trade

trade is a skill for Claude Code from ChainGPT-org/chaingpt-claude-skill. It costs 171 tokens per session (1,527 once invoked), scanned A, original, MIT.

A skill for carrying out token swaps on supported blockchain networks through decentralized exchanges. It checks the token and trade risk, gets a price quote, builds an unsigned transaction for the user’s wallet to sign, and confirms the result after broadcasting.

In plain words
What is it for?
Use it to research a token, check its risks, quote and prepare EVM or Solana swaps, handle token approvals where needed, and confirm completed transactions.
Why use it?
It provides checks for token risk, expected output, price impact, routing, and required approvals before a mainnet trade. The skill does not hold the user’s keys.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the chaingpt plugin — 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server shipped together

Good fit Use it to research a token, check its risks, quote and prepare EVM or Solana swaps, handle token approvals where needed, and confirm completed transactions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chaingpt-org/chaingpt-claude-skill/trade
Install

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.

Any agent
npx skills add ChainGPT-org/chaingpt-claude-skill --skill trade
Clone the repo
git clone --depth 1 https://github.com/ChainGPT-org/chaingpt-claude-skill

Made for: Claude Code.

Or install chaingpt, the plugin that ships this one along with the rest of its 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server.

Wrote 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.

agentmods badge for trade

README.md
[![agentmods](https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/trade/github.svg)](https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/trade)
Your own site
<a href="https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/trade"><img src="https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/trade/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.

agentmods 80×15 button for trade

Your own site · 80×15
<a href="https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/trade"><img src="https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/trade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 171 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,527 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 Excessive Agency · line 31
    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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00171 $0.01527
Opus 5.5 $0.00068 $0.00611
Sonnet 5.5 $0.00034 $0.00305
Haiku 4.5 $0.00017 $0.00153

Measured 1mo ago against content hash 5638d9c10a3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

trade 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.

skills/trade/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChainGPT Trade Skill

You execute real mainnet DEX trades on behalf of the user. The plugin never holds keys. Your job is to:

  1. Run the pre-flight checks the user expects from a serious trading interface.
  2. Build the unsigned transaction.
  3. Hand it to the user's wallet to sign.

The mandatory pipeline (EVM)

chaingpt_research_token        — confirm the user is buying the token they think
chaingpt_risk_token            — GoPlus + Honeypot check on the OUT token (MANDATORY)
chaingpt_dex_quote             — expected output, price impact, route
       │  (surface to user with USD-denominated cost and slippage)
       ▼
chaingpt_dex_approve_tx        — if inToken is ERC-20 and current allowance is insufficient (requires acknowledgeMainnet: true — approvals delegate spend authority)
       │  (user signs + broadcasts the approval)
       ▼
chaingpt_dex_build_swap_tx     — REFUSES mainnet unless acknowledgeMainnet=true
       │  (user signs + broadcasts the swap)
       ▼
chaingpt_onchain_tx hash=…     — confirm execution, surface received-amount

Pipeline for Solana is identical but two-step (no approval needed):

chaingpt_risk_token (on Solana outToken)
chaingpt_dex_jupiter_quote
chaingpt_dex_jupiter_build_swap_tx (requires acknowledgeMainnet)

Hard rules for mainnet

  1. NEVER call chaingpt_dex_build_swap_tx with acknowledgeMainnet: true unless the user has explicitly confirmed they want to swap on mainnet with the specific amounts and tokens you echoed back.
  2. ALWAYS surface the price impact and USD cost from chaingpt_dex_quote before asking for confirmation.
  3. If chaingpt_risk_token raises a honeypot or cannot-sell-all flag, REFUSE the swap. Surface the flag and require an explicit user override before re-running.
  4. For >$1,000 trades, also call chaingpt_audit_contract on the outToken's contract if it's a freshly-deployed or unverified contract. The audit gate is the ChainGPT-native moat.
  5. For ERC-20 swaps, always insert the approval step. Skipping approval is the single most common cause of failed swaps.

Read the full file on GitHub · 97 lines

Changes

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.

  1. 1mo ago First seen · 97 lines · 171 tokens per session scan A 5638d9c10a3c

Subscribe to this mod's changes

trade is a skill published in the GitHub repository ChainGPT-org/chaingpt-claude-skill (7 stars, last pushed 1mo ago), licensed MIT. It adds 171 tokens to every session and 1,527 once invoked, about $0.0007 per session on Opus 5.5. 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.