
trader-risk
Risk Manager. Checks every trade against your limits and stops anything over them, before it can reach the broker. For a day trade: a stop is required, the loss at the stop must fit your max loss per trade (measured from the higher of the plan's entry and a fresh price), reward:risk must meet your minimum, the day's total risk must fit your daily loss limit, no more than your trades per day, and no new entries outside your entry window or when the market is closed. It also keeps the basics: blocked tickers, order size, position cap, cash buffer, margin, short sales, options and crypto, malformed or bad bracket orders, duplicates and a daily order limit. Getting out is never blocked by a day limit. Prints PASS or BLOCK with the reason and records the verdicts so trader-broker only shows an order that passed. Use when the user says "check my order", "is this safe", "risk check", "does this break my rules", "can I take this trade", "how much have I risked today", or before /trader-broker,
- Installs
- 91
- Last 24h
- +16
- Trending rank
- #6805
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/jakeschincariol/day-trader-skill --skill trader-risk- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads trader-risk automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
trader-risk
The Risk Manager is the gate between a proposal and the broker. Every order written by trader-budget or trader-broker's flatten passes through it. A BLOCK is final for that order: it does not go to the user for a yes, and it does not go to the broker. Most people who day trade lose money. These limits keep each loss and each day's losses small. They do not make a trade win.
${CLAUDE_SKILL_DIR} below is this skill's folder (where this SKILL.md lives).
python3 "${CLAUDE_SKILL_DIR}/check.py" # trader/ files; writes trader/state/risk.json
python3 "${CLAUDE_SKILL_DIR}/check.py" --json
python3 "${CLAUDE_SKILL_DIR}/check.py" --no-write # look without recording
python3 "${CLAUDE_SKILL_DIR}/check.py" --now "2026-10-19 10:15" # pin the clock (New York time)
What it reads and writes
| file | what |
|---|---|
trader/orders.json | the proposed orders (trader-budget, or trader-broker's flatten) |
trader/config.json | the limits (trader-budget ships config.example.json) |
trader/portfolio.json | cash and holdings; if missing, a fresh account funded with the budget |
trader/prices.json | a fresh price raises the entry it measures risk from; also values holdings |
trader/state/broker.json | what was placed today: duplicates, trades per day, daily loss, day trades |
trader/state/risk.json | the verdicts it writes, with a fingerprint of each exact order |
Entries and exits
An entry opens or adds to a position: a buy, or a sell that would go short. An exit only reduces what you already hold. Getting out must always be possible, so an exit is checked for format, asset and short sales only. Every other rule (day limits, entry window, loss, reward:risk, blocked list, size, duplicates) turns into a warning for an exit, never a BLOCK.
The checks
Orders are checked in file order, as if each passed order had filled, so a batch that is fine order by order but breaks a limit together is caught.
| check | blocks when |
|---|---|
| format | no symbol, side not buy or sell, both or neither of qty and notional, a notional order that is not market + day (Alpaca's rule), a limit order with no limit price; a bracket that is not whole shares, not day or gtc, or misses its stop-loss or take-profit |
| asset | an option symbol while allow_options is false; crypto or anything that is not a US stock or ETF ticker |
| short | a sell of more than you hold (allow_short false) |
| blocked | (entries) the ticker is on the blocked list |
| size | (entries) under min_order_usd or over max_order_usd |
| position | (entries) the stock would be over max_position_pct of the account |
| cash | (entries) the buy would leave less than the cash buffer, or need margin |
| stop | (entries) no stop while require_stop is true (a bracket stop_loss_stop_price, or the order's plan stop); a stop on the wrong side of the entry |
| loss | (entries) qty x (entry minus stop) over max_loss_per_trade_usd |
| reward:risk | (entries) (target minus entry) / (entry minus stop) under min_reward_risk |
| daily loss | (entries) the max losses at the stops of today's entries, plus this one, over max_daily_loss_usd |
| trades | (entries) max_trades_per_day entries already placed today |
| window | (entries) before no_entries_before or after no_entries_after, or the market is closed |
| pdt | (entries, only with pdt_guard true) 3 day trades already in the last 5 business days |
| duplicate | (entries) the same symbol and side twice in one batch, or already placed today |
| daily limit | (entries) max_orders_per_day orders already placed today |
How the numbers work:
- The entry it measures from: the limit price for a limit order. For a
market order, the HIGHER of the plan's entry and a fresh price from
trader/prices.json(under 15 minutes old). A plan written at 10:15 cannot understate the risk at 10:55 after the price ran up. An older price is not used, and it says so. - Daily loss counts the full max loss of every entry placed today, win or lose, as trader-broker logged it. Three full-size trades use up a $150 day.
