Track Record
11 of 14 real-money trades closed at a profit.
Claude Code trading the GammaRips pool with real money, Sep 14 to Oct 2, 2026. Each morning the agent reads the pool over MCP, chooses its own contract, and sets its target and its stop before entry.
net realized P&L, all 14 trades
closed at the target the agent set before entry
median trade, on premium
Record through Oct 2, 2026, updated daily. Every closed trade in the window is below, wins and losses. The agent's day-by-day traces are public in the traces folder on GitHub.
| Entry day | Ticker | Contract | Entry | Exit | % on premium | P&L | Exit reason |
|---|---|---|---|---|---|---|---|
| Sep 14out Sep 15 | BE | $300 call, exp Oct 16 '26BE261016C00300000 | $10.68 | $14.00 | +31.1% | +$332 | Target |
| Sep 16out Sep 17 | NVDA | $215 call, exp Sep 25 '26NVDA260925C00215000 | $4.70 | $6.25 | +33.0% | +$310 | Target |
| Sep 17 | TSLA | $365 call, exp Sep 25 '26TSLA260925C00365000 | $12.85 | $9.20 | −28.4% | −$365 | Stop |
| Sep 18 | NVDA | $222.50 call, exp Sep 25 '26NVDA260925C00222500 | $2.15 | $2.69 | +25.1% | +$270 | Target |
| Sep 21 | NVDA | $225 call, exp Sep 28 '26NVDA260928C00225000 | $2.92 | $3.60 | +23.3% | +$476 | Target |
| Sep 22 | NVDA | $230 call, exp Oct 2 '26NVDA261002C00230000 | $4.00 | $4.80 | +20.0% | +$400 | Target |
| Sep 23 | NVDA | $232.50 call, exp Oct 2 '26NVDA261002C00232500 | $2.23 | $1.5317 | −31.3% | −$419 | Stop |
| Sep 24 | INTC | $125 call, exp Oct 2 '26INTC261002C00125000 | $4.645 | $5.90 | +27.0% | +$251 | Target |
| Sep 25 | NVDA | $227.50 call, exp Oct 2 '26NVDA261002C00227500 | $2.18 | $2.77 | +27.1% | +$413 | Target |
| Sep 28out Sep 29 | SPCX | $155 call, exp Oct 9 '26SPCX261009C00155000 | $2.16 | $2.70 | +25.0% | +$378 | Target |
| Sep 29out Oct 1 | NVDA | $232.50 call, exp Oct 16 '26NVDA261016C00232500 | $5.00 | $5.40 | +8.0% | +$120 | End of hold |
| Sep 30out Oct 1 | SPCX | $155 call, exp Oct 9 '26SPCX261009C00155000 | $2.58 | $3.20 | +24.0% | +$372 | Target |
| Oct 1 | INTC | $125 call, exp Oct 9 '26INTC261009C00125000 | $1.99 | $2.58 | +29.6% | +$295 | Target |
| Oct 2 | NVDA | $235 call, exp Oct 9 '26NVDA261009C00235000 | $5.15 | $3.25 | −36.9% | −$570 | Stop |
| 14 trades · 11 closed at a profit · 10 at target | median +24.5% | +$2,263 | |||||
Names traded: NVDA (8), INTC (2), SPCX (2), BE (1), TSLA (1). Entry and exit are realized broker fills per share. P&L is in dollars for the full position. The premium column is the exit fill against the entry fill.
Past results: real-money trades and historical pool data. Educational only. Not investment advice.
The pool moves. Here is how often, and how far.
Every pool contract, measured from the 10:00 ET entry. This is the history your AI sets its targets from. Updated daily.
Before expiration
hit +20% before expiration
hit +50% before expiration
hit +100% before expiration
N = 793 expired pool contracts, scan dates Aug 24 to Oct 1, 2026
Within 3 trading days
hit +20% within 3 trading days
hit +50% within 3 trading days
hit +100% within 3 trading days
N = 1,613 pool contracts · scan dates Aug 24 to Oct 12, 2026 · 35 scan days · median peak +29.7%
Why the exit plan matters
73.2% of the same 1,613 contracts also touched −30% inside the same window. Most contracts move both ways, so the exit plan your AI sets decides the result. That is what the exit lab is for: your AI reads these touch rates for any target and any stop, scores the bracket on past pool contracts, and sets both before entry. Connect your AI.
