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-fast-scalergit 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-fast-scaler)<a href="https://agentmods.dev/skills/spartanlabsxyz/simmer-sdk/polymarket-fast-scaler"><img src="https://agentmods.dev/badge/skills/spartanlabsxyz/simmer-sdk/polymarket-fast-scaler/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-fast-scaler"><img src="https://agentmods.dev/badge/skills/spartanlabsxyz/simmer-sdk/polymarket-fast-scaler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 74 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00084 | $0.02201 |
| Opus 5 | $0.00042 | $0.01100 |
| Sonnet 5 | $0.00017 | $0.00440 |
| Haiku 4.5 | $0.00008 | $0.00220 |
Grade A, and why
polymarket-fast-scaler 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 12d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polymarket FastScaler
Trade Polymarket BTC 5-minute fast markets with a conviction-ladder strategy. Only enters when Binance 1m momentum exceeds the 0.10% magnitude gate. Position size scales with signal strength across 3 tiers.
🚨 Framework, not a production trading system. Read DISCLAIMER.md before connecting to a wallet with real funds.
Polymarket only. All trades execute on Polymarket with real USDC. Paper mode is the default.
⛔ Performance claim retracted (2026-06-12). An earlier version cited an "89.4% win rate / +5.04%" backtest. A look-ahead-enforced replay (Simmer skill-replay) found that backtest measured the 1m candle that starts at window-open, which only closes 60 seconds into the 5-minute window it is meant to predict. The signal the skill can actually act on at the decision point (the last complete 1m candle, i.e. the prior minute) shows no measured edge: roughly a coin flip before fees. Treat this skill as an unvalidated reference template, not a validated edge. Run paper mode and form your own view.
⚠️ Strategy invariants.
magnitude_gate_pctdefaults to 0.10%. Below it the gate admits more low-magnitude noise and fees dominate a larger share of trades. This is a design default, not a validated profit threshold (see the retraction above).
⚠️ Risk monitoring does not apply to sub-15-minute markets. Simmer's stop-loss and take-profit monitors check positions every 15 minutes — they will never fire on 5m markets before resolution. Size accordingly.
Strategy
Signal: Binance 1m candle at window-open — momentum = (close - open) / open × 100
Gate: |momentum| >= magnitude_gate_pct (default 0.10%). Below = no trade.
Side: momentum > 0 → YES, momentum < 0 → NO. Pure direction — no divergence filter.
Sizing (conviction ladder): | Tier | |momentum| | Position | |------|-----------|----------| | 1 | 0.10% – 0.20% | $3 | | 2 | 0.20% – 0.35% | $5 | | 3 | ≥ 0.35% | $10 |
What ships with it
7 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.
- 12d ago First seen · 156 lines · 84 tokens per session scan A ea01ddd1c1ac
polymarket-fast-scaler is a skill published in the GitHub repository SpartanLabsXyz/simmer-sdk (48 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 2,201 once invoked, about $0.0004 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
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-profile
Polymarket address profiler — input any 0x address, get a complete trading profile with PnL, win rate, positions, category breakdown, and top trades. All data from public APIs, no local database needed.
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.