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 preflightgit 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/preflight)<a href="https://agentmods.dev/skills/spartanlabsxyz/simmer-sdk/preflight"><img src="https://agentmods.dev/badge/skills/spartanlabsxyz/simmer-sdk/preflight/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/preflight"><img src="https://agentmods.dev/badge/skills/spartanlabsxyz/simmer-sdk/preflight.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 | $0.00061 | $0.01995 |
| Opus 5 | $0.00030 | $0.00997 |
| Sonnet 5 | $0.00012 | $0.00399 |
| Haiku 4.5 | $0.00006 | $0.00199 |
Grade A, and why
simmer-preflight 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 2d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simmer Preflight
Run client.preflight() before every real-money trade. One call returns:
- Who you are: agent ID, tier, venue resolved from your API key context
- Which wallet will sign: execution wallet, deposit wallet, signer mode (OWS / external key / managed)
- Spendable balance: venue-specific USDC or $SIM balance from the briefing
- Open exposure: sum of
current_valueacross your existing positions (real venues only for USD cap) - Cap check: whether
planned_amount + open_exposure_totalexceeds yourexposure_cap_usd - Risk alerts: any briefing risk signals (concentration, expiry, reliability)
- ok_to_trade: a single boolean — True if no blockers
When to use
Call preflight before every automated trade, especially:
- Before the first real-money order of a run
- Before scaling into a position beyond your initial size
- When your heartbeat wakes up after a long sleep (state may have changed)
Do not call it on every polling tick — it makes 3 API calls. Once per trade intent is correct.
Call it
from simmer_sdk import SimmerClient
client = SimmerClient.from_env(venue="polymarket")
result = client.preflight(
venue="polymarket", # venue to check (defaults to client.venue)
planned_amount=5.0, # USDC you plan to spend on this trade
exposure_cap_usd=100.0, # your total cross-venue exposure limit
)
if not result.ok_to_trade:
print(f"Preflight blocked: {result.blockers}")
# e.g. ["EXPOSURE_CAP_EXCEEDED"]
return
# Log for audit
ledger.record({
"preflight_id": result.client_preflight_id,
"ok": result.ok_to_trade,
"exposure_before": result.open_exposure_total,
"planned": result.planned_amount,
})
Result fields
| Field | Type | Description |
|---|---|---|
client_preflight_id |
str | UUID for your trade ledger — log before every order |
agent_id |
str | None | Agent UUID from /api/sdk/agents/me |
tier |
str | None | Account tier: "free" / "pro" / "elite" |
resolved_venue |
str | Normalised venue: "sim" / "polymarket" / "kalshi" |
execution_wallet |
str | None | EOA that signs trades (per-agent OWS wallet for Elite per-agent callers) |
deposit_wallet |
str | None | Deposit wallet address (DW cohort only; None for Cohort A) |
signer_status |
str | "ows" / "external_key" / "managed" |
spendable_balance |
float | None | Venue balance: pUSD/USDC (real) or $SIM (sim) |
gas_balance |
float | None | POL / SOL for gas — None in v0 (deferred to v1) |
open_exposure_total |
float | Sum of current_value across open positions (real venues only when cap is USD) |
exposure_cap_usd |
float | The cap you passed in |
planned_amount |
float | The planned trade size you passed in |
would_exceed_cap |
bool | True if open_exposure_total + planned_amount > exposure_cap_usd |
pending_alerts |
list[dict] | Risk alerts from briefing (normalised to {message: str}) |
ok_to_trade |
bool | True if no blockers |
blockers |
list[str] | Blocker codes (see below) |
warnings |
list[str] | Non-blocking advisories (fetch failures, skipped checks) |
What ships with it
4 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.
- 2d ago Changed 505d8381caef
- 11d ago First seen · 179 lines · 61 tokens per session scan A 02aebd4a27ed
simmer-preflight is a skill published in the GitHub repository SpartanLabsXyz/simmer-sdk (48 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 1,995 once invoked, about $0.0003 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.
daily-review
Daily review of open prediction-market exposure with oddsrail: positions, resting orders, fills, markets closing soon, builder attribution.
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.
polymarket
Query Polymarket: markets, prices, orderbooks, history.