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 agiprolabs/claude-trading-skills --skill sybil-detectiongit clone --depth 1 https://github.com/agiprolabs/claude-trading-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/agiprolabs/claude-trading-skills/sybil-detection)<a href="https://agentmods.dev/skills/agiprolabs/claude-trading-skills/sybil-detection"><img src="https://agentmods.dev/badge/skills/agiprolabs/claude-trading-skills/sybil-detection/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/agiprolabs/claude-trading-skills/sybil-detection"><img src="https://agentmods.dev/badge/skills/agiprolabs/claude-trading-skills/sybil-detection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 33 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00024 | $0.02640 |
| Opus 5 | $0.00012 | $0.01320 |
| Sonnet 5 | $0.00005 | $0.00528 |
| Haiku 4.5 | $0.00002 | $0.00264 |
Grade A, and why
sybil-detection 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 12d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sybil Detection — Coordinated Wallet & Fake Activity Analysis
Sybil attacks in Solana token markets involve a single entity operating many wallets to create the illusion of organic activity. This skill covers detecting coordinated wallet clusters, wash trading, bundled transactions, and fake holder inflation — critical for evaluating whether a token's metrics reflect real demand or manufactured signals.
Why Sybil Detection Matters
Token markets on Solana are rife with manufactured signals:
- Inflated holder counts: 500 "holders" that are really 10 entities with 50 wallets each
- Fake volume: Wash trading between self-controlled wallets to simulate demand
- Artificial social proof: Many wallets holding small amounts to appear broadly distributed
- Rug preparation: Creator distributes supply across many wallets, then sells coordinated
- Bundled launches: PumpFun tokens where creator buys via Jito bundle in first slot
A token showing 1,000 holders with 80% funded from 3 wallets is fundamentally different from one with 1,000 independently-funded holders. Sybil detection separates real demand from theater.
Detection Categories
1. Funding Source Analysis
Trace each holder wallet back 1-2 hops to find who sent them SOL:
import httpx
def trace_funding_source(wallet: str, api_key: str, max_hops: int = 2) -> list[str]:
"""Trace SOL funding sources for a wallet via Helius parsed transactions."""
url = f"https://api.helius.xyz/v0/addresses/{wallet}/transactions"
resp = httpx.get(url, params={"api-key": api_key, "type": "TRANSFER", "limit": 50})
transfers = resp.json()
funders = []
for tx in transfers:
for transfer in tx.get("nativeTransfers", []):
if transfer["toUserAccount"] == wallet and transfer["amount"] > 0.001 * 1e9:
funders.append(transfer["fromUserAccount"])
return funders
Key signals:
- 3+ holder wallets funded from the same source = cluster
- Funding within 24h of token creation = high suspicion
- Funding amounts are identical (e.g., 0.05 SOL to each) = automated distribution
What ships with it
4 files 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.
- 12d ago First seen · 243 lines · 24 tokens per session scan A 549548699ec6
sybil-detection is a skill published in the GitHub repository agiprolabs/claude-trading-skills (356 stars, last pushed 9d ago), licensed MIT. It adds 24 tokens to every session and 2,640 once invoked, about $0.0001 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
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.
marginfi
MarginFi — Solana lending and borrowing.
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…