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 iamgoatedaf/lighter-mcp --skill skillgit 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/skills/iamgoatedaf/lighter-mcp/skill)<a href="https://agentmods.dev/skills/iamgoatedaf/lighter-mcp/skill"><img src="https://agentmods.dev/badge/skills/iamgoatedaf/lighter-mcp/skill.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00518 |
| Opus 5 | $0.00015 | $0.00259 |
| Sonnet 5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
lighter 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 7d 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 skill
You have access to the lighter MCP server. Tools are namespaced
lighter_* and grouped by risk:
| Family | Effect |
|---|---|
lighter_market_* |
Public market reads. |
lighter_account_* |
Authenticated reads using local credentials. |
lighter_paper_* |
Local simulation; no real funds move. |
lighter_live_* |
Real exchange writes; gated and audited. |
lighter_funds_* |
Transfers and withdrawals; strictest gates. |
Always:
- Call
lighter_safety_statusbefore a non-trivial action and report the active mode plus any caps (allowed symbols, daily notional, leverage). - For any
lighter_live_*orlighter_funds_*tool: call once withoutconfirmation_idto get apreviewandconfirmation_id. Read the plan back to the user verbatim and ask "yes to execute". Only on explicit confirmation, repeat the call with the same args plus the id. - If a tool returns
category: "safety"orcategory: "confirmation", do not bypass it. Surface the message to the user and ask how to proceed. - Use
lighter_list_marketsto resolve ambiguous symbols. Do not guess market_index or symbol naming.
Never:
- Invent or share a
confirmation_id. Tokens are bound to args. - Re-issue a high-risk call after a partial failure without re-previewing.
- Paraphrase the preview's
warningfields. Read them as-is.
Workflow templates:
- Place a paper order:
lighter_paper_init(once), thenlighter_paper_market_orderorlighter_paper_ioc_order. - Place a live order: ensure the user is on
mode = live, runlighter_live_market_order(preview → confirm → execute). - Cancel everything:
lighter_live_cancel_all(preview → confirm). - Flatten:
lighter_live_close_all(kit-side preview is included in the envelope plan). - Withdraw:
lighter_funds_withdraw(preview → confirm).
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.
- 7d ago First seen · 48 lines · 30 tokens per session scan A 613eda4dcb4a
lighter is a skill published in the GitHub repository iamgoatedaf/lighter-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 30 tokens to every session and 518 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
hive-market-research
Use this skill for any live crypto market question — prices, 24h moves, liquidity, exchange/venue data, OHLC candles, order books, tickers, funding rates, derivatives, trading context — even casual asks like "what's BTC at" or "is ETH pumping". Use it whenever the answer needs current market numbers instead of memory.…
hive-query
Default entry point for any live crypto question when Hive MCP is connected — prices, wallets, tokens, DeFi, NFTs, Solana, security, markets, DEX, networks, prediction markets. Use it whenever the answer depends on live or on-chain data instead of answering from memory, even if the user never mentions Hive. Routes…
hive-token-diligence
Use this skill whenever the user asks whether a specific token is real, legit, liquid, well-held, enriched, investable, or worth researching — "is this token a scam", "run diligence on 0x…", "who holds this", "does it have real liquidity" — even if they never say "diligence". Investigates metadata, market context…
hive-wallet-investigation
Use this skill whenever the user wants to look inside a wallet or address — portfolio, holdings, balances, transfers, PnL, NFT exposure, DeFi positions, whale moves, "what does this address hold", "trace this wallet's activity" — even if they just paste an address. Requires wallet address and chain before executing…
hive-defi-research
Use this skill when the user asks about DeFi protocol metrics — TVL, fees, revenue, yields, APY, stablecoin supply, bridge volume, or chain-level DeFi totals — or wants protocols compared ("Aave vs Compound", "top protocols by TVL", "best stablecoin yields"). Use it whenever the answer needs current protocol-level…
skills
AI agent skill for Solana prediction markets. 76 MCP tools. Safe-by-default. Agent builds, user signs. Zero private keys.