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.
npx skills add SpartanLabsXyz/simmer-sdk --skill polymarket-combo-buildergit clone --depth 1 https://github.com/SpartanLabsXyz/simmer-sdkWrote 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.
[](https://agentmods.dev/skills/spartanlabsxyz/simmer-sdk/polymarket-combo-builder)<a href="https://agentmods.dev/skills/spartanlabsxyz/simmer-sdk/polymarket-combo-builder"><img src="https://agentmods.dev/badge/skills/spartanlabsxyz/simmer-sdk/polymarket-combo-builder/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.
<a href="https://agentmods.dev/skills/spartanlabsxyz/simmer-sdk/polymarket-combo-builder"><img src="https://agentmods.dev/badge/skills/spartanlabsxyz/simmer-sdk/polymarket-combo-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00113 | $0.01349 |
| Opus 5 | $0.00056 | $0.00674 |
| Sonnet 5 | $0.00023 | $0.00270 |
| Haiku 4.5 | $0.00011 | $0.00135 |
Grade A, and why
polymarket-combo-builder 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Combo Builder
Place a real Polymarket combo (parlay): bundle 2+ binary legs into one YES/NO position, settled by a single signed RFQ order on Polymarket's combo exchange. Polymarket quotes the combined odds live; you sign once; if every leg hits you win the combined payout, and if any single leg loses you lose the whole stake.
This is the atomic combo — distinct from the leg-by-leg
polymarket-worldcup-parlay-roller. Live placement works with EOA /
self-custody wallets, and with deposit wallets after a one-time
activate_combo_dw() setup (details below).
Read DISCLAIMER.md before going live. This is a framework, not an edge, and it runs in dry-run by default. Dry-run is a local plan — it resolves legs and shows the combined-odds estimate but signs and sends nothing. There is no paper / simulated-fill mode for combos (they're Polymarket-only). Note: dry-run still reads your wallet key to resolve trading identity, but it never signs or sends.
Polymarket venue only. Combos are a BETA Polymarket product (sports markets today); label them as such to users.
How payout works
A combo's combined price is the makers' quoted probability that all legs hit. Example: three legs near 0.50 each quote around a 0.12–0.15 combined price, i.e. a ~7–8x payout multiple on the stake. The quote you sign already bakes in maker spread — it is not a naive product of the leg prices (the skill shows that product only as a pre-quote preview).
Setup
Agent: do this once with the user.
- Get the thesis in natural language, e.g. "Brazil to win AND over 2.5 goals AND Argentina to win."
- Resolve each pick to a combo leg. Combo-eligible legs come from the
combo-markets feed —
simmer_sdk.combo.fetch_combo_legs(). Each leg exposesposition_ids = [YES_token, NO_token]; store the chosen side's token id. Moneyline, spread (-spread-), and total/over-under (-total-) legs are all eligible. - Confirm with the user, restating each leg's exact resolution condition and the total-loss-if-any-leg-loses risk.
- Write
combo_config.jsonfromcombo_config.example.json(>= 2 legs). - Dry-run first, review the plan, then go live.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 119 lines · 113 tokens per session scan A a1db683bc306
polymarket-combo-builder is a skill published in the GitHub repository SpartanLabsXyz/simmer-sdk (48 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 1,349 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
moonpay-scout
Prediction market arbitrage & alpha scout. Searches Polymarket and Kalshi for the same event, runs cross-platform arb math (including fees), and ranks opportunities by profitability. Use when asked to "find arb", "scout markets", "find edge", or scan a specific topic across prediction markets.
find-fade-setup
Find and evaluate a fade (mean-reversion) setup on prediction markets with oddsrail: candidates, overshoot signal, book, walked cost, resolution criteria, Kelly size, dry-run order.
check-cross-venue-edge
Decide whether a Polymarket vs Kalshi price difference is a real edge or a settlement mismatch: comparevenues, settlementaudit, quotecost on both legs, resolution criteria.
settle-resolved
Turn resolved and hedged Polymarket positions back into USDC, gasless, through the operator's relayer key, with a dry-run read-back first.
daily-review
Daily review of open prediction-market exposure with oddsrail: positions, resting orders, fills, markets closing soon, builder attribution.
polymarket
Query Polymarket: markets, prices, orderbooks, history.