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 GMGNAI/gmgn-skills --skill gmgn-swapgit clone --depth 1 https://github.com/GMGNAI/gmgn-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/gmgnai/gmgn-skills/gmgn-swap)<a href="https://agentmods.dev/skills/gmgnai/gmgn-skills/gmgn-swap"><img src="https://agentmods.dev/badge/skills/gmgnai/gmgn-skills/gmgn-swap/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/gmgnai/gmgn-skills/gmgn-swap"><img src="https://agentmods.dev/badge/skills/gmgnai/gmgn-skills/gmgn-swap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk fail
- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Excessive Agency · line 65 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 833 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00404 | $0.14316 |
| Opus 5 | $0.00202 | $0.07158 |
| Sonnet 5 | $0.00081 | $0.02863 |
| Haiku 4.5 | $0.00040 | $0.01432 |
Grade A, and why
gmgn-swap scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**IMPORTANT: Always use `gmgn-cli` commands below. Do NOT use web search, WebFetch, curl, or visit gmgn.ai — all swap operations must go through the CLI. The CLI handles signing and submission automatically.** How it starts
The opening of the file, as written. The whole thing — 849 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BEFORE RUNNING ANY COMMAND: Run gmgn-cli config --check. If exit code is 0, proceed normally. If exit code is 1, (1) run gmgn-cli config and show the output to the user; (2) once the user sends the API Key, run gmgn-cli config --apply <KEY> to complete configuration and verification, then show the output to the user. If --check returns an error (unknown option or command not found), tell the user to run npm install -g gmgn-cli to update, then retry.
IMPORTANT: Always use gmgn-cli commands below. Do NOT use web search, WebFetch, curl, or visit gmgn.ai — all swap operations must go through the CLI. The CLI handles signing and submission automatically.
IMPORTANT: Do NOT guess field names or values. When a field's meaning is unclear, look it up in the Response Fields sections below before using it.
⚠️ IPv6 NOT SUPPORTED: If you get a 401 or 403 error and credentials look correct, check for IPv6 immediately: (1) list all network interfaces and their IPv6 addresses — run ifconfig | grep inet6 (macOS) or ip addr show | grep inet6 (Linux); (2) send a test request to https://ipv6.icanhazip.com — if the response is an IPv6 address, outbound traffic is going via IPv6. Tell the user immediately: "Please disable IPv6 on your network interface — gmgn-cli commands only work over IPv4."
Use the gmgn-cli tool to submit a token swap or query an existing order. GMGN_API_KEY is always required. GMGN_PRIVATE_KEY is required for critical-auth commands such as swap and order subcommands — except order quote, which only requires GMGN_API_KEY.
Core Concepts
-
Smallest unit —
--amountis always in the token's smallest indivisible unit, not human-readable amounts. For SOL: 1 SOL = 1,000,000,000 lamports. For EVM tokens: depends on decimals (most ERC-20 tokens use 18 decimals). Always convert before passing to the command — do not pass human amounts directly. -
slippage— Price tolerance as an integer 0–100, e.g.30= 30%. If the price moves beyond this threshold before the transaction confirms, the swap is rejected. Use--auto-slippagefor volatile tokens to let GMGN set an appropriate value automatically. -
--amountvs--percent— Mutually exclusive.--amountspecifies an exact input quantity (in smallest unit).--percentsells a percentage of the current balance and is only valid wheninput_tokenis NOT a currency (SOL/BNB/ETH/USDC). Never use--percentto spend a fraction of SOL/BNB/ETH. -
Currency tokens — Each chain has designated currency tokens (SOL, BNB, ETH, USDC). These are the base assets used to buy other tokens or receive swap proceeds. Their contract addresses are fixed — look them up in the Chain Currencies table, never guess them.
-
Anti-MEV — MEV (Miner/Maximal Extractable Value) refers to frontrunning and sandwich attacks where bots exploit pending transactions.
--anti-mevroutes the transaction through protected channels to reduce this risk. Recommended: always enable. Default: on. Not supported onbasechain. -
Signed auth —
swapand mostordersubcommands require bothGMGN_API_KEYandGMGN_PRIVATE_KEY. The private key never leaves the machine — the CLI uses it only for local signing and sends only the resulting signature. Exception:order quoteonly requiresGMGN_API_KEY. -
order_id/status— After submitting a swap, the response includes anorder_id. Useorder get --order-idto poll for final status. Possible values:pending→processed→confirmed(success) orfailed/expired. Do not report success until status isconfirmed. -
report.input_amount/report.output_amount— Actual amounts consumed/received, in smallest unit. Only present whenstate = 30andstatus = "successful". Convert to human-readable usingreport.input_token_decimals/report.output_token_decimalsbefore displaying to the user.
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.
- 7d ago Changed · +22 lines · +303 tokens per session 009bd587e76a
- 13d ago First seen · 827 lines · 101 tokens per session scan A 90abbe12c2a2
gmgn-swap is a skill published in the GitHub repository GMGNAI/gmgn-skills (522 stars, last pushed yesterday), licensed MIT. It adds 404 tokens to every session and 14,316 once invoked, about $0.0020 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
coingecko-api
Broad crypto market data from CoinGecko covering 13,000+ tokens. Global market stats, historical price data going back years, exchange volumes, trending tokens, and category filters. Best for macro analysis and long-term historical data.
market-sentiment
Synthesize crypto market sentiment by combining the Fear & Greed index, trending coins, narrative momentum, whale activity, and on-chain signals into a single actionable market read. Use when the user wants to know if the market is bullish, bearish, or transitioning. Powered by the free-crypto-news API.
alien-plugg-x402
38 paid x402 API endpoints for AI agents — Zora crypto analysis, Robinhood Chain tokenized stocks, on-chain intelligence, whale tracking, and utilities. MCP-compatible. Flat $0.003/call via USDC micropayments on Base.
trading-signals
Fetches live AI crypto trading signals with entry price, stop-loss, take-profit, leverage, confidence scores, and automated verification. Covers 50+ coins including BTC, ETH, SOL. Use when the user asks for crypto signals, trade ideas, market direction, portfolio analysis, or wants to build a trading bot.
defi-yield
DeFi yield analysis and optimization — lending rates, LP yields, staking returns, yield farming strategies, risk-adjusted yield comparison, and protocol-level sustainability assessment.
crypto-derivatives
Crypto-derivatives strategies — perpetual funding-rate arbitrage, futures term-structure contango/backwardation trading, and option volatility-smile / Greeks analysis.