trader-broker
Skill14 starsChanged 29 days agoMITView on GitHub
Order Executor. Places APPROVED orders through your brokerage connector, one at a time, and never without your explicit yes. Shows each order as a plain ticket plus the exact JSON for Alpaca's place_stock_order, records your yes word for word, then Claude's own Allow once / Deny card asks again. Covers setting up Alpaca's official MCP server in Claude Desktop (paper trading by default, keys in env vars, never in chat), the Interactive Brokers connector (orders go to your IBKR account for your approval), and setting order tools to "Needs approval". Use when the user says "place the orders", "buy it", "execute", "send it to my broker", "connect Alpaca", "connect Interactive Brokers", "set up paper trading", or after /trader-risk passes.
- Reads credentials
5 other projects use a version of this, 5 of them edited; 4 new projects in the last 4 weeks, against 0 the 4 before.
Adopted by
Surging: 4 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- Kafish69/ultimate-traderedited, first seen Nov 8, 2026
- hasanaljadi/elite-trader-skilledited, first seen Nov 8, 2026
- KanishkThakar/day-trader-warroomedited, first seen Oct 25, 2026
- neubauerwilli/trader-skill-deutschedited, first seen Oct 25, 2026
- Jakeschincariol/day-trader-skilledited, first seen Oct 20, 2026
Used with
Projects with it also use trader-entry, trader-exit and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JakeschincariolSkilltrader-entry
Entry Timer. Watches a setup bar by bar and tells you the moment to get in. Reads free Yahoo 1-minute or 5-minute bars, builds the opening range (the first 15 minutes by default) and calls the entry on the first completed bar that CLOSES above the range high, or above a level you give it (like a 20-day high from the scanner), with an optional volume check. Says waiting and how far, triggered with the time and the price, expired, or not open yet, and writes trader/entry.json for /trader-exit. Long side only. It never places an order. Use when the user says "tell me when to get in", "watch TSLA", "has it broken out", "did it break the opening range", "entry signal", "time my entry", "check my watchlist", or after /trader-scanner and /trader-news, before /trader-exit.
Also in 4 projects that use this
JakeschincariolSkilltrader-exit
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.
Also in 4 projects that use this
- +2 more from Jakeschincariol
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 5
- Jakeschincariol/day-trader-skill★ 2059% same
- hasanaljadi/elite-trader-skill★ 259% same
- neubauerwilli/trader-skill-deutsch★ 211% same
- Kafish69/ultimate-trader★ 159% same
- KanishkThakar/day-trader-warroom★ 059% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- trader-alertsSkill
- trader-analystSkill
- trader-budgetSkill
- trader-copycatSkill
- trader-newsSkill
- trader-pelosiSkill
- trader-rebalanceSkill
- trader-riskSkill
- trader-screenerSkill
- trader-taxSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. 7 are common, 0 are distinctive, and 6 are very specific to this project.
7
Common
Most of the 4 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 75
Keys never go in the chat: Never ask for them, never read this file back into the conversation, and if the user pastes a key anyway, tell …
- Very specific: line 85
every other tool that places, changes, cancels or closes anything (cancel_order_by_id, close_position, update_account_config): Needs …
- Very specific: line 90
read-only tools (get_account_info, get_all_positions, get_stock_snapshot, get_stock_latest_quote): Always allow is fine.
- Common: line 92
Check it: ask Claude for the Alpaca account info (read only) and confirm in the Alpaca dashboard that it is the paper account.
- Common: line 118
If it prints "Not recorded", the reply was not an explicit yes for this order (for example "sure", "yes to all", or a yes that names a …
- Very specific: line 121
Only after "Recorded your yes", call place_stock_order with exactly the JSON the ticket printed.
- Very specific: line 127
When the fill is known (the tool's response, or later from get_all_positions), ticket.py fill adds it to trader/portfolio.json as a tax lot …
- Common: line 148
Never places an order without all three gates, and never two orders on one yes.
- Common: line 149
Never places orders from a scheduled or background task: nobody is there to say yes.
- Common: line 150
Never asks for, reads, stores or repeats API keys or passwords.
- Very specific: line 151
Never switches ALPACA_PAPER_TRADE or "paper" to live.
- Very specific: line 152
Never calls close_all_positions, cancel_all_orders, option or crypto order tools on its own.
- Common: line 162
No options, margin, short selling or leverage unless the config allows it and the user confirms.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
trader-broker
The Order Executor is the only skill in this pack that can lead to a real order, so it is the strictest. An order reaches the market only after three separate gates, every time, for every order:
- trader-risk passed this exact order today (matched by fingerprint).
- The user typed an explicit yes for this one order in the chat.
- The user clicked Allow once on Claude's own permission card, which appears because the order tool is set to "Needs approval".
Two yeses from the user, one PASS from the rules. No yes, no order.
${CLAUDE_SKILL_DIR} below is this skill's folder (where this SKILL.md lives).
python3 "${CLAUDE_SKILL_DIR}/ticket.py" show # every ticket, READY or not
python3 "${CLAUDE_SKILL_DIR}/ticket.py" approve --index 1 --reply "yes"
python3 "${CLAUDE_SKILL_DIR}/ticket.py" result --index 1 --status placed --broker-id ID
python3 "${CLAUDE_SKILL_DIR}/ticket.py" fill --symbol AAPL --side buy --qty 3.6628 --price 341.27
python3 "${CLAUDE_SKILL_DIR}/ticket.py" logticket.py never talks to a broker. It renders tickets, checks that a reply
is a real yes for that order, and keeps the log in trader/state/broker.json.
