github-pr-review-mcp: Skill for Cursor

.cursor/skills/code-patterns/SKILL.md

code-patterns is a skill for Cursor from jamesjfoong/github-pr-review-mcp. It costs 19 tokens per session (433 once invoked), scanned A, original, MIT.

A collection of coding patterns for this project, including typed code, GitHub API calls, error handling, and code-analysis patterns. The GitHub API is a service for working with repositories and pull requests through code.

In plain words
What is it for?
Use it when adding features, handling GitHub API requests, writing code-analysis rules, or making TypeScript code safer.
Why use it?
It gives implementation work a consistent approach to errors, authentication, rate limits, pagination, and type definitions.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is jamesjfoong/github-pr-review-mcp's own configuration. It tells Cursor how to work on github-pr-review-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything github-pr-review-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jamesjfoong/github-pr-review-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jamesjfoong/github-pr-review-mcp/main/.cursor/skills/code-patterns/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jamesjfoong/github-pr-review-mcp

Made for: Cursor.

Wrote 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.

agentmods badge for code-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/jamesjfoong/github-pr-review-mcp/code-patterns/github.svg)](https://agentmods.dev/skills/jamesjfoong/github-pr-review-mcp/code-patterns)
Your own site
<a href="https://agentmods.dev/skills/jamesjfoong/github-pr-review-mcp/code-patterns"><img src="https://agentmods.dev/badge/skills/jamesjfoong/github-pr-review-mcp/code-patterns/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.

agentmods 80×15 button for code-patterns

Your own site · 80×15
<a href="https://agentmods.dev/skills/jamesjfoong/github-pr-review-mcp/code-patterns"><img src="https://agentmods.dev/badge/skills/jamesjfoong/github-pr-review-mcp/code-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 433 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00433
Opus 5.5 $0.00008 $0.00173
Sonnet 5.5 $0.00004 $0.00087
Haiku 4.5 $0.00002 $0.00043

Measured 2mo ago against content hash f8144e6043ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-patterns 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 2mo 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.

.cursor/skills/code-patterns/SKILL.md · 92 lines

What it actually says

Code Patterns

When to Use

  • Implementing new features
  • Handling GitHub API calls
  • Adding code analysis patterns
  • Writing type-safe code

GitHub API Error Handling

try {
  const result = await this.octokit.pulls.get({
    owner: params.owner,
    repo: params.repo,
    pull_number: params.prNumber,
  });
  return result.data;
} catch (error) {
  const message = error instanceof Error ? error.message : String(error);
  console.error("Error fetching PR:", message);
  throw new Error(`Failed to fetch PR: ${message}`);
}
  • Rate limiting: automatic via @octokit/plugin-throttling
  • Pagination: use @octokit/plugin-paginate-rest
  • Auth: ensure GITHUB_TOKEN in .env

Type-Safe Code

// CORRECT - Explicit type definition
export const PRParamsSchema = z.object({
  owner: z.string(),
  repo: z.string(),
  prNumber: z.number(),
});

export interface PRParams {
  owner: string;
  repo: string;
  prNumber: number;
}

// CORRECT - use optional property
interface GoodType {
  value?: string;
}

// CORRECT - use optional chaining when accessing
const result = obj?.value ?? "default";

Adding Analysis Patterns

Security patterns (src/code-analyzer.ts):

{
  pattern: /your-regex-pattern/gi,
  message: "Description of the issue",
}

Code smell patterns:

{
  pattern: /your-regex-pattern/g,
  message: "Description of the smell",
}

Service Layer

All GitHub API calls must go through GitHubService:

// CORRECT
const result = await githubService.getPRDetails(params);

// WRONG - bypasses service
const result = await octokit.pulls.get({...});
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.

  1. 2mo ago First seen · 92 lines · 19 tokens per session scan A f8144e6043ce

Subscribe to this mod's changes

code-patterns is a skill published in the GitHub repository jamesjfoong/github-pr-review-mcp (1 stars, last pushed 9mo ago), licensed MIT. It adds 19 tokens to every session and 433 once invoked, about $0.0001 per session on Opus 5.5. 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.

Related

code-patterns compared with skills from other repositories

code-patterns next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
code-patternsjamesjfoong/github-pr-review-mcpSkill19mo agoMITA19Cursor
pr-descriptionjnMetaCode/skilletSkill21mo agoMITA31Claude Code, Codex
pr-reviewerchainlesschain/chainlesschainSkill11todaynoneA38Claude Code
ask-copilotsickn33/agentic-awesome-skillsSkill49kyesterdayMITA30Claude Code
issuejeremylongshore/tons-of-skills-marketplaceSkill2.9kyesterdayMITA115Claude Code
prjeremylongshore/tons-of-skills-marketplaceSkill2.9kyesterdayMITA105Claude Code
code-review-githubinitializ/forgeSkill235yesterdayApache-2.0A30Claude Code, Codex