Works with the AI Agents you already use
Boons
A multi-skill package for disciplined coding, original systems design, and authorized security analysis.
Free
Boons
Example session with this skill installed
Build me a simple Python CLI tool that tracks daily water intake. It should feel lightweight and punchy. Make sure to include basic tests for the logic.
- Read your context and instructions
- Compiled the boons
I have built a lightweight CLI tool for tracking water intake. It focuses on speed and minimal friction, using a local JSON file for persistence.
WaterTrack CLI
import sys
import json
import datetime
from pathlib import Path
DATA_FILE = Path.home() / ".watertrack.json"
def load_data():
if not DATA_FILE.exists():
return {"logs": {}}
with open(DATA_FILE, "r") as f:
return json.load(f)
def save_data(data):
with open(DATA_FILE, "w") as f:
json.dump(data, f)
def log_water(amount_ml):
data = load_data()
today = str(datetime.date.today())
data["logs"][today] = data["logs"].get(today, 0) + amount_ml
save_data(data)
return data["logs"][today]
def main():
if len(sys.argv) < 2:
print("Usage: wt <amount_ml>")
sys.exit(1)
try:
amount = int(sys.argv[1])
total = log_water(amount)
print(f"Added {amount}ml. Total for today: {total}ml. Stay hydrated.")
except ValueError:
print("Error: Amount must be an integer.")
sys.exit(1)
if __name__ == "__main__":
main()
Logic Test
def test_intake_logic():
# Mocking data storage for logic verification
mock_data = {"logs": {}}
today = "2023-10-27"
amount = 500
mock_data["logs"][today] = mock_data["logs"].get(today, 0) + amount
assert mock_data["logs"][today] == 500
print("Logic test passed: Intake correctly summed.")
if __name__ == "__main__":
test_intake_logic()
Next steps
- Run
python watertrack.py 250to log your first drink. - Alias the command to
wtin your shell for faster access. - Add a
historycommand if you need to see past performance.
Connects securely to your tools. The creator never sees your data.
About this skill
Development often forces a choice between disciplined engineering and creative momentum. Boons is a collection of six high-utility skills designed to bridge that gap, providing tools for builders who need to move fast without breaking their technical standards. Whether you are scaffolding a new project, synthesizing complex game systems, or conducting authorized security reviews, these skills prioritize intentionality, scope control, and verifiable results.
What it does
- Disciplined Coding builds software by fusing creative intent with rigorous engineering loops like shape, weight, and feel.
- Systems Synthesis designs original mechanics, rules, and power systems for games or fiction by mapping logic across domains.
- Voice & Editing refines technical or creative text while strictly preserving factual claims, figures, and certainty markers.
- Security Triage organizes bug bounty reconnaissance and evidence within authorized boundaries to draft clear disclosures.
- Defensive Auditing plans security reviews and risk mitigations based on verified observations and proportionate remediation.
- Artifact Analysis transforms technical artifacts into high-level evidence and findings to guide downstream automation.
How it works
- Define Intent by providing a one-line concept, a specific codebase, or an authorized security target.
- Set Weight to determine if the output should be a lightweight script, a rich system, or a formal disclosure.
- Execute Loop through specific workflows for building, synthesizing, or triaging based on the selected skill.
- Verify & Exit with a short note on what was built, what was inferred, and what remains unverified.
Frameworks & tools
This package is framework-agnostic and works with any language or environment. It integrates with existing test suites, version control systems, and security tools like Ghidra when available in the workspace.
Why this beats prompting it yourself
Generic prompts often result in scope creep, hallucinated dependencies, or ignored constraints. Boons enforces a "smallest whole" philosophy and a mandatory verification step, ensuring that creative output remains technically sound and legally compliant.
Use cases
- Rapidly prototyping tools or games that feel right without writing a full spec.
- Designing original RPG mechanics or magic systems that avoid copyright infringement.
- Drafting professional security reports from raw reconnaissance data.
- Refactoring complex documentation while keeping technical details 100% intact.
Known limitations
Does not perform active network scanning, exploits, or external deployments. Requires user-provided authorization for all security-related tasks and cannot resolve factual conflicts in source text.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires user-provided authorization for security tasks. No active network scanning or deployments. Cannot resolve factual conflicts in source text or provide credentials.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account
- Software
Node.js
Git