Setup A: Alpaca (official MCP server, Claude Desktop)
Alpaca's own server is github.com/alpacahq/alpaca-mcp-server (MIT). It runs on the user's computer inside Claude Desktop. It is not in Claude's connector directory. It trades on a paper account unless told otherwise.
- The user makes an Alpaca account and creates paper trading API keys in the Alpaca dashboard. Paper keys are separate from live keys.
- The user installs
uv(it providesuvx), from docs.astral.sh/uv. - In Claude Desktop: Settings > Developer > Edit Config. That opens
claude_desktop_config.json(macOS:~/Library/Application Support/Claude/, Windows:%APPDATA%\Claude\). The user adds this block (also inclaude_desktop_config.example.jsonhere) and types their own keys into the file:
{
"mcpServers": {
"alpaca": {
"command": "uvx",
"args": ["alpaca-mcp-server"],
"env": {
"ALPACA_API_KEY": "paste your paper key here, in this file only",
"ALPACA_SECRET_KEY": "paste your paper secret here, in this file only",
"ALPACA_PAPER_TRADE": "true",
"ALPACA_TOOLSETS": "account,trading,stock-data"
}
}
}
}The env block hands the keys to the server as environment variables.
Keys never go in the chat. Never ask for them, never read this file
back into the conversation, and if the user pastes a key anyway, tell them
to delete that message and make new keys in the Alpaca dashboard.
ALPACA_PAPER_TRADE is already true by default; writing it makes it
visible. ALPACA_TOOLSETS is optional and hides the tools they do not need.
4. Restart Claude Desktop.
5. Set the tool permissions. Customize > Connectors (Settings > Connectors
in older versions), open alpaca, and for each tool pick Always allow, Needs
approval or Blocked:
place_stock_order: Needs approval. Never Always allow.- every other tool that places, changes, cancels or closes anything
(
cancel_order_by_id,close_position,update_account_config): Needs approval. place_option_order,place_crypto_order,close_all_positions,cancel_all_orders,exercise_options_position: Blocked unless the user has a reason and says so.- read-only tools (
get_account_info,get_all_positions,get_stock_snapshot,get_stock_latest_quote): Always allow is fine.
- Check it: ask Claude for the Alpaca account info (read only) and confirm in the Alpaca dashboard that it is the paper account.
In Claude Code instead of Claude Desktop, keep the order tool on ask in
.claude/settings.json: "permissions": {"ask": ["mcp__alpaca__place_stock_order"]},
and never put an order tool in allow.
Setup B: Interactive Brokers (connector in Claude's directory)
Interactive Brokers publishes a verified connector: claude.ai/directory/interactive-brokers
(connector URL https://api.ibkr.com/v1/api/mcp). Add it from Customize >
Connectors > Browse connectors and sign in to IBKR there, not in the chat.
Its listing says Claude can draft trade instructions that are sent to the
user's IBKR account for their review and approval, and that Claude never
submits orders directly to the market. So with IBKR the final yes happens in
IBKR as well. Set "broker": "ibkr" in trader/config.json, and size with
--whole-shares if IBKR wants share counts. Set its tools that draft orders
to Needs approval too.
Steps, for each order
ticket.py show. Only READY tickets go to the user. A ticket that is NOT READY or BLOCKED goes back to/trader-risk.- Show ONE ticket and ask: "Place this order? Reply yes or no." One order per question. Never offer "yes to all".
- Run
ticket.py approve --index N --reply "<the user's reply, word for word>". If it prints "Not recorded", the reply was not an explicit yes for this order (for example "sure", "yes to all", or a yes that names a different stock or amount). Ask again. Never turn a reply into a yes yourself. - Only after "Recorded your yes", call
place_stock_orderwith exactly the JSON the ticket printed. Claude's card appears: Allow once or Deny. - Record what happened:
ticket.py result --index N --status placed --broker-id <id from the response>, or--status deniedif they pressed Deny, or--status failedwith--notefor an error. A failed order is not retried without a new check and a new yes. - When the fill is known (the tool's response, or later from
get_all_positions),ticket.py filladds it totrader/portfolio.jsonas a tax lot for trader-tax. Then the next ticket.
Example: the reel
ORDER 1 of 5, PAPER account, Alpaca
BUY $1,250 of AAPL, market order, good for today
READY: trader-risk PASS, waiting for your yes
Claude will call place_stock_order with exactly:
{"symbol": "AAPL", "side": "buy", "notional": "1250",
"type": "market", "time_in_force": "day"}The user replies "yes". Claude records it, calls place_stock_order, and the
card reads "Claude wants to use Place stock order" with that JSON and two
buttons: Allow once, Deny. Allow once sends it to the paper account.
What it never does
- Never places an order without all three gates, and never two orders on one yes.
- Never places orders from a scheduled or background task: nobody is there to say yes.
- Never asks for, reads, stores or repeats API keys or passwords.
- Never switches
ALPACA_PAPER_TRADEor"paper"to live. The user does that themselves. - Never calls
close_all_positions,cancel_all_orders, option or crypto order tools on its own.
Safety
- Education and tooling, not financial advice. No order here is a recommendation, and nothing promises returns.
- Paper trading by default (
"paper": true,ALPACA_PAPER_TRADEtrue). Going live is the user's own decision. - 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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

