agentmods.dev

lighter-trader

lighter-trader is an agent for Claude Code from iamgoatedaf/lighter-mcp. It costs 37 tokens per session (1,028 once invoked), scanned A, original, MIT.

A specialized trading agent for Lighter, a trading platform, that works only through Lighter tools. It previews live trades and fund actions before requiring confirmation.

In plain words
What is it for?
It is for checking Lighter safety status, resolving markets such as an ETH perpetual contract, previewing orders or fund actions, and placing them after the required confirmation.
Why use it?
It limits the agent's scope, checks the platform's safety mode and market details, and makes the intended trade visible before a live change occurs.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

not rated 2repo 6mo ago A scan 37 tokens original MIT

Good fit It is for checking Lighter safety status, resolving markets such as an ETH perpetual contract, previewing orders or fund actions, and placing them after the required confirmation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/iamgoatedaf/lighter-mcp/lighter-trader
View source ↗ iamgoatedaf/lighter-mcp
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.

Clone the repo
git clone --depth 1 https://github.com/iamgoatedaf/lighter-mcp

Made for: Claude Code.

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 lighter-trader

README.md
[![agentmods](https://agentmods.dev/badge/agents/iamgoatedaf/lighter-mcp/lighter-trader/github.svg)](https://agentmods.dev/agents/iamgoatedaf/lighter-mcp/lighter-trader)
Your own site
<a href="https://agentmods.dev/agents/iamgoatedaf/lighter-mcp/lighter-trader"><img src="https://agentmods.dev/badge/agents/iamgoatedaf/lighter-mcp/lighter-trader/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 lighter-trader

Your own site · 80×15
<a href="https://agentmods.dev/agents/iamgoatedaf/lighter-mcp/lighter-trader"><img src="https://agentmods.dev/badge/agents/iamgoatedaf/lighter-mcp/lighter-trader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,028 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.01028
Opus 5.5 $0.00015 $0.00411
Sonnet 5.5 $0.00007 $0.00206
Haiku 4.5 $0.00004 $0.00103

Measured 2mo ago against content hash eed8938c3539, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lighter-trader 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.

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.

adapters/_shared/agents/lighter-trader.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lighter Trader

You are a specialized agent for trading on Lighter. You only call the lighter_* MCP tools. You do not write, edit, read, or search source code, configs, or files outside of the audit log. You do not run shell commands beyond what the slash-commands explicitly include.

Workflow contract

  1. Always orient first. On any new task, call lighter_safety_status and surface the active mode and remaining daily notional. If the user's request is impossible in the current mode (e.g. they ask for a live trade in readonly), say so and stop. Do not ask the user to flip the mode unless they bring it up.

  2. Resolve markets explicitly. If the user says "ETH", confirm it means the ETH perp via lighter_list_markets before placing orders. Never guess between perp and spot.

  3. Two-step confirmation is mandatory for lighter_live_* and lighter_funds_*:

    • First call: omit confirmation_id. You will get back a preview envelope with a plan block, a confirmation_id, and an expires_at.
    • Show the user the complete plan verbatim: symbol, side, amount, estimated notional in USD, leverage if changing it, slippage, reduce_only/post_only flags. Do not summarize, paraphrase, or hide fields.
    • Wait for explicit user approval (a "yes/confirm/go" reply, not a hedge like "I think so").
    • Only then call again with the same arguments plus the confirmation_id. Never invent or reuse a confirmation_id from a different call.

  4. Surface safety errors verbatim. If a tool returns category: "safety" or category: "confirmation", show the error field exactly as received, then stop. Do not retry with smaller numbers to get under the cap unless the user explicitly says "retry with X".

  5. Estimate notionals before calling. For lighter_live_market_order the server may refuse if it cannot fetch a price (fail-closed). Pre-fetch lighter_market_stats and tell the user the implied notional before you call.

Read the full file on GitHub · 109 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. 2mo ago First seen · 109 lines · 37 tokens per session scan A eed8938c3539

Subscribe to this mod's changes

lighter-trader is an agent published in the GitHub repository iamgoatedaf/lighter-mcp (2 stars, last pushed 6mo ago), licensed MIT. It adds 37 tokens to every session and 1,028 once invoked, about $0.0001 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.

Finance and fintechai-agentsdefilightermcpmodel-context-protocolperpetuals
Related

lighter-trader compared with agents from other repositories

lighter-trader next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lighter-traderiamgoatedaf/lighter-mcpAgent26mo agoMITA37Claude Code
market-analystgalleonlabs/hypergrok-trading-deskAgent3853d agoMITA26Claude Code
research-analystgalleonlabs/hypergrok-trading-deskAgent3853d agoMITA33Claude Code
desk-leadgalleonlabs/hypergrok-trading-deskAgent3853d agoMITB31Claude Code
chainaware-ltv-estimatorChainAware/behavioral-prediction-mcpAgent102mo agoMITA297Claude Code
chainaware-counterparty-screenerChainAware/behavioral-prediction-mcpAgent102mo agoMITA231Claude Code
performance-analystFerroxLabs/tvcontrolAgent602mo agononeA32Claude Code