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 commands/ivangrynenko/cursorrules/pr-resolvegit clone --depth 1 https://github.com/ivangrynenko/cursorrulesWhat 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 | $0.00000 | $0.01268 |
| Opus 5 | $0.00000 | $0.00634 |
| Sonnet 5 | $0.00000 | $0.00254 |
| Haiku 4.5 | $0.00000 | $0.00127 |
Grade A, and why
pr-resolve 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Custom Command: PR Resolve
Command Usage
/pr-resolve <pr-url-or-number> [context]
Require the PR URL/number as the first argument. Treat any following text as remediation instructions from the reviewer.
Please address review comments for Pull Request: Use the user-provided arguments (if any) as contextual input. If no artument was provided or you can't read it, stop and ask the user for the prompt, pull request URL and any instructions. Any user input becomes the Use the user-provided arguments (if any) as contextual input. Use those instructions from the Use the user-provided arguments (if any) as contextual input and pull request URL in further steps.
This command uses AI coding agent to efficiently resolve PR feedback while maintaining code quality.
0. VALIDATION PHASE
If no PR link provided in Use the user-provided arguments (if any) as contextual input, ask user: "Please provide the PR link (e.g., https://github.com/org/repo/pull/123 or just the PR number if in the current repo)"
1. ANALYSIS PHASE
Launch initial analysis agent:
Task: "Analyze PR #Use the user-provided arguments (if any) as contextual input comprehensively:
- Use 'gh pr view Use the user-provided arguments (if any) as contextual input' to get PR details
- Use 'gh pr reviews Use the user-provided arguments (if any) as contextual input' to get all review comments
- Use 'gh api repos/{owner}/{repo}/pulls/{number}/comments' for inline file comments
- Check current PR status and CI/CD results
- Categorize feedback into: code changes, test additions, documentation updates
- Check project's AGENTS.md for available testing and linting commands"
2. MULTI-STEP RESOLUTION PHASE
Step 1 - Code Changes & Review Comments
Task: "Address all code review feedback for PR #Use the user-provided arguments (if any) as contextual input:
- For each review comment:
* Understand the requested change
* Implement the fix following reviewer suggestions
* Search codebase for similar patterns to ensure consistency
- For inline file comments:
* Navigate to exact file and line
* Implement suggested changes
* Consider impact on surrounding code
- Make logical commits grouping related 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.
- 2d ago First seen · 129 lines · 0 tokens per session scan A 3ed3235e096e
pr-resolve is a command published in the GitHub repository ivangrynenko/cursorrules (88 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,268 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
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
matcha:audit
🍵 Stack health check — find overlaps, waste, and risks before they become problems.
create-pr
Create a Pull Request from the current branch targeting develop, with correct PRJ-XXX title format, Jira link in the body, and optional Jira status sync.
typescript
Apply TypeScript best practices and coding standards.
fix-issue
Command "fix-issue" from HKTITAN/cursor-best-practices, covering steps and rules.
learn
Analyze the current session and extract any patterns worth saving as skills.