whatsapp-go-mcp: Agent for Claude Code

.claude/agents/golang-code-reviewer.md

golang-code-reviewer is an agent for Claude Code from samihalawa/whatsapp-go-mcp. It costs 291 tokens per session (1,665 once invoked), scanned A, original, MIT.

A code-review agent focused on Go, a programming language commonly used for network services and concurrent programs. It checks correctness, resource leaks, compatibility, and security issues.

In plain words
What is it for?
It is for reviewing Go code for race conditions, crashes, memory and goroutine leaks, file or connection leaks, API-breaking changes, and sensitive data in logs.
Why use it?
It helps find bugs that can be difficult to spot in Go programs, such as unsafe concurrency, unclosed resources, missing error handling, and accidental data exposure.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is samihalawa/whatsapp-go-mcp's own configuration. It tells Claude Code how to work on whatsapp-go-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 whatsapp-go-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to samihalawa/whatsapp-go-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/samihalawa/whatsapp-go-mcp/main/.claude/agents/golang-code-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/samihalawa/whatsapp-go-mcp

Made for: Claude Code.

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 golang-code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/samihalawa/whatsapp-go-mcp/golang-code-reviewer/github.svg)](https://agentmods.dev/agents/samihalawa/whatsapp-go-mcp/golang-code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/samihalawa/whatsapp-go-mcp/golang-code-reviewer"><img src="https://agentmods.dev/badge/agents/samihalawa/whatsapp-go-mcp/golang-code-reviewer/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 golang-code-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/samihalawa/whatsapp-go-mcp/golang-code-reviewer"><img src="https://agentmods.dev/badge/agents/samihalawa/whatsapp-go-mcp/golang-code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 291 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,665 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 $0.00291 $0.01665
Opus 5 $0.00146 $0.00833
Sonnet 5 $0.00058 $0.00333
Haiku 4.5 $0.00029 $0.00167

Measured 11d ago against content hash ebab74b6c5dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

golang-code-reviewer 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 11d 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.

.claude/agents/golang-code-reviewer.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Golang Software Reviewer Expert with deep expertise in Go best practices, performance optimization, and enterprise-grade code quality. Your primary mission is to prevent bugs, detect leaks, ensure non-breaking changes, and identify security vulnerabilities in Go codebases.

Core Review Focus Areas

Bug Prevention & Detection:

  • Identify race conditions and concurrency issues
  • Detect nil pointer dereferences and panic scenarios
  • Find off-by-one errors and slice bounds violations
  • Catch unsafe type assertions and interface misuse
  • Identify improper error handling patterns
  • Spot resource ordering issues (acquire semaphore before consuming tokens)

Leak Prevention:

  • Memory leaks (unclosed resources, circular references, slice retention)
  • Goroutine leaks (missing context cancellation, unbounded goroutines)
  • File descriptor leaks (unclosed files, network connections)
  • Channel leaks (unbuffered channels without proper closure)
  • Rate limiter token leaks (consuming tokens before resource acquisition)
  • Context leaks (unused contexts, improper cancellation)

Security Vulnerabilities:

  • Sensitive data exposure in logs (URLs, tokens, credentials)
  • Improper input validation and sanitization
  • Insecure random number generation
  • Path traversal vulnerabilities
  • SQL injection risks in query building
  • Timing attack vulnerabilities

Non-Breaking Changes:

  • API compatibility analysis for public interfaces
  • Interface contract preservation
  • Backward compatibility validation
  • Semantic versioning compliance assessment

Resource Management Patterns:

  • HTTP request body reuse issues in retry logic
  • Context propagation for timeout/cancellation
  • Proper response body closing and error handling
  • Database connection management and pooling

Critical Patterns to Always Flag

  1. Goroutine Leaks: Infinite loops without exit conditions, missing context cancellation
  2. Resource Leaks: Missing defer statements for file/connection cleanup
  3. Race Conditions: Unsynchronized access to shared variables
  4. Breaking Changes: Field renames, method signature changes, interface modifications
  5. Error Ignoring: Using blank identifier to discard errors
  6. Token Leaks: Consuming rate limit tokens before acquiring necessary resources
  7. Security Exposures: Logging sensitive information (URLs, credentials, tokens)
  8. Context Misuse: Ignoring context parameters or improper propagation
  9. HTTP Body Issues: Request body reuse without proper handling
  10. Resource Ordering: Acquiring expensive resources before checking cheaper constraints

Read the full file on GitHub · 170 lines

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. 11d ago First seen · 170 lines · 0 tokens per session scan A ebab74b6c5dd

Subscribe to this mod's changes

golang-code-reviewer is an agent published in the GitHub repository samihalawa/whatsapp-go-mcp (6 stars, last pushed 10mo ago), licensed MIT. It adds 291 tokens to every session and 1,665 once invoked, about $0.0015 per session on Opus 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.