PLS Agent Tools

Provides utilities for safe file handling, JSON/YAML editing, regex text processing, system commands, encoding, date/time, and validation tasks.

Security Scan

The skill is an instruction-only collection of shell/CLI examples whose contents match its stated purpose, but it provides powerful system commands (delete, kill, network calls) without declaring dependencies—review and sandbox before use.

Purpose & Capability

The name and description (file handling, JSON/YAML editing, regex, system commands, encoding, date/time, validation) match the SKILL.md examples. The examples rely on common Unix tooling (jq, yq, rsync, curl, lsof, trash, etc.), which is coherent for a utility skill.

Instruction Scope

Instructions include potentially destructive or high-impact commands (trash/mv/rm, find -exec trash, kill -9 via xargs, lsof|xargs kill) and network operations (curl POST). These are within the stated utility scope but grant broad capability to modify/delete local files and to send data externally; the SKILL.md does not place safety limits or require confirmations.

Install Mechanism

There is no install spec (instruction-only), which is the lowest install risk. No archives or remote downloads are performed by the skill itself.

Credentials

The skill declares no required environment variables or credentials, which is appropriate. However, it references many external CLI tools without listing them as dependencies; verify the runtime environment provides the expected tools (and versions) before relying on the examples.

Persistence & Privilege

The skill does not request persistent/system-wide privileges and is not forced-always. It uses the platform-default ability for autonomous invocation; combined with the destructive commands above, autonomous execution increases blast radius, so consider restricting autonomous use if you want tighter control.

Assessment

This skill is essentially a cookbook of shell commands that align with its stated purpose. Before installing or enabling it for autonomous use: (1) verify your agent runtime has the referenced tools (jq, yq, rsync, trash, lsof, curl, etc.) or adapt examples to your environment; (2) be aware examples include destructive operations (deleting files, killing processes) and network requests—run them in a sandbox or with backups and least-privilege accounts first; (3) if you don't want the agent to run these commands automatically, disable autonomous invocation for this skill or require explicit user invocation; (4) review the SKILL.md and remove or modify any commands that would operate on sensitive paths or send data to external endpoints you don't control.

Agent Tools - Universal Utility Belt

A collection of practical utilities for everyday agent operations.

File Operations

Safe File Manipulation

Always use trash instead of rm when possible:

trash /path/to/file  # Safer deletion (recoverable)

Bulk File Operations

# Rename files with pattern
for f in *.txt; do mv "$f" "${f/.txt/.md}"; done

# Find and delete files older than 7 days
find . -name "*.log" -mtime +7 -exec trash {} \;

# Copy with progress
rsync -av --progress src/ dest/

JSON/YAML Processing

JSON Operations (jq)

# Pretty print
jq '.' file.json

# Extract field
jq '.field' file.json

# Update field
jq '.field = "new_value"' file.json > tmp && mv tmp file.json

# Merge JSON files
jq -s 'add' file1.json file2.json

YAML Operations (yq)

# Read value
yq '.key' file.yaml

# Update value
yq '.key = "value"' -i file.yaml

# Convert YAML to JSON
yq -o=json '.' file.yaml

Text Processing

Common Patterns

# Search and replace in files
sed -i '' 's/old/new/g' file.txt

# Extract matches
grep -oP 'pattern' file.txt

# Count occurrences
grep -c 'pattern' file.txt

# Remove duplicate lines
sort file.txt | uniq > deduplicated.txt

# Extract column
awk '{print $2}' file.txt

System Utilities

Process Management

# Find process by name
ps aux | grep process_name

# Kill by port
lsof -ti:3000 | xargs kill -9

# Monitor resource usage
htop

Network Operations

# Check port availability
lsof -i :PORT

# Download with retry
curl --retry 3 -O URL

# Test endpoint
curl -X POST -H "Content-Type: application/json" -d '{"key":"value"}' URL

Encoding/Decoding

# Base64 encode/decode
echo "text" | base64
echo "dGV4dAo=" | base64 -d

# URL encode/decode
python3 -c "import urllib.parse; print(urllib.parse.quote('text'))"
python3 -c "import urllib.parse; print(urllib.parse.unquote('text%20here'))"

# JSON escape/unescape
jq -R . <<< 'string to escape'
jq -r . <<< '"escaped string"'

Date/Time Utilities

# Current timestamp
date +%s

# ISO format
date -u +"%Y-%m-%dT%H:%M:%SZ"

# Convert timestamp
date -r 1234567890

# Timezone conversion
TZ="America/Chicago" date

Validation Helpers

# Validate JSON
jq empty file.json && echo "Valid JSON"

# Validate YAML
python3 -c "import yaml; yaml.safe_load(open('file.yaml'))" && echo "Valid YAML"

# Check JSON schema
check-jsonschema --schemafile schema.json document.json

Quick Reference

Task	Command
Safe delete	trash file
Find files	find . -name "*.ext"
Search in files	grep -r "pattern" .
Replace text	sed -i '' 's/old/new/g'
JSON pretty	jq '.'
YAML read	yq '.key'
Port check	lsof -i :PORT
Base64 decode	base64 -d