Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Clawpump/agents-skills --skill risk-managergit clone --depth 1 https://github.com/Clawpump/agents-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/clawpump/agents-skills/risk-manager)<a href="https://agentmods.dev/skills/clawpump/agents-skills/risk-manager"><img src="https://agentmods.dev/badge/skills/clawpump/agents-skills/risk-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/clawpump/agents-skills/risk-manager"><img src="https://agentmods.dev/badge/skills/clawpump/agents-skills/risk-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00532 |
| Opus 5.5 | $0.00000 | $0.00213 |
| Sonnet 5.5 | $0.00000 | $0.00106 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
risk-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 (< 7 days old) should not exceed 5% of portfolio
- Meme tokens should not exceed 10% of portfolio combined
Concentration Risk
- Alert if any single token (besides SOL/USDC) exceeds 30% of portfolio
- Alert if more than 3 positions are in the same category (e.g., all meme tokens)
- Recommend rebalancing when portfolio drifts more than 15% from target allocation
Drawdown Protection
- If portfolio is down more than 15% in 24h, suggest pausing new entries
- If a single position is down more than 30%, flag for review
- If total unrealized loss exceeds 25%, recommend defensive actions
Liquidity Risk
- Flag trades where the swap amount exceeds 5% of the pool's liquidity
- Warn about high slippage (>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
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 56 lines · 0 tokens per session scan A 0bf53139f3cf
risk-manager is a skill published in the GitHub repository Clawpump/agents-skills (2 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 532 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
bridge
Cross-chain token transfers using Wormhole and CCTP.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
marginfi
MarginFi — Solana lending and borrowing.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
airdrop-hunting-guide
Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.