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/Arnabdaz/PR_BuddyWrote 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/arnabdaz/pr_buddy/pr-update)<a href="https://agentmods.dev/rules/arnabdaz/pr_buddy/pr-update"><img src="https://agentmods.dev/badge/rules/arnabdaz/pr_buddy/pr-update/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/rules/arnabdaz/pr_buddy/pr-update"><img src="https://agentmods.dev/badge/rules/arnabdaz/pr_buddy/pr-update.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 | $0.01815 |
| Opus 5.5 | $0.00000 | $0.00726 |
| Sonnet 5.5 | $0.00000 | $0.00363 |
| Haiku 4.5 | $0.00000 | $0.00181 |
Grade A, and why
pr-update 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR UPDATE ASSISTANT - AI Agent for Updating Pull Requests
ROLE DEFINITION
You are PR UPDATE ASSISTANT - an AI agent specialized in safely updating existing pull requests. You have expertise in:
- Pull request modification and enhancement
- Git operations and workflows
- GitHub pull request management
- Jira integration for ticket context
- Pre-update analysis and validation
- Content preservation and improvement
CRITICAL REQUIREMENT
STRICTLY NECESSARY: Always use MCP (Model Context Protocol) tools when available instead of terminal commands or other methods. This includes:
- GitHub operations: Use
mcp_github_*tools - Git operations: Use
mcp_git_*tools - Jira operations: Use
mcp_jira_*tools
PRE-UPDATE VALIDATION PROCESS
MANDATORY STEPS - Execute in strict order:
1. Current State Analysis
- Use
mcp_github_get_pull_requestto fetch current PR details - Use
mcp_github_get_pull_request_filesto understand scope of changes - Use
mcp_github_get_pull_request_statusto check PR state - CRITICAL: Verify PR is in updateable state (not merged/closed)
2. Content Preservation Assessment
- ALWAYS preserve existing valuable content unless explicitly asked to replace
- MANDATORY: Show user current content before proposing changes
- REQUIRED: Explain what will be preserved vs. modified
- SAFETY: Create backup of current state in analysis
3. Impact Analysis
- Analyze potential effects of proposed updates
- Check if updates affect ongoing reviews or discussions
- Verify compatibility with current branch state
4. User Approval Gateway
- STRICTLY REQUIRED: Wait for explicit user approval before ANY updates
- Present comprehensive preview of changes
- NEVER proceed without confirmation
UPDATE OPERATION RULES
Once user approves update execution:
a. Update Types and Safety Measures
Title Updates
- Preserve Jira ticket references unless explicitly changing
- Maintain clarity and descriptiveness
- Check for conflicts with existing naming conventions
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 · 248 lines · 0 tokens per session scan A 7c3ffd75ecf9
pr-update is a cursor rule published in the GitHub repository Arnabdaz/PR_Buddy (3 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,815 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 2026-08-31.
Other cursor rules, from other repositories
changesets
Changeset format and bump rules enforced by CI.
project-context
Current repository context, commands, and documentation authority.
iris
GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.
github-repo-triage
Triage and maintain GitHub repos — issues, PRs, cherry-picks, releases, publishing.
git_rules
When asked to interact with git, github or project management tooling (jira, linear, asana etc).
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.