Runtimes & Install

Agent support and multichain scope

The hosted agent service and installable skill are maintained separately from this interface. The published skill covers all five networks and documents xTOPAZ entry and redemption, bridging and spoke voting. Its quote and swap-batch helpers accept all five chain IDs; the remaining helpers and command-line tools target BNB Chain. Check the service's current capabilities and deployed network before using a builder; never substitute BNB addresses or data for a planned spoke.

This interface supports xTOPAZ entry, redemption, bridging and spoke voting on the live networks. The hosted agent service and installable skill have their own release capabilities; web support does not activate agent builders. Check the published service manifest and chain-qualified addresses. Live networks · Multichain integration.

Carry chain, account, contract, token address, recipient and NFT or local stake ID in every quote and plan. Keep source submission, source confirmation and destination delivery distinct. A transaction hash is not proof that a bridge completed or a destination action succeeded.

Pick a loading pattern

Three patterns cover essentially every agent runtime that exists today:

Conventional install locations

If you want the skill on disk for an agent that reads from a well-known directory, these are the conventions per runtime. They are not requirements — any path works, as long as you point the agent at it.

One-line installer

The repo ships an installer that auto-detects an existing agent skills directory and installs there. Detection order:

1. ~/.claude/skills/ exists → ~/.claude/skills/topaz
2. ~/.config/opencode/skills/ exists → ~/.config/opencode/skills/topaz
3. ~/.hermes/skills/ exists → ~/.hermes/skills/defi/topaz
4. None of the above → fallback to ~/.local/share/topaz-skill (installer prints a notice asking you to wire the agent at that path)

The installer prints its chosen destination and the reason before cloning. Pass an explicit path to override detection.

# auto-detect destination
curl -fsSL https://raw.githubusercontent.com/topazdex/agent-skill/main/install.sh | bash

# explicit path
curl -fsSL https://raw.githubusercontent.com/topazdex/agent-skill/main/install.sh \
  | bash -s -- ~/some/other/path

Manual install via git

Equivalent to the installer if you prefer to clone manually.

git clone https://github.com/topazdex/agent-skill.git <dest>
cd <dest>/scripts
cp .env.example .env       # set BSC_RPC_URL; PRIVATE_KEY only needed for writes
yarn install --immutable
yarn validate && yarn smoke

Prompt templates

Generic prompts that work across runtimes. Adapt the wording to your agent's conventions if it prefers a specific style.

URL-reading agents

Read the official Topaz DEX agent skill at
https://www.topazdex.com/skill.md and follow it when working
with Topaz DEX swaps, pools, gauges, bribes, veNFTs,
rewards, quotes, routes, or integrations.

Git-capable coding agents

Clone https://github.com/topazdex/agent-skill and follow
SKILL.md. Use references, examples, and scripts from the
cloned repo when available.

Claude Code

Read https://www.topazdex.com/skill.md. If more detail is
needed, clone https://github.com/topazdex/agent-skill into
~/.claude/skills/topaz (or .claude/skills/topaz for
project-local) and follow SKILL.md as guidance for Topaz
DEX tasks.

Codex / Cursor / Continue / generic

Use https://www.topazdex.com/skill.md as the Topaz DEX
protocol guide. For full references and scripts, clone
https://github.com/topazdex/agent-skill.

Updating an installed skill

If you cloned the repo:

git -C <dest> pull --ff-only
# or the wrapper:
bash <dest>/update.sh

# check if an update is available without applying it
cd <dest> && bash tools/check_update.sh
# exit 0 = up to date, 10 = update available

Agents that loaded the skill from a URL can refetch /skill.md or compare their installed version against /skill.json.

Continue reading