peterkc/settings.json

#Requires -Version 5.1

# Set strict mode and stop on errors (equivalent to set -euo pipefail)
$ErrorActionPreference = 'Stop'
Set-StrictMode -Version Latest

try {
    # This is a Claude Code hook to stop it saying "you are right".
    #
    # Installation:
    # 1. Save this script as a .ps1 file
    # 2. Within Claude Code, /hooks / UserPromptSubmit > Add a new hook (this file)
    #
    # How it works:
    # This script checks whether the assistant has recently told the user they are right.
    # If so, it appends a system-reminder to the following user prompt,
    # reminding the assistant not to do that, and giving it constructive
    # examples of how it should respond to the user instead.

    # Read stdin
    $stdin = [Console]::In.ReadToEnd()
    
    # Parse JSON and extract transcript_path
    $inputJson = $stdin | ConvertFrom-Json
    $transcriptPath = $inputJson.transcript_path

    # Read transcript file and get last 5 assistant messages
    $transcriptContent = Get-Content -Path $transcriptPath -Raw
    $allLines = $transcriptContent -split "`n"
    $assistantLines = $allLines | Where-Object { $_ -match '"role":"assistant"' } | Select-Object -Last 5

    # Check for triggering phrases
    $needsReminder = $false
    foreach ($line in $assistantLines) {
        $item = $line | ConvertFrom-Json
        
        # Skip if not the right type
        if ($item.type -ne "assistant") { continue }
        if ($item.message.content[0].type -ne "text") { continue }
        
        $text = $item.message.content[0].text
        $first80 = $text.Substring(0, [Math]::Min(80, $text.Length))
        
        # Check for triggering patterns
        if ($first80 -match '[Yy]ou.*(right|correct)') { $needsReminder = $true }
        if ($first80 -match '[Aa]bsolutely') { $needsReminder = $true }
        if ($first80 -match '사용자가.*맞다') { $needsReminder = $true }  # Korean
        if ($first80 -match '맞습니다') { $needsReminder = $true }  # Korean
    }

    # If no reminder needed, exit successfully
    if (-not $needsReminder) { exit 0 }

    # Output the system reminder
    @'
<system-reminder>
Avoid reflexive agreement phrases like "you are right" or "absolutely correct."

Instead, engage thoughtfully: analyze the user's reasoning, identify potential improvements, 
or provide substantive confirmation when their approach is sound.

When the user presents a valid solution:
- Acknowledge the correctness with specific technical reasoning
- Consider edge cases, alternative approaches, or potential optimizations
- Build collaboratively rather than merely agreeing

When the user's approach has issues:
- Identify specific problems or gaps
- Suggest concrete improvements
- Explain the technical reasoning behind your analysis

<example>
user: It's failing on empty inputs, so we should add a null-check.
assistant: That addresses the immediate null case. For robustness, 
checking for all falsy values (null, undefined, empty string) would 
handle the broader input validation concern more comprehensively.
</example>

<example>
user: I'm concerned that we haven't handled connection failure.
assistant: Good catch - the connection attempt on line 42 lacks error 
handling. If that fails, the catch block on line 49 won't trigger. 
Moving the try-catch around the connection attempt would resolve this.
</example>

<example>
user: We should use async/await here instead of promises.
assistant: Async/await would improve readability here. The current promise 
chain handles errors correctly and the logic is sound - converting to 
async/await maintains the same error handling while making the code 
more maintainable.
</example>
</system-reminder>
'@

    exit 0
}
catch {
    Write-Error "Error at line $($_.InvocationInfo.ScriptLineNumber): $_"
    exit 1
}