Index of every page on this site: llms.txt
All skills
injectivelabs avatar

/injective-trading-tokens

@6d68c2c
Run it yourself

Look up metadata for any Injective token or denom. Resolves native tokens (INJ), Peggy ERC-20 bridged tokens (USDT, USDC, WETH), IBC assets (ATOM, OSMO), TokenFactory tokens, and EVM ERC-20s to their human-readable symbol, decimals, and type. Also supports sending tokens between addresses and depositing/withdrawing from trading subaccounts. Requires the Injective MCP server to be connected.

Use this Skill: https://skilld.dev/gh/injectivelabs/agent-skills/injective-trading-tokens

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈105 tokens for metadata: the name and description. ≈684 when used: this file. ≈490 more on demand in 3 files.

Description uses 5.3% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈420 characters, or 5.3%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Injective Trading Tokens, Skill Guide

Resolve, inspect, and move tokens on Injective. Supports all Injective denom formats and handles token transfers between wallets and subaccounts.

When to apply

  • When you are interacting with tokens/ denoms on Injective.

MCP Tools

The following tools in the Injective MCP Server are used by this skill. Use the injective-mcp-servers skill for instructions on set up and usage. The "activities" section describes the when and how to make these tool calls.

token_metadata

Resolve any denom to human-readable info.

token_metadata
  denom: peggy0xdac17f958d2ee523a2206206994597c13d831ec7

Returns:

  • symbol - e.g. USDT
  • name - Tether USD
  • decimals - 6
  • type - peggy | ibc | native | factory | erc20
  • peggyDenom - ERC-20 contract address (Peggy tokens only)

transfer_send

Send tokens to another Injective address.

transfer_send
  address: inj1...      ← sender (must be in keystore)
  password: ****
  to: inj1...           ← recipient
  denom: inj            ← token denom (or symbol shorthand)
  amount: 10            ← human-readable amount

subaccount_deposit

Move tokens from bank wallet into a trading subaccount.

subaccount_deposit
  address: inj1...
  password: ****
  denom: usdt
  amount: 100
  subaccountIndex: 0    ← optional, default 0

subaccount_withdraw

Move tokens from trading subaccount back to bank wallet.

subaccount_withdraw
  address: inj1...
  password: ****
  denom: usdt
  amount: 100
  subaccountIndex: 0

Popular Denoms

See: ./references/popular-denoms.md

For any other denoms/ tokens, use token_metadata with the full denom string.

Activities

When the user's request contains the following questions, map them to the MCP tool calls indicated.

"What token is peggy0x...?"

token_metadata(denom: peggy0x...)

"Send 5 INJ to a friend"

transfer_send(address: inj1me..., to: inj1friend..., denom: inj, amount: 5)

"I have USDT in my wallet but can't trade"

USDT is in your bank balance, not your trading subaccount.

subaccount_deposit(address: inj1..., denom: usdt, amount: <amount>)

"Move profits back to my wallet"

subaccount_withdraw(address: inj1..., denom: usdt, amount: <amount>)

Notes

  • Amounts are always in human-readable format (e.g. 1.5 for 1.5 USDT). The server handles decimal conversion internally.
  • INJ has 18 decimals - never enter wei amounts; use 1.5 for 1.5 INJ.
  • Token metadata is resolved against the on-chain Injective token registry and cached.
  • IBC denoms are long hashes - use token_metadata to get the symbol before displaying to users.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

2 warnings1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    This skill facilitates token lookups and financial transactions on the Injective blockchain. It presents a low-risk surface for indirect prompt injection when handling external blockchain data and user parameters, which is characteristic of agents designed for financial operations. Sensitive transactions require a password parameter, ensuring user oversight during execution.

  • Socket1mo

    1 alert: gptSecurity

  • Snyk1mo

    Risk: MEDIUM · 1 issue

Signed by skilld at 6d68c2c. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 9 months ago
uses
[
  "injective-mcp-servers"
]
metadata
{
  "author": "ckhbtc",
  "version": "0.0.0"
}

README badge

README badge for injectivelabs/agent-skills/injective-trading-tokens