Adds the plugin-dev plugin to public marketplace. A comprehensive toolkit for
developing Claude Code plugins with 7 expert skills, 3 AI-assisted agents, and
extensive documentation covering the complete plugin development lifecycle.
Key features:
- 7 skills: hook-development, mcp-integration, plugin-structure, plugin-settings,
command-development, agent-development, skill-development
- 3 agents: agent-creator (AI-assisted generation), plugin-validator (structure
validation), skill-reviewer (quality review)
- 1 command: /plugin-dev:create-plugin (guided 8-phase workflow)
- 10 utility scripts for validation and testing
- 21 reference docs with deep-dive guidance (~11k words)
- 9 working examples demonstrating best practices
Changes for public release:
- Replaced all references to internal repositories with "Claude Code"
- Updated MCP examples: internal.company.com → api.example.com
- Updated token variables: ${INTERNAL_TOKEN} → ${API_TOKEN}
- Reframed agent-creation-system-prompt as "proven in production"
- Preserved all ${CLAUDE_PLUGIN_ROOT} references (186 total)
- Preserved valuable test blocks in core modules
Validation:
- All 3 agents validated successfully with validate-agent.sh
- All JSON files validated with jq
- Zero internal references remaining
- 59 files migrated, 21,971 lines added
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
11 KiB
Settings File Parsing Techniques
Complete guide to parsing .claude/plugin-name.local.md files in bash scripts.
File Structure
Settings files use markdown with YAML frontmatter:
---
field1: value1
field2: "value with spaces"
numeric_field: 42
boolean_field: true
list_field: ["item1", "item2", "item3"]
---
# Markdown Content
This body content can be extracted separately.
It's useful for prompts, documentation, or additional context.
Parsing Frontmatter
Extract Frontmatter Block
#!/bin/bash
FILE=".claude/my-plugin.local.md"
# Extract everything between --- markers (excluding the markers themselves)
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$FILE")
How it works:
sed -n- Suppress automatic printing/^---$/,/^---$/- Range from first---to second---{ /^---$/d; p; }- Delete the---lines, print everything else
Extract Individual Fields
String fields:
# Simple value
VALUE=$(echo "$FRONTMATTER" | grep '^field_name:' | sed 's/field_name: *//')
# Quoted value (removes surrounding quotes)
VALUE=$(echo "$FRONTMATTER" | grep '^field_name:' | sed 's/field_name: *//' | sed 's/^"\(.*\)"$/\1/')
Boolean fields:
ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//')
# Use in condition
if [[ "$ENABLED" == "true" ]]; then
# Enabled
fi
Numeric fields:
MAX=$(echo "$FRONTMATTER" | grep '^max_value:' | sed 's/max_value: *//')
# Validate it's a number
if [[ "$MAX" =~ ^[0-9]+$ ]]; then
# Use in numeric comparison
if [[ $MAX -gt 100 ]]; then
# Too large
fi
fi
List fields (simple):
# YAML: list: ["item1", "item2", "item3"]
LIST=$(echo "$FRONTMATTER" | grep '^list:' | sed 's/list: *//')
# Result: ["item1", "item2", "item3"]
# For simple checks:
if [[ "$LIST" == *"item1"* ]]; then
# List contains item1
fi
List fields (proper parsing with jq):
# For proper list handling, use yq or convert to JSON
# This requires yq to be installed (brew install yq)
# Extract list as JSON array
LIST=$(echo "$FRONTMATTER" | yq -o json '.list' 2>/dev/null)
# Iterate over items
echo "$LIST" | jq -r '.[]' | while read -r item; do
echo "Processing: $item"
done
Parsing Markdown Body
Extract Body Content
#!/bin/bash
FILE=".claude/my-plugin.local.md"
# Extract everything after the closing ---
# Counts --- markers: first is opening, second is closing, everything after is body
BODY=$(awk '/^---$/{i++; next} i>=2' "$FILE")
How it works:
/^---$/- Match---lines{i++; next}- Increment counter and skip the---linei>=2- Print all lines after second---
Handles edge case: If --- appears in the markdown body, it still works because we only count the first two --- at the start.
Use Body as Prompt
# Extract body
PROMPT=$(awk '/^---$/{i++; next} i>=2' "$RALPH_STATE_FILE")
# Feed back to Claude
echo '{"decision": "block", "reason": "'"$PROMPT"'"}' | jq .
