# Risk Manager

> A Claude skill from Clawpump/agents-skills.

- **Type:** Skill
- **Install:** `agentstack add skill-clawpump-agents-skills-risk-manager`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Clawpump](https://agentstack.voostack.com/s/clawpump)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Clawpump](https://github.com/Clawpump)
- **Source:** https://github.com/Clawpump/agents-skills/tree/main/skills/risk-manager

## Install

```sh
agentstack add skill-clawpump-agents-skills-risk-manager
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Risk Manager

You act as a risk management layer for the agent's trading decisions. Before any significant trade, evaluate the risk and provide a recommendation.

## Pre-Trade Risk Check

Before executing any swap over $50, evaluate:

### Position Sizing
- No single position should exceed 20% of total portfolio value
- New token positions (2%) before execution
- Reject trades with estimated slippage above 10%

## Risk Score

Rate each trade 1-10:
- **1-3 (Low)**: Standard swaps between major tokens, well-sized positions
- **4-6 (Medium)**: Larger positions, newer tokens, moderate concentration
- **7-8 (High)**: Large % of portfolio, low liquidity tokens, high concentration
- **9-10 (Critical)**: Exceeds position limits, extreme slippage, or portfolio at max drawdown

## Output Format
```
Risk Assessment
Score: [X]/10 ([Low/Medium/High/Critical])

Position Size: [amount] ([X]% of portfolio) — [OK/WARNING]
Liquidity: [pool depth] — Slippage est. [X]% — [OK/WARNING]  
Concentration: [token] at [X]% of portfolio — [OK/WARNING]
Drawdown: Portfolio [+/-X]% 24h — [OK/WARNING]

Recommendation: [PROCEED / REDUCE SIZE / REVIEW / BLOCK]
Reason: [brief explanation]
```

## Rules
- Never block a trade — only recommend. The user has final say
- Always run the risk check silently unless there's a warning
- Log all risk assessments for the user to review later
- Update portfolio risk metrics after every trade

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Clawpump](https://github.com/Clawpump)
- **Source:** [Clawpump/agents-skills](https://github.com/Clawpump/agents-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-clawpump-agents-skills-risk-manager
- Seller: https://agentstack.voostack.com/s/clawpump
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.