backtest-expert
Expert guidance for systematic backtesting of trading strategies. Use when developing,…
Calculate contract-based futures position sizes from a direction, entry, and stop-loss, using verified per-symbol contract specs (multiplier, tick size, tick value). Use when the user asks how many futures contracts to trade, wants to size a futures position (ES, NQ, ZB, GC, CL,
$ npx -y skills add tradermonty/claude-trading-skills --skill futures-position-sizer --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/futures-position-sizerContext preview
The summary Claude sees to decide when to auto-load this skill.
Calculate contract-based futures position sizes from a direction, entry, and stop-loss, using verified per-symbol contract specs (multiplier, tick size, tick value). Use when the user asks how many futures contracts to trade, wants to size a futures position (ES, NQ, ZB, GC, CL,
name: futures-position-sizer description: Calculate contract-based futures position sizes from a direction, entry, and stop-loss, using verified per-symbol contract specs (multiplier, tick size, tick value). Use when the user asks how many futures contracts to trade, wants to size a futures position (ES, NQ, ZB, GC, CL, 6E/E6, VX, BT, ...), or is handing off a contrarian-setup-gate READY_FOR_PLAN direction/invalidation_level for sizing. Pure, offline calculation -- no API keys, no network.
Shapiro pipeline step 4: convert a direction, entry price, and stop-loss into a contract count, given an account risk budget and a verified contract spec (multiplier, tick size, tick value). This is a NEW, separate skill from `position-sizer` -- futures contracts are leveraged, multiplier-based instruments with wildly different dollar-per-point values (a $0.25 move is $12.50 on ES but $5.00 on NQ and $31.25 on ZB); reusing the equity share-count sizer for futures would silently produce wrong position sizes.
Two ways to size a trade:
`--entry` is ALWAYS required, in both modes -- neither this skill nor the gate ever derives an entry price; the operator supplies it.
**Mode A -- explicit:**
python3 skills/futures-position-sizer/scripts/futures_position_sizer.py \ --symbol ES --direction LONG --entry 5000.25 --stop 4980.00 \ --account-size 100000 --risk-pct 1.0 \ --output-dir reports/ --format both
**Mode B -- gate handoff:**
python3 skills/futures-position-sizer/scripts/futures_position_sizer.py \ --gate-json reports/contrarian_setup_gate_B6_2026-07-15.json \ --entry 1.3400 \ --account-size 100000 --risk-pct 1.0 \ --output-dir reports/ --format both
`--symbol` may be omitted in mode B -- it is taken from the gate report. If both are given, they must match (`gate_symbol_mismatch` otherwise). `--direction`/`--stop` are rejected alongside `--gate-json` (usage error, exit 2) -- pass one mode or the other, never both.
| `sizing_status` | Meaning | |---|---| | `SIZED` | `contracts` >= 1; `total_risk_usd`/`risk_pct_of_account` are the actual risk taken | | `NO_TRADE` | Never a crash -- always carries `no_trade_reason`. See the reason glossary below |
A `NO_TRADE` result from `risk_below_one_contract` still reports the full risk math (risk per contract, risk budget, stop distance) -- the account simply cannot afford one contract at this risk percentage and stop distance; widen the stop, increase risk %, or skip the trade.
`warnings` (top-level list) never blocks sizing -- it flags audit-worthy conditions: `risk_pct_above_2` (risk above the 2% guideline), `off_tick_grid_entry`/`off_tick_grid_stop` (a non-bond symbol's price is not exactly on the tick grid -- legitimate for a mid-quote, but worth a second look).
python3 skills/futures-position-sizer/scripts/futures_position_sizer.py --list-specs
Prints the full 23-market core table (multiplier, tick size, tick value, currency, exchange) sourced from official exchange contract-spec pages -- see `references/futures-contract-specs.md` for the per-row source URLs and verification dates.
Bond/note futures (ZT, ZF, ZN, ZB) quote in fractions of a point (32nds, or 32nds-of-32nds), commonly written with an apostrophe: `110'16` means `110 + 16/32 = 110.50`. Typing `110.16` instead -- reading the digits after the apostrophe as if they were decimal cents -- is a classic, silent, wrong-money-math mistake: `110.16` is not on the ZB tick grid (`0.03125` = 1/32) at all.
# WRONG -- 110.16 is not on the 1/32 grid; this is almost certainly a # mistyped "110'16" (which means 110.50). Exits 2, no report written: python3 skills/futures-position-sizer/scripts/futures_position_sizer.py \ --symbol ZB --direction LONG --entry 110.16 --stop 108.00 \ --account-size 100000 --risk-pct 1.0 # CORRECT -- decimal points, not the raw 32nds digits: python3 skills/futures-position-sizer/scripts/futures_position_sizer.py \ --symbol ZB --direction LONG --entry 110.50 --stop 108.00 \ --account-size 100000 --risk-pct 1.0
Every other symbol in the table quotes in plain decimal points -- an off-grid price there (a mid-quote, for instance) is only a soft `off_tick_grid_*` warning, never a rejection.
Writes `futures_position_size_<SYMBOL>_<as-of>.json` to `--output-dir` when `--format json|both`; `--format text|both` prints a formatted summary to stdout. `--as-of` defaults to today (this is an operator-time sizing tool, not a backtest tool).
Claude Trading Skills started as a personal project to use AI to improve my own trading process. Claude Trading Skills is a Claude Skills-based trading workflow toolkit for time-constrained individual investors.
Expert guidance for systematic backtesting of trading strategies. Use when developing,…
This skill should be used when analyzing market breadth charts, specifically the S&P 500…
Generate Minervini-style breakout trade plans from VCP screener output with worst-case risk…
Screen US stocks using William O'Neil's CANSLIM growth stock methodology. Use when user…
Synthesize the three Jason Shapiro contrarian-pipeline verdicts (COT crowding, news-reaction…
Detect crowded speculative positioning in CFTC futures markets (COT report analysis) to find…