Important: Use jq -n --arg for safer JSON construction with user content:
PROMPT=$(awk '/^---$/{i++; next} i>=2' "$FILE")
# Safe JSON construction
jq -n --arg prompt "$PROMPT" '{
"decision": "block",
"reason": $prompt
}'
Common Parsing Patterns
Pattern: Field with Default
VALUE=$(echo "$FRONTMATTER" | grep '^field:' | sed 's/field: *//' | sed 's/^"\(.*\)"$/\1/')
# Use default if empty
if [[ -z "$VALUE" ]]; then
VALUE="default_value"
fi
Pattern: Optional Field
OPTIONAL=$(echo "$FRONTMATTER" | grep '^optional_field:' | sed 's/optional_field: *//' | sed 's/^"\(.*\)"$/\1/')
# Only use if present
if [[ -n "$OPTIONAL" ]] && [[ "$OPTIONAL" != "null" ]]; then
# Field is set, use it
echo "Optional field: $OPTIONAL"
fi
Pattern: Multiple Fields at Once
# Parse all fields in one pass
while IFS=': ' read -r key value; do
# Remove quotes if present
value=$(echo "$value" | sed 's/^"\(.*\)"$/\1/')
case "$key" in
enabled)
ENABLED="$value"
;;
mode)
MODE="$value"
;;
max_size)
MAX_SIZE="$value"
;;
esac
done <<< "$FRONTMATTER"
Updating Settings Files
Atomic Updates
Always use temp file + atomic move to prevent corruption:
#!/bin/bash
FILE=".claude/my-plugin.local.md"
NEW_VALUE="updated_value"
# Create temp file
TEMP_FILE="${FILE}.tmp.$$"
# Update field using sed
sed "s/^field_name: .*/field_name: $NEW_VALUE/" "$FILE" > "$TEMP_FILE"
# Atomic replace
mv "$TEMP_FILE" "$FILE"
Update Single Field
# Increment iteration counter
CURRENT=$(echo "$FRONTMATTER" | grep '^iteration:' | sed 's/iteration: *//')
NEXT=$((CURRENT + 1))
# Update file
TEMP_FILE="${FILE}.tmp.$$"
sed "s/^iteration: .*/iteration: $NEXT/" "$FILE" > "$TEMP_FILE"
mv "$TEMP_FILE" "$FILE"
Update Multiple Fields
# Update several fields at once
TEMP_FILE="${FILE}.tmp.$$"
sed -e "s/^iteration: .*/iteration: $NEXT_ITERATION/" \
-e "s/^pr_number: .*/pr_number: $PR_NUMBER/" \
-e "s/^status: .*/status: $NEW_STATUS/" \
"$FILE" > "$TEMP_FILE"
mv "$TEMP_FILE" "$FILE"
Validation Techniques
Validate File Exists and Is Readable
FILE=".claude/my-plugin.local.md"
if [[ ! -f "$FILE" ]]; then
echo "Settings file not found" >&2
exit 1
fi
if [[ ! -r "$FILE" ]]; then
echo "Settings file not readable" >&2
exit 1
fi
Validate Frontmatter Structure
# Count --- markers (should be exactly 2 at start)
MARKER_COUNT=$(grep -c '^---$' "$FILE" 2>/dev/null || echo "0")
if [[ $MARKER_COUNT -lt 2 ]]; then
echo "Invalid settings file: missing frontmatter markers" >&2
exit 1
fi
Validate Field Values
MODE=$(echo "$FRONTMATTER" | grep '^mode:' | sed 's/mode: *//')
case "$MODE" in
strict|standard|lenient)
# Valid mode
;;
*)
echo "Invalid mode: $MODE (must be strict, standard, or lenient)" >&2
exit 1
;;
esac
Validate Numeric Ranges
MAX_SIZE=$(echo "$FRONTMATTER" | grep '^max_size:' | sed 's/max_size: *//')
if ! [[ "$MAX_SIZE" =~ ^[0-9]+$ ]]; then
echo "max_size must be a number" >&2
exit 1
fi
if [[ $MAX_SIZE -lt 1 ]] || [[ $MAX_SIZE -gt 10000000 ]]; then
echo "max_size out of range (1-10000000)" >&2
exit 1
fi
Edge Cases and Gotchas
Quotes in Values
YAML allows both quoted and unquoted strings:
# These are equivalent:
field1: value
field2: "value"
field3: 'value'
Handle both:
# Remove surrounding quotes if present
VALUE=$(echo "$FRONTMATTER" | grep '^field:' | sed 's/field: *//' | sed 's/^"\(.*\)"$/\1/' | sed "s/^'\\(.*\\)'$/\\1/")
--- in Markdown Body
If the markdown body contains ---, the parsing still works because we only match the first two:
---
field: value
---
# Body
Here's a separator:
---
More content after the separator.
The awk '/^---$/{i++; next} i>=2' pattern handles this correctly.
