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.
git clone --depth 1 https://github.com/iamgoatedaf/lighter-mcpWrote 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/rules/iamgoatedaf/lighter-mcp/lighter-safety)<a href="https://agentmods.dev/rules/iamgoatedaf/lighter-mcp/lighter-safety"><img src="https://agentmods.dev/badge/rules/iamgoatedaf/lighter-mcp/lighter-safety/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/rules/iamgoatedaf/lighter-mcp/lighter-safety"><img src="https://agentmods.dev/badge/rules/iamgoatedaf/lighter-mcp/lighter-safety.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 | $0.00018 | $0.00472 |
| Opus 5 | $0.00009 | $0.00236 |
| Sonnet 5 | $0.00004 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
lighter-safety 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 8d 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.
What it actually says
Lighter trading — safety contract
When using the lighter MCP server, follow these rules.
Mode-aware behavior
Call lighter_safety_status (or read lighter_version) before any
non-trivial action and tell the user the active mode and remaining daily
notional. Modes:
readonly— only read tools available.paper— paper trading available; nothing real moves.live— live writes available; treat outputs as irreversible.funds— also enables transfers and withdrawals.
If you receive a category: "safety" error envelope, do not retry with
different arguments to bypass it. Surface the limit to the user verbatim and
ask whether to relax the config.
Two-step confirmation
lighter_live_* and lighter_funds_* tools use a preview/execute pattern:
- Call without
confirmation_idfirst. The response hasstage: "preview", aplanblock, and aconfirmation_id. - Show the entire plan to the user (symbol, side, amount, estimated notional, leverage, slippage, etc.). Ask explicit confirmation in plain language before continuing.
- Only on explicit user approval, repeat the call with the same
arguments plus
confirmation_idset to the issued token.
Never invent a confirmation id, never reuse one across different actions, and never paraphrase the plan before reading it back to the user.
High-risk actions
lighter_live_close_all, lighter_live_cancel_all, lighter_funds_withdraw,
and lighter_funds_transfer are always treated as high-risk regardless of
context. Surface every warning the preview emits.
Symbol handling
Use perp symbols like BTC, ETH, SOL and spot pairs like ETH/USDC.
Resolve ambiguous market references via lighter_list_markets rather than
guessing.
Audit
Every tool call is recorded to the audit log configured server-side. Do not attempt to suppress, edit, or pre-summarize calls that should be auditable.
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.
- 8d ago First seen · 57 lines · 18 tokens per session scan A d6100d77ec56
lighter-safety is a cursor rule published in the GitHub repository iamgoatedaf/lighter-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 472 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.
Other cursor rules, from other repositories
invompt-local-beta-invoice
Create or manage an Invompt invoice, quote, estimate, or pro forma from natural-language intent in any language.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.