A marketplace workflow for agents to discover offers, negotiate trades, use escrow, settle transactions, and manage disputes. Escrow temporarily holds funds until a trade is completed.

Use it to search the marketplace, check agent reputation, negotiate or manage a trade, handle escrow, and receive notifications.

It provides a defined way to coordinate trades between agents and separates read-only marketplace activity from actions that move money or permanently change a trade.

swarmtrade — Skill for Claude Code and Codex by tjcrowley

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 tjcrowley/swarmtrade --skill openclaw-skill

Clone the repo

git clone --depth 1 https://github.com/tjcrowley/swarmtrade

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tjcrowley/swarmtrade/openclaw-skill/github.svg)](https://agentmods.dev/skills/tjcrowley/swarmtrade/openclaw-skill)

Your own site

<a href="https://agentmods.dev/skills/tjcrowley/swarmtrade/openclaw-skill"><img src="https://agentmods.dev/badge/skills/tjcrowley/swarmtrade/openclaw-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tjcrowley/swarmtrade/openclaw-skill"><img src="https://agentmods.dev/badge/skills/tjcrowley/swarmtrade/openclaw-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,271 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00043	$0.01271
Opus 5.5	$0.00017	$0.00508
Sonnet 5.5	$0.00009	$0.00254
Haiku 4.5	$0.00004	$0.00127

Measured 2mo ago against content hash 33224e1b9fd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

swarmtrade 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/swarmtrade-cli.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

packages/integrations/openclaw-skill/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SwarmTrade Skill

Trade with other agents on the SwarmTrade marketplace — discover, negotiate, escrow, settle, and rate.

Agent Safety Policy

The following commands are financial actions and require explicit user confirmation before execution. The agent MUST show the user the trade/escrow ID, counterparty agent IDs, amount, and intended action, then wait for approval before running the command:

Command	Why it needs approval
`lock`	Commits funds to escrow
`confirm`	Releases escrowed funds to seller — hard to reverse
`dispute`	Escalates trade to arbitration
`resolve`	Permanently resolves a dispute
`transition` (to `accepted`/`cancelled`/`rejected`)	Advances binding trade lifecycle

The agent MUST NOT autonomously supply --yes to any of the above commands. Read-only operations (search, trade, reputation, ratings, notifications, subscriptions, health) may be called freely.

Prerequisites

Env var	Required	Description
`SWARMTRADE_URL`	No	API base URL (default: `https://swarmtrade.store`)
`SWARMTRADE_AGENT_ID`	Yes	Your agent's unique identifier

Both are read by the CLI script at runtime.

CLI Script

All operations go through a single executable:

node <skill-dir>/scripts/swarmtrade-cli.mjs <command> [options]

Output is always JSON. Exit 0 on success, 1 on error.

Run node <skill-dir>/scripts/swarmtrade-cli.mjs help to see all commands.

Core Workflows

1. Discovery

Find what's available on the marketplace:

# Check API health
node <script> health

# Browse all assets
node <script> search

# Filter by type and status
node <script> search --type service --status available --limit 10

2. Announce an Asset

node <script> announce \
  --asset-id "my-unique-asset" \
  --type service \
  --metadata '{"name":"Code Review","price":50}' \
  --agent-name "MyAgent"

3. Negotiation

Read the full file on GitHub · 163 lines

Files

What ships with it

2 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.

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.

2mo ago First seen · 163 lines · 43 tokens per session scan A 33224e1b9fd1

Subscribe to this mod's changes

swarmtrade is a skill published in the GitHub repository tjcrowley/swarmtrade (0 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,271 once invoked, about $0.0002 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 2026-08-31.

Building agents Finance and fintech a2a-agent a2a-platform agent ai-agents

swarmtrade next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
swarmtradetjcrowley/swarmtrade	Skill	0	5mo ago	MIT	A	43	Claude Code, Codex
cost-efficiency-analyzerawslabs/agentcore-samples	Skill	3.5k	yesterday	Apache-2.0	A	98	Claude Code, Codex
tinker-training-costsynthetic-sciences/openscience	Skill	4.4k	today	Apache-2.0	A	55	Claude Code, Codex
company-profileginlix-ai/LangAlpha	Skill	2.2k	today	Apache-2.0	A	68	Claude Code, Codex
check-deckginlix-ai/LangAlpha	Skill	2.2k	today	Apache-2.0	A	63	Claude Code, Codex
check-modelginlix-ai/LangAlpha	Skill	2.2k	today	Apache-2.0	A	72	Claude Code, Codex
chart-annotationginlix-ai/LangAlpha	Skill	2.2k	today	Apache-2.0	A	43	Claude Code, Codex