- The window is New York time, worked out in the tool (daylight saving
included), never from the computer's clock zone. Weekends and NYSE holidays
are closed. On a 1:00 p.m. early close the window ends 3 hours earlier too.
Set both
no_entries_*to null to switch the window off. - pdt_guard (off by default) counts a day trade as a symbol bought and
sold on the same day in the log, plus any entry placed today (it is meant
to be flat by the close). FINRA removed the $25,000 pattern-day-trader
minimum (Regulatory Notice 26-10, effective June 4, 2026; firms may phase
in until October 20, 2027), so some brokers still apply the old rule: turn
pdt_guardon if yours does.
Warnings do not block, but say them to the user: a LIVE account, a number sent as a number instead of a string, a stop that lives only in the plan and not at the broker, a price too old to use, an early close today.
Steps
- If the price may have moved since the plan, refresh it first
(trader-alerts:
alerts.py quote TSLA --write). - Run
check.py. Exit code 0 means every order passed, 1 means at least one was blocked. - Tell the user the result in plain words, order by order: the max loss at the stop, reward:risk, and how much of today's limits it uses. For a BLOCK, give the reason and the fix (fewer shares, a closer stop from trader-exit, wait for the window, or skip the trade). Never change a limit yourself.
- If the order changes in any way, run the check again. trader-broker matches each order to its verdict by fingerprint, so an edited order is not ready until it passes again, and a verdict from yesterday does not count today.
Example: the reel
The TSLA bracket from trader-budget at 10:15 AM on Monday 2026-10-19, on a fresh $5,000 paper account with the example config:
PASS #1 buy TSLA 8 shares, entry
entry 364.18 (the plan's entry), stop 358.32, target 370.04: risk 5.86 a share
max loss $46.88 (limit $50), reward:risk 1.00 (min 1)
today before this: 0 of 3 trades, $0 of $150 daily loss
1 passed, 0 blocked at 2026-10-19 10:15 New York. Cash after the passed orders: $2,086.56 (paper account).
One more share and it is blocked:
BLOCK #1 buy TSLA 9 shares, entry
entry 364.18 (the plan's entry), stop 358.32, target 370.04: risk 5.86 a share
max loss $52.74 (limit $50), reward:risk 1.00 (min 1)
today before this: 0 of 3 trades, $0 of $150 daily loss
- loss: 9 shares x 5.86 risk a share = $52.74 at the stop, over your $50 max loss per trade
The same 8 shares checked at 10:55 with the real 10:52 quote (366.48) in
trader/prices.json are blocked twice: 8 x 8.16 = $65.28 at the stop, and
reward:risk 0.44. At 9:40 they are blocked by the window (no new entries
before 9:45). The 3:55 PM sell that closes the position passes, even though
it is after the 3:30 entry cutoff: it is an exit.
Rules
- A PASS only means the order is allowed to be shown to the user. It is not a yes.
- Every number comes from the config, the order, the portfolio, the prices or the broker log.
- Free Yahoo prices are unofficial and can lag; the broker's price is the one that fills, and a stop can fill worse than its price in a fast market.
What it never does
It never places an order, never edits an order to make it pass, never loosens a limit, never blocks a sell that only gets the user out, and never treats a PASS as the user's yes.
Safety
- Education and tooling, not financial advice. A PASS is a rules check, not a recommendation.
