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 tjcrowley/swarmtrade --skill openclaw-skillgit clone --depth 1 https://github.com/tjcrowley/swarmtradeWrote 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/tjcrowley/swarmtrade/openclaw-skill)<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.
<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>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 | $0.00022 | $0.00635 |
| Sonnet 5 | $0.00009 | $0.00254 |
| Haiku 4.5 | $0.00004 | $0.00127 |
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 9d 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.
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
Register something you're offering:
node <script> announce \
--asset-id "my-unique-asset" \
--type service \
--metadata '{"name":"Code Review","price":50}' \
--agent-name "MyAgent"
3. Negotiation
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.
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.
- 9d ago First seen · 163 lines · 43 tokens per session scan A 33224e1b9fd1
swarmtrade is a skill published in the GitHub repository tjcrowley/swarmtrade (0 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,271 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
onboarding
First-time user onboarding to set up investment profile, watchlists, portfolio, and preferences.
chart-annotation
Draw price lines, trendlines, zones, and event markers directly on a stock's price chart — reach for it whenever you'd otherwise describe a level, pattern, or event in prose. Renders live on MarketView and as a clickable preview card in any other chat.
check-deck
Investment deck QC: number consistency, data-narrative alignment, IB language, formatting audit.
check-model
Financial model audit: structural checks, formula validation, integrity testing.