think-in-code

The reduction is typically ~60x in tokens consumed versus reading each file individually and tallying manually.

Think-in-Code Skill

Principle

1 Bash script = N Read calls avoided.

When you'd read 10 files sequentially to extract a summary, you waste tokens loading full contents into context. Instead: 1 shell pipeline returns the compact aggregated result.

Heuristic: if your task is "for each file in set, compute/extract X, then aggregate" → write the script. Reserve Read for targeted inspection of a specific file you already know matters.

5 Runnable Patterns

1. File size audit (> 100 lines violations)

find . -type f \( -name "*.ts" -o -name "*.tsx" -o -name "*.py" -o -name "*.php" \) \
  -not -path "*/node_modules/*" -not -path "*/vendor/*" \
  | xargs wc -l 2>/dev/null \
  | awk '$1 > 100 && $2 != "total" {print $1, $2}' \
  | sort -rn | head -20

2. Multi-grep symbols (compact JSON)

rg --json -g '*.ts' -g '*.tsx' 'export (function|class|const) (\w+)' src/ \
  | jq -r 'select(.type=="match") | "\(.data.path.text):\(.data.line_number) \(.data.lines.text)"' \
  | head -50

3. Dependencies with versions

# Node
jq -r '.dependencies, .devDependencies | to_entries[] | "\(.key)@\(.value)"' package.json 2>/dev/null

# PHP
jq -r '.require, ."require-dev" | to_entries[] | "\(.key)@\(.value)"' composer.json 2>/dev/null

4. Error log scan

grep -rEn 'ERROR|FATAL|Exception|panic:|stack trace' \
  --include="*.log" logs/ 2>/dev/null \
  | tail -30

5. Lines of code by extension

find . -type f \( -name "*.ts" -o -name "*.tsx" -o -name "*.js" -o -name "*.py" -o -name "*.php" \) \
  -not -path "*/node_modules/*" -not -path "*/vendor/*" -not -path "*/.git/*" \
  -exec wc -l {} + \
  | awk '{ext=$2; sub(/.*\./,"",ext); sum[ext]+=$1} END {for (e in sum) print sum[e], e}' \
  | sort -rn