A hit is a touch: the option premium traded at that level at some point in the window. It is a measure of how far contracts moved, not profit kept by any account.
Past results: real-money trades and historical pool data. Educational only. Not investment advice. Pool figures are tracked on a paper basis.
Most pool contracts had a moment before expiration.
We follow every contract we surface, from the 10:00 ET fill on the morning we surfaced it through to expiration, with no exit rule applied. Nothing gets edited out.
were up +40% or better at some point
were up +66% or more at their best moment
doubled at some point
full-life window, no exit rule · all 4,356 contracts that have expired so far, 2026-04-10 to 2026-10-01 · updated daily · includes contracts from the funnel before 2026-08-24
The best moment usually comes early.
When did each contract hit its best price, counting from the morning we surfaced it? Day 1 is that morning.
Most best moments come early. Even so, about 1 out of 6 contracts does not hit its best price until more than two weeks in.
This chart is the full-life window, from the morning we surfaced each contract to expiration. The hit rates above use a 3-trading-day window. Match the window to the hold your AI plans.
The exit plan is where the result gets made.
The moves are real, and they are temporary. The typical contract's worst moment along the way was -98% from the fill, even when it also had a big up moment. Held all the way to expiration with no exit, about 7 out of every 10 finished down 90% or more.
A target and a stop set before entry decide how much of a move a trade keeps. Your AI sets both from the exit lab. The live agent at the top of this page sets both before every entry.
Building a pool you can actually trade is our job. The trade plan is yours and your AI's.
See the full data: charts and tables for people and agents who want the detail
Every figure below sits in the full-life window: the 10:00 ET surfacing fill through to expiration, with no exit rule applied. It is a different window from the 3-trading-day hit rates above and from the 3-day opportunity surface served over MCP. Compare numbers inside one window.
median best moment (peak premium return)
the top 10% of contracts peaked here or higher
median worst moment along the way
median value if held to expiration
Best moment before expiration
Each contract's best price after surfacing, against the 10:00 ET surfacing price. Share of all 4,356 tracked contracts per bucket.
Value if held to expiration
The same pool, never sold. Settlement value against the surfacing price. Blue = loss side, gold = gain side. N = 4,358.
| bucket | contracts | share |
|---|---|---|
| <+5% | 683 | 15.7% |
| +5–20% | 512 | 11.8% |
| +20–40% | 522 | 12% |
| +40–70% | 516 | 11.8% |
| +70–100% | 399 | 9.2% |
| +100–200% | 728 | 16.7% |
| +200%+ | 996 | 22.9% |
| bucket | contracts | share |
|---|---|---|
| <−90% | 3033 | 69.6% |
| −90–−50% | 148 | 3.4% |
| −50–0% | 201 | 4.6% |
| 0–+50% | 168 | 3.9% |
| +50–100% | 145 | 3.3% |
| +100–200% | 222 | 5.1% |
| +200%+ | 441 | 10.1% |
Peak figures are realized per-contract extremes. They are profit potential, not a return anyone earned. Nobody sells at the exact top. Distributions cover 2026-04-10 to 2026-10-01 and exclude 1,349 contracts too illiquid to price cleanly at entry, 960 not yet expired or awaiting the nightly labeler, and 4 whose labeling failed. All counted, none hidden. Cohort break: contracts surfaced before the morning of 2026-08-25 (scan dates before 2026-08-24) came from the earlier unusual-activity funnel, which the liquid-universe funnel replaced. The two are not one population, and this record is still mostly the older pool, because a contract only joins it after it expires. The research record behind the pool, with every study, is on Methodology.
Past results: real-money trades and historical pool data. Educational only. Not investment advice. Pool figures are tracked on a paper basis.
Give your AI the same pool.
The agent behind this record reads the same nightly pool your AI gets over MCP, in Claude, ChatGPT, Cursor, or Codex. Add the exit lab, and your AI builds the trade plan with you: candidates, entry, target, stop, and size. You decide.
Or browse the pool free, no account needed.
The live record is real-money trades in the founder's agent account, entered on this page by hand from realized broker fills. Pool figures are historical data tracked on a paper basis. Hit and excursion figures are per-contract touches inside the stated window, not returns earned by any account. Educational content only. Not investment advice. Past results do not promise future results.