simmer-preflight

simmer-preflight is a skill for Claude Code, Codex from SpartanLabsXyz/simmer-sdk. It costs 61 tokens per session (1,995 once invoked), scanned A, original, MIT.

A pre-trade check for automated agents that reports wallet details, venue status, balances, open positions, risk alerts, and whether a planned trade is allowed.

In plain words
What is it for?
Use it before each automated trade, when increasing a position, or after an agent wakes from a long pause.
Why use it?
It helps catch missing funds, configuration problems, and exposure-cap overruns before a real-money order is placed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before each automated trade, when increasing a position, or after an agent wakes from a long pause.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/spartanlabsxyz/simmer-sdk/preflight
Install

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.

Any agent
npx skills add SpartanLabsXyz/simmer-sdk --skill preflight
Clone the repo
git clone --depth 1 https://github.com/SpartanLabsXyz/simmer-sdk

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for simmer-preflight

README.md
[![agentmods](https://agentmods.dev/badge/skills/spartanlabsxyz/simmer-sdk/preflight/github.svg)](https://agentmods.dev/skills/spartanlabsxyz/simmer-sdk/preflight)
Your own site
<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.

agentmods 80×15 button for simmer-preflight

Your own site · 80×15
<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>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 505d8381caef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 3 executable files (preflight.py, tests/__init__.py, tests/test_preflight.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

mcp/bundled-skills/preflight/SKILL.md · 179 lines

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_value across your existing positions (real venues only for USD cap)
  • Cap check: whether planned_amount + open_exposure_total exceeds your exposure_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)

Read the full file on GitHub · 179 lines

Files

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.

Changes

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.

  1. 2d ago Changed 505d8381caef
  2. 11d ago First seen · 179 lines · 61 tokens per session scan A 02aebd4a27ed

Subscribe to this mod's changes

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.