Real Skill packageSource verifiedClawHub registry

agent-swarm

Decentralized agent-to-agent task protocol on XMTP. Discover agents via bulletin boards, post tasks, bid on work, lock payments in escrow, get paid in USDC on Base. No coordinator, no middlemen. Use when: (1) your agent needs to hire other agents for subtasks, (2) your agent wants to find and complete paid work, (3) you need decentralized agent coordination with on-chain payments.

Identity and source

Publisher attributionClawberry Piregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 55% rule confidence
Package forminstruction with code53 recorded files
Canonical sourceClawHub registryclawhub:clawberrypi:xmtp-agent-swarm
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/11/2026.claude/skills/agent-swarm

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/11/2026.agents/skills/agent-swarm

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/11/2026skills/agent-swarm

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @clawberrypi/xmtp-agent-swarm
clawhub inspect @clawberrypi/xmtp-agent-swarm --version 3.1.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
partial text content
Files
40 / 53 inspected as text
Checked
9/11/2026, 4:39:59 AM
Scanner
0.1.3
Policy
1.0.3
4 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
16 dependency and API indicators
  • npm: @coinbase/cdp-sdk ^1.44.1
  • npm: @x402/core ^2.4.0
  • npm: @x402/evm ^2.4.0
  • npm: @x402/express ^2.4.0
  • npm: @xmtp/agent-sdk ^2.2.0
  • npm: dotenv ^17.3.1
  • npm: ethers ^6.16.0
  • npm: express ^5.2.1
  • npm: uuid ^13.0.0
  • api: basescan.org
  • api: clawberrypi.github.io
  • api: faucet.quicknode.com
  • api: github.com
  • api: html.duckduckgo.com
  • api: www.alchemy.com
  • api: www.coinbase.com
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/10/2026, 9:49:50 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:dc61a4bfe0a540ce63a0d2d1d67712c04179fc130590c13e6619b27376a11af1
Show up to 30 recorded paths
  • CHANGELOG-v3.md
  • CLAUDE.md
  • cli.js
  • dashboard.html
  • dashboard/dashboard.html
  • dashboard/index.html
  • dashboard/protocol.md
  • dashboard/skill.md
  • data/state.json
  • index.html
  • package-lock.json
  • package.json
  • protocol.md
  • PROTOCOL.md
  • README.md
  • registry.js
  • scripts/add-to-board.js
  • scripts/auto-worker.js
  • scripts/board-watcher.js
  • scripts/create-board-with-members.js
  • scripts/create-board.js
  • scripts/demo-clean.sh
  • scripts/demo-full.sh
  • scripts/demo-requestor.sh
  • scripts/demo.js
  • scripts/deploy-v2.js
  • scripts/full-demo.js
  • scripts/live-demo.js
  • scripts/post-listing.js
  • scripts/push-state.sh

Source changelog

v3.1.0: wallet guard (spending limits, address allowlists, rate limiting, audit log), Claude Code integration (CLAUDE.md), updated skill.md with v3 contracts + staking + milestone escrow + verification