peterkc · November 27, 2025 12:48 · SpeedRanger · Nov 27, 2025
diff --git a/settings.json b/settings.json
 {
  "hooks": {
    "UserPromptSubmit": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "$CLAUDE_PROJECT_DIR/.claude/hooks/you_are_not_right.sh"
          }
        ]
      }
    ]
  }
 }
diff --git a/you_are_not_right.sh b/you_are_not_right.sh
 #!/usr/bin/env bash
 set -euo pipefail
 trap 'echo "at line $LINENO, exit code $? from $BASH_COMMAND" >&2; exit 1' ERR

 # This is a Claude Code hook to stop it saying "you are right".
 #
 # Installation:
 # 1. Save this script and chmod +x it to make it executable.
 # 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.

 stdin=$(cat)
 transcript_path=$(echo "$stdin" | jq -r ".transcript_path")

 # We'll look through the last 5 items in the transcript.
 # Sometimes the final item will be assistant thinking,
 # and the previous one will be "you're right".
 # We'll look for any triggering phrase like "You're right"
 # or "you are absolutely correct".
 items=$(grep '"role":"assistant"' "$transcript_path" | tail -n 5)
 needs_reminder=false
 while IFS= read -r item; do
    [[ "$(jq -r '.type // empty' <<< "$item")" == "assistant" ]] || continue
    [[ "$(jq -r '.message.content[0].type // empty' <<< "$item")" == "text" ]] || continue
    text=$(jq -r '.message.content[0].text' <<< "$item")
    [[ "${text:0:80}" =~ .*[Yy]ou.*(right|correct) ]] && needs_reminder=true
    [[ "${text:0:80}" =~ .*[Aa]bsolutely ]] && needs_reminder=true
    [[ "${text:0:80}" =~ .*사용자가.*맞다 ]] && needs_reminder=true  # Korean
    [[ "${text:0:80}" =~ .*맞습니다 ]] && needs_reminder=true  # Korean
 done <<< "$items"
 [[ "$needs_reminder" == "true" ]] || exit 0

 # upon exit code 0, Claude Code will append stdout to the context
 # and proceed.
 cat <<'EOF'
 <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>
 EOF

 exit 0
	{
	"hooks": {
	"UserPromptSubmit": [
	{
	"hooks": [
	{
	"type": "command",
	"command": "$CLAUDE_PROJECT_DIR/.claude/hooks/you_are_not_right.sh"
	}
	]
	}
	]
	}
	}
	#!/usr/bin/env bash
	set -euo pipefail
	trap 'echo "at line $LINENO, exit code $? from $BASH_COMMAND" >&2; exit 1' ERR

	# This is a Claude Code hook to stop it saying "you are right".
	#
	# Installation:
	# 1. Save this script and chmod +x it to make it executable.
	# 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.

	stdin=$(cat)
	transcript_path=$(echo "$stdin" \| jq -r ".transcript_path")

	# We'll look through the last 5 items in the transcript.
	# Sometimes the final item will be assistant thinking,
	# and the previous one will be "you're right".
	# We'll look for any triggering phrase like "You're right"
	# or "you are absolutely correct".
	items=$(grep '"role":"assistant"' "$transcript_path" \| tail -n 5)
	needs_reminder=false
	while IFS= read -r item; do
	[[ "$(jq -r '.type // empty' <<< "$item")" == "assistant" ]] \|\| continue
	[[ "$(jq -r '.message.content[0].type // empty' <<< "$item")" == "text" ]] \|\| continue
	text=$(jq -r '.message.content[0].text' <<< "$item")
	[[ "${text:0:80}" =~ .[Yy]ou.(right\|correct) ]] && needs_reminder=true
	[[ "${text:0:80}" =~ .*[Aa]bsolutely ]] && needs_reminder=true
	[[ "${text:0:80}" =~ .사용자가.맞다 ]] && needs_reminder=true # Korean
	[[ "${text:0:80}" =~ .*맞습니다 ]] && needs_reminder=true # Korean
	done <<< "$items"
	[[ "$needs_reminder" == "true" ]] \|\| exit 0

	# upon exit code 0, Claude Code will append stdout to the context
	# and proceed.
	cat <<'EOF'
	<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>
	EOF

	exit 0