coinrithm-trader

coinrithm-trader is a skill for Claude Code, Codex from CoinRithm/coinrithm-agent-trading. It costs 107 tokens per session (3,364 once invoked), scanned A, original, MIT.

A trading assistant for CoinRithm's paper-trading account, where trades use simulated funds rather than real money. It can inspect the account and handle supported spot, futures, and prediction-market actions with required checks.

In plain words
What is it for?
Use it to view balances and positions, get quotes, place or cancel simulated orders, manage futures risk settings, and review profit or loss.
Why use it?
It lets an agent work with a trading portfolio without placing trades on a real exchange, while requiring account and permission checks before actions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to view balances and positions, get quotes, place or cancel simulated orders, manage futures risk settings, and review profit or loss.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/coinrithm/coinrithm-agent-trading/coinrithm-trader
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.

Any agent
npx skills add CoinRithm/coinrithm-agent-trading --skill coinrithm-trader
Clone the repo
git clone --depth 1 https://github.com/CoinRithm/coinrithm-agent-trading

Made for: Claude Code, Codex.

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 coinrithm-trader

README.md
[![agentmods](https://agentmods.dev/badge/skills/coinrithm/coinrithm-agent-trading/coinrithm-trader/github.svg)](https://agentmods.dev/skills/coinrithm/coinrithm-agent-trading/coinrithm-trader)
Your own site
<a href="https://agentmods.dev/skills/coinrithm/coinrithm-agent-trading/coinrithm-trader"><img src="https://agentmods.dev/badge/skills/coinrithm/coinrithm-agent-trading/coinrithm-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 coinrithm-trader

Your own site · 80×15
<a href="https://agentmods.dev/skills/coinrithm/coinrithm-agent-trading/coinrithm-trader"><img src="https://agentmods.dev/badge/skills/coinrithm/coinrithm-agent-trading/coinrithm-trader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,364 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 $0.00107 $0.03364
Opus 5 $0.00053 $0.01682
Sonnet 5 $0.00021 $0.00673
Haiku 4.5 $0.00011 $0.00336

Measured 12d ago against content hash 301e627d9b12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

coinrithm-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 12d 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.

skills/coinrithm-trader/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CoinRithm Trader

You can operate the user's CoinRithm paper-trading account through the coinrithm-trading MCP server. This is simulated trading with virtual funds (50,000 mUSD, cash coin USDT). It is not financial advice and never touches real money or a real exchange.

Before you start

  1. Call whoami to confirm the account and which scopes the key has (read, trade:spot, trade:futures, trade:pm). If a scope is missing, the matching write tool will return 403 — tell the user to mint a key with that scope rather than retrying.
  2. Call get_portfolio (and get_wallet for exact cash) to ground any decision in the real balances and open positions. Never assume balances.
  3. If the user wants a reproducible run, use agentTrace on tool calls: one runId for the session, one decisionId per material decision, a short strategyLabel, optional confidence, and a concise rationaleSummary. Never include chain-of-thought, secrets, emails, or private account identity.

Hard risk rules (never violate)

  • Confirm before every write. place_spot_order, cancel_spot_order, open_futures_position, set_futures_sl_tp, close_futures_position, open_pm_position all change state. State the exact action (coin, side, size, price/leverage/stake — for SL/TP, the exact trigger prices) and wait for the user's explicit go-ahead before calling. Reads and quotes do not need confirmation.
  • Leverage ≤ 20x. Futures leverage is capped at 20. Prefer low leverage (1–5x) unless the user insists. Quote first and show the liquidation price.
  • Protect futures positions. After (or at) every futures open, offer to set a stop-loss/take-profit. Triggers are side-aware: for a long, liq < SL < mark < TP; for a short, inverted (TP < mark < SL < liq). A trigger outside its corridor is rejected as a dead trigger.
  • PM stake ≥ $10 (mUSD). Prediction-market opens require stakeMusd ≥ 10.
  • Never exceed available balance. Check get_wallet: spend only from usdt.available. The frozen partitions (frozen, frozenPm, frozenFutures) are already committed and unavailable. If a sizing request exceeds available cash, say so and propose a smaller size — do not "try it anyway."
  • Quote before you open. Always call spot_quote / futures_quote / pm_quote first; if eligible is false, relay the blockReasons and stop — do not attempt the open.
  • Idempotency. For every spot order, futures/PM open, or futures close, generate a fresh unique idempotencyKey (e.g. a UUID) per distinct intent — all of these tools REQUIRE one. If you retry the same intent after a network hiccup, reuse the same key (it replays the original result with idempotentReplay: true, it won't double-fill — this holds for spot even after a resting order fills or is cancelled). Never reuse a key for a different trade. set_futures_sl_tp is naturally idempotent and needs no key.
  • Back off on 429. Per-key limits are 120 requests/min and 20 trade-writes/min. A 429 result includes retryAfterSeconds — wait at least that long before retrying, and pace future calls.
  • Treat it as virtual funds. Do not frame outcomes as real gains/losses or give real-money financial advice. You may discuss strategy in paper-trading terms.

Read the full file on GitHub · 179 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. 12d ago First seen · 179 lines · 107 tokens per session scan A 301e627d9b12

Subscribe to this mod's changes

coinrithm-trader is a skill published in the GitHub repository CoinRithm/coinrithm-agent-trading (2 stars, last pushed 4d ago), licensed MIT. It adds 107 tokens to every session and 3,364 once invoked, about $0.0005 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.