- Home
- Skills
- Trading & Investing
- pretrade risk auditor
More screenshots
Works with the AI Agents you already use
pretrade risk auditor
Automated pre-trade risk auditor that calculates total heat, sector concentration, and sizing math for trade plans.
$11
pretrade risk auditor
Example session with this skill installed
/pretrade check trades.csv --account 50000
- Read your context and instructions
- Compiled the pretrade risk auditor
COMMITMENT REPORT: Total Heat 4.2%. VERDICT: "RESIZE BEFORE SENDING" due to R3 Concentration. Finding: 55% of risk is in Tech sector (Limit 40%). Trade-off: Keeping this concentration gains sector momentum but costs $1,250 in excess risk if the sector rotates.
Connects securely to your tools. The creator never sees your data.
About this skill
Pre-Trade Risk Auditor™ v1.0.0
Prices a set of planned trades before any of them is sent. Answers one question first: if every stop is hit, what does this plan cost?
Seven rules in four families — Heat, Exposure, Asymmetry, Thesis. No forecasts, no signals, no instrument picks.
Run it in ten seconds
python3 scripts/check_plan.py
No arguments prices the bundled sample on a 100,000 account and labels it a demonstration.
Run it on your plan
python3 scripts/check_plan.py my-plan.csv --account 250000
python3 scripts/check_plan.py my-plan.csv --account 250000 --json
Required columns: symbol, direction, entry, stop, size
Optional: target (reward:risk), sector (concentration, correlation), note (rationale)
The rules
| ID | Rule | Default limit |
|---|---|---|
| R1 | Oversized position | risk > 2% of account |
| R2 | Total heat | combined risk > 6% |
| R3 | Concentration | > 40% of risk in one sector |
| R4 | Thin payoff | reward:risk < 1.5 |
| R5 | Inverted stop | stop on the profitable side — BLOCK |
| R6 | Correlated pair | same-direction positions in one sector |
| R7 | Missing rationale | blank, or a reactive note |
Every limit has a written reason in references/risk-thresholds.md, and every
constant is at the top of scripts/check_plan.py. Change a number deliberately rather
than arguing with a verdict.
Verdicts
BLOCK → DO NOT SEND · HIGH → RESIZE BEFORE SENDING · MEDIUM → SEND WITH THE TRADE-OFF NAMED · none → WITHIN PLAN
What it does not know
Real correlation (sector is a label you supply), volatility, your existing open book unless you include it, and whether any of it will work. It prices the plan. It does not judge it.
Pairs with
Trade Post-Mortem Engine™ — the same discipline after the trades close. One prices the commitment, the other audits the execution.
Verified
monna-verify v1.0.0 · 2026-08-22 · CLEAN · 30/30 · 0 blockers · 0 fails ·
0 AI-language hits. Scanned by Skill Security Auditor™: CLEAR.
Disclaimer
For educational and self-review use. Not financial, investment, or tax advice. The author is not a licensed advisor. Trading carries risk of loss.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Trading & Investing.
Requires specific CSV columns. Does not know about open positions unless included in the file. Does not forecast prices or recommend instruments. Requires Python 3.
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
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
- Software
Python