- Paper trading by default (
"paper": true). Going live is the user's own decision, in their own config. - Nothing in this pack places an order except trader-broker, and only when all three hold: trader-risk passed that exact order today, the user typed an explicit yes for that one order in the chat, and the user clicked Allow once on Claude's own card because the order tool is set to "Needs approval" (Customize > Connectors > tool permissions). Never set an order tool to "Always allow".
- No options, margin, short selling or leverage unless the config allows it and the user confirms.
- Broker keys live in environment variables or the Claude Desktop config, never in the chat.
FAQ
What does the trader-risk skill do?
Risk Manager. Checks every trade against your limits and stops anything over them, before it can reach the broker. For a day trade: a stop is required, the loss at the stop must fit your max loss per trade (measured from the higher of the plan's entry and a fresh price), reward:risk must meet your minimum, the day's total risk must fit your daily loss limit, no more than your trades per day, and no new entries outside your entry window or when the market is closed. It also keeps the basics: blocked tickers, order size, position cap, cash buffer, margin, short sales, options and crypto, malformed or bad bracket orders, duplicates and a daily order limit. Getting out is never blocked by a day limit. Prints PASS or BLOCK with the reason and records the verdicts so trader-broker only shows an order that passed. Use when the user says "check my order", "is this safe", "risk check", "does this break my rules", "can I take this trade", "how much have I risked today", or before /trader-broker,
How do I install trader-risk?
Run npx skills add https://github.com/jakeschincariol/day-trader-skill --skill trader-risk in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/trader-risk/ (personal) or .claude/skills/trader-risk/ (project).
Which AI agents can use trader-risk?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is trader-risk safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains trader-risk?
It is published by jakeschincariol in jakeschincariol/day-trader-skill. It has 91 recorded installs.
More from jakeschincariol/day-trader-skill
trader-timemachine
jakeschincariol/day-trader-skill
Open the skill to read its SKILL.md instructions.
trader-scanner
jakeschincariol/day-trader-skill
Chart Scanner. Scans thousands of charts for setups: opening-range breakouts, flags, oversold bounces. Builds the list of US-listed common stocks, ordinary shares and ADRs from Nasdaq Trader's symbol directories, runs a pre-market scan of daily closes (20-day closing-high breakout, bull flag, reclaimed the 20-day average, oversold, oversold bounce) and an intraday opening-range breakout scan on 5-minute bars, then writes trader/watchlist.json for trader-news and trader-entry. Free Yahoo data, bar by bar. Use when the user says "scan the market", "find me setups", "what is breaking out", "opening range breakouts", "scan for bull flags", "oversold stocks", "pre-market scan", "build my watchlist", "what should I look at today", or at the start of a trading day before /trader-news.
trader-exit
jakeschincariol/day-trader-skill
Exit Planner. Sets your stop and your target before you enter, so you know when to get out. Reads the entry from trader-entry (or a price you give), puts the stop at the opening-range midpoint by default (or the range low, your price, a percent, or a multiple of the ATR), rounds it down to the cent, and sets the target at 2R (or 1R, or your price). Refuses a stop at or above the entry, a target at or below it, or a stop too tight to survive the spread, and says why. Writes trader/plan.json for the Time Machine, the Budget Manager and Price Alerts. Long side only. Use when the user says "where's my stop", "set my stop and target", "plan the exit", "when do I get out", "stop loss", "what's my R", "risk reward", or right after /trader-entry triggers, before /trader-timemachine.
trader-analyst
jakeschincariol/day-trader-skill
The Earnings Analyst. Reads a company's reported numbers straight from SEC EDGAR (XBRL company facts from its 10-Qs and 10-Ks, plus the latest earnings 8-K and its press release) and sums up what changed: revenue, gross, operating and net margins, net income and diluted EPS, quarter by quarter, each against the same quarter a year earlier, with the trailing twelve months. Reads an earnings call transcript when you paste one. Use when the user says "how did Tesla's earnings look", "analyze the earnings", "what changed this quarter", "is revenue growing", "check the 10-Q", "compare margins", "sum up the call", "does it report this week", or before trading a stock around its earnings.
trader-entry
jakeschincariol/day-trader-skill
Open the skill to read its SKILL.md instructions.
trader-news
jakeschincariol/day-trader-skill
Open the skill to read its SKILL.md instructions.