Empty Values
Handle missing or empty fields:
field1:
field2: ""
field3: null
Parsing:
VALUE=$(echo "$FRONTMATTER" | grep '^field1:' | sed 's/field1: *//')
# VALUE will be empty string
# Check for empty/null
if [[ -z "$VALUE" ]] || [[ "$VALUE" == "null" ]]; then
VALUE="default"
fi
Special Characters
Values with special characters need careful handling:
message: "Error: Something went wrong!"
path: "/path/with spaces/file.txt"
regex: "^[a-zA-Z0-9_]+$"
Safe parsing:
# Always quote variables when using
MESSAGE=$(echo "$FRONTMATTER" | grep '^message:' | sed 's/message: *//' | sed 's/^"\(.*\)"$/\1/')
echo "Message: $MESSAGE" # Quoted!
Performance Optimization
Cache Parsed Values
If reading settings multiple times:
# Parse once
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$FILE")
# Extract multiple fields from cached frontmatter
FIELD1=$(echo "$FRONTMATTER" | grep '^field1:' | sed 's/field1: *//')
FIELD2=$(echo "$FRONTMATTER" | grep '^field2:' | sed 's/field2: *//')
FIELD3=$(echo "$FRONTMATTER" | grep '^field3:' | sed 's/field3: *//')
Don't: Re-parse file for each field.
Lazy Loading
Only parse settings when needed:
#!/bin/bash
input=$(cat)
# Quick checks first (no file I/O)
tool_name=$(echo "$input" | jq -r '.tool_name')
if [[ "$tool_name" != "Write" ]]; then
exit 0 # Not a write operation, skip
fi
# Only now check settings file
if [[ -f ".claude/my-plugin.local.md" ]]; then
# Parse settings
# ...
fi
Debugging
Print Parsed Values
#!/bin/bash
set -x # Enable debug tracing
FILE=".claude/my-plugin.local.md"
if [[ -f "$FILE" ]]; then
echo "Settings file found" >&2
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$FILE")
echo "Frontmatter:" >&2
echo "$FRONTMATTER" >&2
ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//')
echo "Enabled: $ENABLED" >&2
fi
Validate Parsing
# Show what was parsed
echo "Parsed values:" >&2
echo " enabled: $ENABLED" >&2
echo " mode: $MODE" >&2
echo " max_size: $MAX_SIZE" >&2
# Verify expected values
if [[ "$ENABLED" != "true" ]] && [[ "$ENABLED" != "false" ]]; then
echo "⚠️ Unexpected enabled value: $ENABLED" >&2
fi
Alternative: Using yq
For complex YAML, consider using yq:
# Install: brew install yq
# Parse YAML properly
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$FILE")
# Extract fields with yq
ENABLED=$(echo "$FRONTMATTER" | yq '.enabled')
MODE=$(echo "$FRONTMATTER" | yq '.mode')
LIST=$(echo "$FRONTMATTER" | yq -o json '.list_field')
# Iterate list properly
echo "$LIST" | jq -r '.[]' | while read -r item; do
echo "Item: $item"
done
Pros:
- Proper YAML parsing
- Handles complex structures
- Better list/object support
Cons:
- Requires yq installation
- Additional dependency
- May not be available on all systems
Recommendation: Use sed/grep for simple fields, yq for complex structures.
Complete Example
#!/bin/bash
set -euo pipefail
# Configuration
SETTINGS_FILE=".claude/my-plugin.local.md"
# Quick exit if not configured
if [[ ! -f "$SETTINGS_FILE" ]]; then
# Use defaults
ENABLED=true
MODE=standard
MAX_SIZE=1000000
else
# Parse frontmatter
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$SETTINGS_FILE")
# Extract fields with defaults
ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//')
ENABLED=${ENABLED:-true}
MODE=$(echo "$FRONTMATTER" | grep '^mode:' | sed 's/mode: *//' | sed 's/^"\(.*\)"$/\1/')
MODE=${MODE:-standard}
MAX_SIZE=$(echo "$FRONTMATTER" | grep '^max_size:' | sed 's/max_size: *//')
MAX_SIZE=${MAX_SIZE:-1000000}
# Validate values
if [[ "$ENABLED" != "true" ]] && [[ "$ENABLED" != "false" ]]; then
echo "⚠️ Invalid enabled value, using default" >&2
ENABLED=true
fi
if ! [[ "$MAX_SIZE" =~ ^[0-9]+$ ]]; then
echo "⚠️ Invalid max_size, using default" >&2
MAX_SIZE=1000000
fi
fi
# Quick exit if disabled
if [[ "$ENABLED" != "true" ]]; then
exit 0
fi
# Use configuration
echo "Configuration loaded: mode=$MODE, max_size=$MAX_SIZE" >&2
# Apply logic based on settings
case "$MODE" in
strict)
# Strict validation
;;
standard)
# Standard validation
;;
lenient)
# Lenient validation
;;
esac
This provides robust settings handling with defaults, validation, and error recovery.