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 nansen-ai/nansen-cli --skill nansen-polymarket-insider-scangit clone --depth 1 https://github.com/nansen-ai/nansen-cliWrote 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/nansen-ai/nansen-cli/nansen-polymarket-insider-scan)<a href="https://agentmods.dev/skills/nansen-ai/nansen-cli/nansen-polymarket-insider-scan"><img src="https://agentmods.dev/badge/skills/nansen-ai/nansen-cli/nansen-polymarket-insider-scan/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/nansen-ai/nansen-cli/nansen-polymarket-insider-scan"><img src="https://agentmods.dev/badge/skills/nansen-ai/nansen-cli/nansen-polymarket-insider-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00040 | $0.00801 |
| Opus 5 | $0.00020 | $0.00400 |
| Sonnet 5 | $0.00008 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
nansen-polymarket-insider-scan 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 10d 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.
What it actually says
PM Suspicious Wallet Scanner
Answers: "Are there wallets with suspicious trading patterns in this Polymarket market?"
# 1. Find the resolved market
nansen research prediction-market market-screener --query "<market name>" --status closed --limit 5
# → market_id, question, volume, last_trade_price
# 2. Get top winners (positive PnL) — paginate if needed, keep per_page <= 10
MID=<market_id>
nansen research prediction-market pnl-by-market --market-id $MID --limit 10
# → address (proxy), owner_address (wallet), side_held, net_buy_cost_usd, total_pnl_usd
# 3. For each top winner, run these three calls (use proxy address for PM, owner for profiler):
PROXY=<address_from_pnl>
nansen research prediction-market trades-by-address --address $PROXY --limit 100
# → market_id, market_question, side, price, size, usdc_value, taker_action, timestamp
OWNER=<owner_address_from_pnl>
nansen research profiler historical-balances --address $OWNER --chain polygon --days 365 --sort block_timestamp:asc --limit 100
# → block_timestamp, value_usd, token_symbol — first non-zero value_usd = wallet funding date
nansen research profiler labels --address $OWNER --chain polygon
# → label, category
For each winner, compute ROI = total_pnl_usd / net_buy_cost_usd * 100 (skip ROI flags if net_buy_cost_usd <= 0), then score (0–13). Within each tier group, apply only the highest matching flag:
| Flag | Pts | Trigger |
|---|---|---|
| NEW_WALLET | 3 | First funded within 7 days of now |
| YOUNG_WALLET | 1 | First funded 8–28 days ago (skip if NEW_WALLET fires) |
| SINGLE_MARKET | 3 | trades-by-address shows only 1 distinct market_id |
| FEW_MARKETS | 1 | 2–3 distinct market_ids (skip if SINGLE_MARKET fires) |
| EXTREME_ROI | 3 | ROI >= 500% |
| HIGH_ROI | 2 | ROI 200–499% (skip if EXTREME_ROI fires) |
| LATE_ENTRY | 2 | Any trade on this market at price >= 0.80 |
| LARGE_POSITION | 2 | net_buy_cost_usd >= $10k |
| KNOWN_ENTITY | -2 | Has Nansen labels |
Flagged at score >= 3. High risk at >= 7. High-confidence suspicious pattern: NEW_WALLET + SINGLE_MARKET + EXTREME_ROI (score 9+).
If owner_address is invalid (e.g. "0x"), use the proxy address for profiler calls too. If historical-balances returns no records with value_usd > 0, the wallet may predate the 365-day window — treat wallet age as unknown and skip NEW_WALLET / YOUNG_WALLET flags. Pause ~1.5s between wallets to avoid rate limits. Skip wallets that error and continue scanning.
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.
- 10d ago First seen · 63 lines · 40 tokens per session scan A 36634b1a9b5e
nansen-polymarket-insider-scan is a skill published in the GitHub repository nansen-ai/nansen-cli (135 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 801 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
cobie-cycle-filter
Use when evaluating crypto decisions through a Cobie-style cycle filter: common-sense risk, narrative traps, leverage humility, and avoiding obvious stupid trades.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
bridge
Cross-chain token transfers using Wormhole and CCTP.