Popular business & finance skills
sales-enablement
coreyhaines31/marketingskills
When the user wants to create sales collateral, pitch decks, one-pagers, objection handling docs, or demo scripts. Also use when the user mentions 'sales deck,' 'pitch deck,' 'one-pager,' 'leave-behind,' 'objection handling,' 'deal-specific ROI analysis,' 'demo script,' 'talk track,' 'sales playbook,' 'proposal template,' 'buyer persona card,' 'battle card,' 'battlecard,' 'competitive one-pager,' 'win-loss analysis,' 'why are we losing deals,' 'loss reasons,' 'how do I respond to this objection,' 'prospect just said,' 'help my sales team,' 'sales materials,' or 'what should I give my sales reps,' 'cold call script,' or 'voicemail script.' Use this for any document or asset that helps a sales team close deals. For public competitor comparison pages, see competitors. For running buyer interviews or churn research, see customer-research. For marketing website copy, see copywriting. For cold outreach emails, see cold-email. For the offer being sold (bonuses, guarantees, pricing structure),
revops
coreyhaines31/marketingskills
When the user wants help with revenue operations, lead lifecycle management, or marketing-to-sales handoff processes. Also use when the user mentions 'RevOps,' 'revenue operations,' 'lead scoring,' 'outbound pipeline stages,' 'lead routing,' 'MQL,' 'SQL,' 'pipeline stages,' 'deal desk,' 'CRM automation,' 'marketing-to-sales handoff,' 'data hygiene,' 'leads aren't getting to sales,' 'pipeline management,' 'lead qualification,' or 'when should marketing hand off to sales.' Use this for anything involving the systems and processes that connect marketing to revenue. For cold outreach emails, see cold-email. For email drip campaigns, see emails. For pricing decisions, see pricing.
sales-funnel-blueprint
autonnel/autonnel-skills
Turn an offer into a concrete multi-step sales funnel spec - page-by-page structure, price ladder, copy outline and the metrics each step must hit. Use when asked to build a sales funnel, marketing funnel, landing page flow, lead magnet funnel, webinar funnel, tripwire or VSL funnel, when planning a product launch page flow, or when someone asks "what pages do I need" for selling something online.
pricing
coreyhaines31/marketingskills
When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' 'monetization,' 'how much should I charge,' 'my pricing is wrong,' 'pricing page,' 'annual vs monthly,' 'per seat pricing,' 'should I offer a free plan,' 'pricing page teardown,' 'pricing page audit,' 'is my pricing page AI-readable,' or 'can AI read my pricing.' Use this whenever someone is figuring out what to charge, how to structure their plans, or wants to audit a pricing page (for humans and for the AI agents that shortlist tools). For in-app upgrade screens, see paywalls. For offer construction (bonuses, guarantees, value framing, naming) on services/courses/coaching/high-ticket B2B, see offers.
cross-border-ecommerce
nexscope-ai/ecommerce-skills
Cross-border e-commerce expansion advisor. Scores target markets on 8 weighted dimensions (market size, ecommerce penetration, competition, regulatory complexity, logistics infrastructure, payment ecosystem, cultural distance, IP protection), compares 5 fulfillment models with cost and transit data, provides country-by-country tax/duty compliance guides (EU VAT/IOSS, UK VAT, US sales tax, CA GST, AU GST, JP consumption tax), maps local payment preferences by market, and builds a phased expansion roadmap. No API key required.
pricing-strategy
coreyhaines31/marketingskills
When the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increase,' 'value metric,' 'Van Westendorp,' 'willingness to pay,' 'monetization,' 'how much should I charge,' 'my pricing is wrong,' 'pricing page,' 'annual vs monthly,' 'per seat pricing,' or 'should I offer a free plan.' Use this whenever someone is figuring out what to charge or how to structure their plans. For in-app upgrade screens, see paywall-upgrade-cro.