Add AgentFlow skill — screen Base wallets for wash/sybil before transacting#128
Open
leonidahqadmin-cell wants to merge 1 commit into
Open
Add AgentFlow skill — screen Base wallets for wash/sybil before transacting#128leonidahqadmin-cell wants to merge 1 commit into
leonidahqadmin-cell wants to merge 1 commit into
Conversation
Collaborator
🟡 Heimdall Review Status
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this adds
A new skill —
skills/agentflow/SKILL.md— the safety layer for the onchain agent kit. Before an agent transacts with, trades against, pays, or trusts an unknown Base wallet, it screens the counterparty for wash-trading / sybil behavior and gets back a calibrated sybil score (0–100) + confidence + the reasons, from real on-chain Base USDC flow.Why it fits
The current skills let agents transact / trade / lend / mint / buy — but there's no "is this counterparty actually safe?" step. This fills that gap. It pairs with the existing skills: screen first, then act.
How it works
/public/wash-demo, rate-limited) for zero-setup trials/v1/wash, $0.01/call) settles in USDC via x402 — the agent pays directly, no signupHappy to adjust format/placement to match the repo's conventions.