Trade-Audit — Mandatory Audit Gate for Trading & Transfer Decisions

When to use

This skill is designed for auditing financial decisions — buy, sell, swap, transfer, liquidity pool entry/exit, or any on-chain value movement. The user may ask you to run it before executing a trade or transfer, or to always use it as a pre-check for financial actions.

What this skill does

Takes agent-prepared decision material and sends it to the Apus deterministic inference API running on an NVIDIA H100 TEE. Returns a structured, hardware-attested decision packet with:

• Bundle Hash — SHA-256 of the normalized decision material
• Output Hash — SHA-256 of the model's structured decision packet
• TEE Nonce — hardware attestation for that specific run
• Verdict — APPROVE / REJECT / WAIT
• Confidence — 1-100 integer, gated by --min-confidence (default 60)

Every run is logged to ~/.trade-audit/audit.jsonl.

No wallet or API key required. This skill only reads public data and calls the Apus inference API. It does not execute any transactions.

Important boundary:

The script is at {baseDir}/analyze.py.

• The agent collects the page contents, address information, pool details, rules, and relevant facts.
• The agent organizes that material into either a text/markdown file or a JSON decision bundle.
• This script does not fetch pages or explorer data itself.
• Reuse the bundled templates when preparing inputs:
  • Markdown template: {baseDir}/templates/prepared-decision-template.md
  • JSON template: {baseDir}/templates/prepared-bundle-template.json

Step 1 — Prepare the decision material

The audit model (gemma-3-27b-it) performs best with concise, focused inputs. The agent MUST distill raw data into core decision points before submitting.

Data preparation rules:

• Extract only: prices, thresholds, numeric values, rules/conditions, addresses, risk factors
• Strip out: page chrome, disclaimers, marketing text, navigation, repeated boilerplate
• Keep material under 4,000 characters when possible (warning at 4k, hard truncation at 12k)
• Each fact should be one short bullet — no paragraphs
• If a page has 50 data points, pick the 5-10 that directly affect the decision

Create one of these:

1. A text or markdown file containing the organized facts.
2. A JSON bundle containing the organized facts plus decision_goal.

For example, a prepared text file might contain:

Page: https://polymarket.com/event/what-price-will-bitcoin-hit-before-2027
Decision goal: Decide whether there is a justified BTC buy level from this market page.

Collected facts:
- Market title: What price will Bitcoin hit before 2027
- Threshold ladder excerpt:
  - Below 55,000: Yes 74c / No 27c
  - Below 50,000: Yes 61c / No 40c
- Rules:
  - Market resolves yes if Binance BTC/USDT trades at or below the threshold in the specified window.
- Observation:
  - 55,000 is the strongest downside threshold shown in the collected page notes.