What is xfuel-swarm-coordinate?

An on-chain workflow for coordinating up to 18 software agents around one shared task, with TFUEL held in an escrow pool. Agents join, get paid after their contributions are settled with zero-knowledge proofs, and any remaining funds return when the swarm ends.

Forming an agent group, registering members, funding the group, settling each member's payment, and dissolving the group with a refund of unused escrow.

It organizes shared work and payment in one defined process, so the coordinator does not have to track agent participation and payouts manually.

xfuel-swarm-coordinate — Skill for Claude Code and Codex by XFuel-Lab

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 XFuel-Lab/xfuel-protocol --skill xfuel-swarm-coordinate

Clone the repo

git clone --depth 1 https://github.com/XFuel-Lab/xfuel-protocol

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-swarm-coordinate/github.svg)](https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-swarm-coordinate)

Your own site

<a href="https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-swarm-coordinate"><img src="https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-swarm-coordinate/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-swarm-coordinate"><img src="https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-swarm-coordinate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,075 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00125	$0.02075
Opus 5.5	$0.00050	$0.00830
Sonnet 5.5	$0.00025	$0.00415
Haiku 4.5	$0.00013	$0.00208

Measured 2mo ago against content hash 366b6e977cae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

xfuel-swarm-coordinate 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 2mo ago.

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.

packages/agent-skills/xfuel-swarm-coordinate/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

XFuel: Swarm Coordination

Coordinate a group of agents working toward one objective. A coordinator forms a swarm and funds a TFUEL escrow pool; members join; each member's contribution is settled from the pool with a ZK proof; leftover escrow refunds to the coordinator on dissolve. All swarm calls live on A2ACircuit; this skill builds the calldata (via xfuel-sdk/onchain) and submits through the server relayer or hands you signed-out-of-band calldata. Skills never hold keys.

Lifecycle & phases

                 formSwarm            joinSwarm (×N)       settleSwarmAgent (×N)     dissolveSwarm
 registerAgent ─────────────► Forming ───────────► Active ───────────────► Settling ──────────► Dissolved
 (coordinator                 (escrow                (first join           (first settle         (refund
  + each member)               funded)                flips Active)         flips Settling)       remaining)

Phase	Meaning
`Forming`	Created, escrow funded, coordinator is member #1. Members may join.
`Active`	≥1 other member joined. Members may still join (until full) and settlements can begin.
`Settling`	First `settleSwarmAgent` has paid out; members can still be settled.
`Dissolved`	Coordinator/admin dissolved (or timed-out force-dissolve). Remaining escrow refunded.

Prerequisites

XFUEL_API_URL, XFUEL_API_KEY.
A2A_CIRCUIT_ADDRESS configured on the server (relayer submits, or the skill returns calldata). For on-chain reads (getSwarm), a Theta RPC URL.
Coordinator and every member must be registered active agents (registerAgent) before forming/joining.

Constraints & fees

Max size: 18 members (MAX_SWARM_SIZE). maxMembers must be 1..18.
Escrow: formSwarm requires msg.value > 0 (TFUEL, in wei).
Fee: swarmFeeBps = 30 (0.3%) taken on each member settlement and on the dissolve refund; routed to the fee collector.
Settlement auth: settleSwarmAgent is RELAYER_ROLE-gated → performed by the server relayer/admin, not arbitrary agents.
swarmId is chain-derived: keccak256(CIRCUIT_ID, coordinator, objectiveHash, swarmCount) — read it from the SwarmFormed event / tx receipt, then share it with members out of band.

Read the full file on GitHub · 163 lines

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.

2mo ago First seen · 163 lines · 125 tokens per session scan A 366b6e977cae

Subscribe to this mod's changes

xfuel-swarm-coordinate is a skill published in the GitHub repository XFuel-Lab/xfuel-protocol (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 125 tokens to every session and 2,075 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.

Building agents Web3 and blockchain ai-agents mcp model-context-protocol theta x402 zk-proofs

xfuel-swarm-coordinate next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
xfuel-swarm-coordinateXFuel-Lab/xfuel-protocol	Skill	1	2mo ago	Apache-2.0	A	125	Claude Code, Codex
agoragentic-interchange-inspectorrhein1/agoragentic-integrations	Skill	41	16d ago	MIT	A	62	Cursor
x402-paymentsANAMIZED/OpenMesha	Skill	1	2mo ago	none	A	39	Claude Code, Codex
okx-cex-earnokx/agent-trade-kit	Skill	501	4d ago	MIT	A	274	Claude Code, Codex
blockrunBlockRunAI/blockrun-mcp	Skill	389	yesterday	MIT	A	244	Claude Code
surfBlockRunAI/blockrun-mcp	Skill	389	yesterday	MIT	A	110	Claude Code, Codex
vulnhunter-solanamtarcure/claude-vibe-squad	Skill	228	9d ago	MIT	A	68	Claude Code, Codex