and cleanup.
ready-pr-in-review
Move a PR from Draft to Ready for Review, assign a reviewer, add labels, and sync the related Jira ticket to In Review with the correct assignee.
/execute
Implement an approved change and keep tasks in sync.
checklist
Generate a custom checklist for the current feature based on user requirements.