Kalshi Fed Dot Plot Trader

Trades Fed rate markets on Kalshi using FOMC dot plot median implied rate path. Computes fair probability of cut/hike per meeting and trades when market dive...

Security Scan

The skill's code and docs are coherent with a trading bot that needs a Simmer API key and a Solana private key, but the registry metadata omits those required credentials and that mismatch + the use of a high-value private key warrants caution before installing or providing secrets.

Purpose & Capability

The skill name/description (Kalshi Fed Dot Plot Trader) matches the observed behavior: it discovers Kalshi markets and uses a Simmer SDK client to execute trades. Requiring SIMMER_API_KEY and a SOLANA_PRIVATE_KEY is consistent with a trading agent that must authenticate to Simmer and sign Solana transactions. However, the registry metadata at the top of the report lists 'Required env vars: none' and 'Primary credential: none' while both SKILL.md and clawhub.json declare SIMMER_API_KEY and SOLANA_PRIVATE_KEY. That inconsistency is notable and unexplained.

Instruction Scope

SKILL.md and trader.py's instructions focus on discovering markets, computing fair probabilities from the Fed dot plot, and executing trades. The runtime instructions and code only reference trading-related environment variables (SIMMER_API_KEY, SOLANA_PRIVATE_KEY, optional TRADING_VENUE, AUTOMATON_MAX_BET) and do not instruct reading unrelated system files or exfiltrating data to unknown endpoints. The skill defaults to dry-run and only performs live trades when '--live' is passed.

Install Mechanism

There is no install spec that downloads arbitrary code; the dependency is a named PyPI package (simmer-sdk) and the SKILL.md / clawhub.json point to a public GitHub repo. This is a normal install surface, but you should review the simmer-sdk source before supplying live credentials, as recommended in SKILL.md.

Credentials

The skill requires two high-value secrets: SIMMER_API_KEY (trading authority) and SOLANA_PRIVATE_KEY (private key used to sign live Solana trades). Those are proportionate to the stated purpose of executing live trades, but they are sensitive and should only be provided after auditing both trader.py and the simmer-sdk. The bigger concern is the mismatch with the registry metadata (which claims no env vars required) — that discrepancy could lead a user to supply credentials without realizing they are needed. The skill also references optional env vars (TRADING_VENUE, AUTOMATON_MAX_BET) not listed in the top-level registry, which is minor but worth noting.

Persistence & Privilege

The skill is not marked always:true and autostart is false. The clawhub.json marks the script as an automaton-managed entrypoint, meaning it can be run by the agent, but default behavior is dry-run. Normal autonomous invocation is allowed by platform settings (disable-model-invocation: false). This combination is expected for a trading skill, but be aware that an agent could potentially invoke the skill with the '--live' flag if given permission, causing real trades.

What to consider before installing

Before installing or providing credentials, do the following: - Do not export your SOLANA_PRIVATE_KEY or SIMMER_API_KEY until you have audited the code and the simmer-sdk dependency. These are high-value secrets that can execute real trades. - The registry metadata omitted required env vars; treat that as a red flag and ask the publisher why the metadata and SKILL.md disagree. - Review the included trader.py and the simmer-sdk source (GitHub/PyPI) to confirm how the private key is used and whether keys are transmitted or only used locally for signing. - Test in dry-run/paper mode only. Only pass '--live' after you are confident and, preferably, with a minimal-balance account to limit potential loss. - Consider providing credentials via a secure secrets store (not raw environment variables) and restrict the API key's permissions if possible. - If you allow autonomous agent invocation, add a policy that prevents automatic live-mode trades (require manual confirmation for '--live'). If you want, I can: (1) scan the rest of trader.py for any code paths that send data to unexpected endpoints, (2) summarize where SOLANA_PRIVATE_KEY is used in the code, or (3) draft questions to ask the publisher about the metadata mismatch.

This is a template. The default signal uses a static dot plot to compute fair probabilities -- remix it with live SEP data, Fed funds futures, or OIS-implied rates. The skill handles all the plumbing (market discovery, trade execution, safeguards). Your agent provides the alpha.

Strategy Overview

The FOMC dot plot median implies a rate path for 2026. This skill computes fair probability of at least one rate cut (or hike) by each meeting date from the implied path, then trades when Kalshi market prices diverge from these fair values.

Key advantages:

• Dot plot is the Fed's own forecast -- strongest available signal for rate expectations
• Updated quarterly -- each SEP release provides fresh data
• Mean-reverting -- market prices tend to converge to dot-plot-implied probabilities between meetings

Signal Logic

Dot Plot to Fair Probability

1. Load FOMC dot plot median rate path (updated after each SEP)
2. Compute implied cuts from current rate to each quarterly endpoint
3. Map cut count to probability of "at least one cut" by each meeting
4. Compare fair probability to Kalshi market price
5. Trade when |fair - market| >= entry_edge

Conviction-Based Sizing

• conviction = min(|edge| / entry_edge, 2.0) / 2.0
• size = max($1.00, conviction * MAX_POSITION_USD)
• Larger edge = larger position, capped at MAX_POSITION_USD

Risk Parameters

Parameter	Default	Notes
Entry edge	10%	Min fair-vs-market divergence to trade
Exit threshold	45%	Sell when position price reaches this
Max position size	$5.00 USDC	Per market
Max trades per run	3	Rate limiting
Max slippage	15%	Skip if slippage exceeds
Min liquidity	$0	Disabled by default

Installation & Setup

clawhub install kalshi-fed-dot-plot-trader

Requires: SIMMER_API_KEY and SOLANA_PRIVATE_KEY environment variables.

Cron Schedule

Cron is set to null -- the skill does not run on a schedule until you configure it in the Simmer UI.

Safety & Execution Mode

The skill defaults to dry-run mode. Real trades only execute when --live is passed explicitly.

Scenario	Mode	Financial risk
python trader.py	Dry run	None
Cron / automaton	Dry run	None
python trader.py --live	Live (Kalshi via DFlow)	Real USDC

Required Credentials

Variable	Required	Notes
SIMMER_API_KEY	Yes	Trading authority. Treat as a high-value credential.
SOLANA_PRIVATE_KEY	Yes	Base58-encoded Solana private key for live trading.

Tunables (Risk Parameters)

Variable	Default	Purpose
SIMMER_FED_DOT_ENTRY_EDGE	0.10	Min divergence to trigger trade
SIMMER_FED_DOT_EXIT_THRESHOLD	0.45	Sell position when price reaches this level
SIMMER_FED_DOT_MAX_POSITION_USD	5.00	Max USDC per trade
SIMMER_FED_DOT_MAX_TRADES_PER_RUN	3	Max trades per execution cycle
SIMMER_FED_DOT_SLIPPAGE_MAX	0.15	Max slippage before skipping trade
SIMMER_FED_DOT_MIN_LIQUIDITY	0	Min market liquidity USD (0 = disabled)

Dependency

simmer-sdk is published on PyPI by Simmer Markets.

• PyPI: https://pypi.org/project/simmer-sdk/
• GitHub: https://github.com/SpartanLabsXyz/simmer-sdk
• Publisher: [e-mail]

Review the source before providing live credentials if you require full auditability.