lighter-paper

lighter-paper is a command for Claude Code from iamgoatedaf/lighter-mcp. It costs 18 tokens per session (387 once invoked), scanned A, original, MIT.

A guarded command for switching the Lighter trading platform into paper-trading mode, where trades are simulated rather than live.

In plain words
What is it for?
Changing the active Lighter mode to paper, preserving the safety state and daily-use ledger, and guiding the user through confirmation and reload steps.
Why use it?
It separates testing from live trading and removes live trading tools until the configuration is changed again and reloaded.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions Codex.

Good fit Changing the active Lighter mode to paper, preserving the safety state and daily-use ledger, and guiding the user through confirmation and reload steps.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/iamgoatedaf/lighter-mcp/lighter-paper
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-paper

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/iamgoatedaf/lighter-mcp/lighter-paper"><img src="https://agentmods.dev/badge/commands/iamgoatedaf/lighter-mcp/lighter-paper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 387 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 $0.00018 $0.00387
Opus 5 $0.00009 $0.00193
Sonnet 5 $0.00004 $0.00077
Haiku 4.5 $0.00002 $0.00039

Measured 9d ago against content hash b2324dd5017c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

lighter-paper 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.

adapters/_shared/commands/lighter-paper.md · 41 lines

What it actually says

/lighter-paper

The lighter-mcp config lives at ~/.lighter/lighter-mcp/config.toml. Mode is the first-line mode = "<readonly|paper|live|funds>".

Steps:

  1. Tell the user you are about to switch the active config to paper. List what that changes:

    • paper trading tools become available (lighter_paper_*).
    • live trading tools are de-registered (no lighter_live_* calls possible until the user re-enables live later).
    • safety state is preserved on disk; daily notional ledger is unchanged.
  2. Wait for the user to confirm in plain language.

  3. Update the config file. Use a small shell snippet:

    python3 -c '
    import os, re, pathlib
    p = pathlib.Path(os.path.expanduser("~/.lighter/lighter-mcp/config.toml"))
    s = p.read_text()
    s = re.sub(r"^mode\s*=\s*\".*\"", "mode = \"paper\"", s, count=1, flags=re.MULTILINE)
    p.write_text(s)
    print("ok")
    '
    
  4. Tell the user to reload the lighter MCP server in their agent (Cursor: "Reload MCP servers"; Claude Desktop: restart the app; Codex: re-run the plugin install or /mcp reload). The new mode takes effect after reload.

  5. After reload, suggest running /lighter-status to confirm the active mode is now paper.

If the user wanted a different mode (live, funds, readonly), do not silently switch to paper — ask which mode they meant and abort.

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. 9d ago First seen · 41 lines · 18 tokens per session scan A b2324dd5017c

Subscribe to this mod's changes

lighter-paper is a command published in the GitHub repository iamgoatedaf/lighter-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 387 once invoked, about $0.0001 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.