What is code-analyzer?

A guide for maintaining a code analysis engine that scans source files for security problems, code smells, and quality measurements.

Use it when adding or fixing scan patterns, security checks, code-smell detection, or quality metrics.

It keeps analysis code predictable by requiring side-effect-free checks and consistent structured results.

How jamesjfoong/github-pr-review-mcp configures Claude Code and Cursor

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/agents/code-analyzer.md

Clone the repo

git clone --depth 1 https://github.com/jamesjfoong/github-pr-review-mcp

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jamesjfoong/github-pr-review-mcp/code-analyzer/github.svg)](https://agentmods.dev/agents/jamesjfoong/github-pr-review-mcp/code-analyzer)

Your own site

<a href="https://agentmods.dev/agents/jamesjfoong/github-pr-review-mcp/code-analyzer"><img src="https://agentmods.dev/badge/agents/jamesjfoong/github-pr-review-mcp/code-analyzer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/jamesjfoong/github-pr-review-mcp/code-analyzer"><img src="https://agentmods.dev/badge/agents/jamesjfoong/github-pr-review-mcp/code-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 291 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.

Model	Per session	Once invoked
Fable 5.1	$0.00023	$0.00291
Opus 5.5	$0.00009	$0.00116
Sonnet 5.5	$0.00005	$0.00058
Haiku 4.5	$0.00002	$0.00029

Measured 2mo ago against content hash 290089302cc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-analyzer 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/agents/code-analyzer.md · 49 lines

What it actually says

Code Analyzer Agent

Purpose: Maintains and extends the code analysis engine.

Responsibilities

Add new analysis patterns to CodeAnalyzer class
Keep analyzers pure (no side effects)
Return structured results: { issues, suggestions, metrics }
Security pattern detection
Code smell detection
Quality metrics calculation

When to Use

When adding new analysis features, improving existing analyzers, or fixing analysis bugs.

Key Rules

Keep CodeAnalyzer pure - no side effects
Return structured results with issues, suggestions, and metrics
Add patterns to appropriate arrays (security, code smells, etc.)
Test analyzers with various code samples
Patterns should be regex-based for code scanning

Examples

// ✅ CORRECT
analyze(files: CodeFile[]): AnalysisResult {
  const issues: CodeIssue[] = [];
  // Pure function - no side effects
  // Returns structured result
  return { issues, suggestions, metrics };
}

// ❌ WRONG - Side effects
analyze(files: CodeFile[]): AnalysisResult {
  console.log("Analyzing..."); // Side effect
  this.cache = files; // Side effect
  return { issues: [] };
}

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.

2mo ago First seen · 49 lines · 23 tokens per session scan A 290089302cc3

Subscribe to this mod's changes

code-analyzer is an agent published in the GitHub repository jamesjfoong/github-pr-review-mcp (1 stars, last pushed 9mo ago), licensed MIT. It adds 23 tokens to every session and 291 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.

Debugging Security github mcp pull-request review

code-analyzer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
code-analyzerjamesjfoong/github-pr-review-mcp	Agent	1	9mo ago	MIT	A	23	Claude Code, Cursor
pre-commit-reviewercostajohnt/oss-autopilot	Agent	26	4d ago	MIT	A	243	Claude Code
bug-detectorliatrio-labs/claude-code-gauntlet	Agent	13	yesterday	Apache-2.0	A	15	Claude Code
challengerliatrio-labs/claude-code-gauntlet	Agent	13	yesterday	Apache-2.0	A	17	Claude Code
code-revieweromgcarlo/fushiguro-mcp	Agent	0	2mo ago	MIT	A	30	Claude Code
performance-optimizationTrevorEdris/fellowship-of-the-workflows	Agent	2	4mo ago	none	A	52	Claude Code
codebase-pattern-finderTrevorEdris/fellowship-of-the-workflows	Agent	2	4mo ago	none	A	32	Claude Code

github-pr-review-mcp: Agent for Claude Code