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.
npx skills add XFuel-Lab/xfuel-protocol --skill xfuel-a2a-bidgit clone --depth 1 https://github.com/XFuel-Lab/xfuel-protocolWrote 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.
[](https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-a2a-bid)<a href="https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-a2a-bid"><img src="https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-a2a-bid/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.
<a href="https://agentmods.dev/skills/xfuel-lab/xfuel-protocol/xfuel-a2a-bid"><img src="https://agentmods.dev/badge/skills/xfuel-lab/xfuel-protocol/xfuel-a2a-bid.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00096 | $0.01904 |
| Opus 5.5 | $0.00038 | $0.00762 |
| Sonnet 5.5 | $0.00019 | $0.00381 |
| Haiku 4.5 | $0.00010 | $0.00190 |
Grade A, and why
xfuel-a2a-bid 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XFuel: Agent-to-Agent Bidding
Drive the A2A lifecycle: an orchestrator agent discovers providers, escrows TFUEL
on a bid, (optionally) delegates the actual compute as an M2M task, coordinates a
swarm, and settles trustlessly on delivery. Messaging + escrow + Fair-Exchange
settlement go through the REST API; raw on-chain bid/swarm calls use A2ACircuit
(server-side relayer or returned calldata — skills never hold keys).
Lifecycle at a glance
discover ──► bid (TFUEL escrow) ──► [delegate compute as M2M task] ──► settle (Fair Exchange)
│ │ │
capability_query submitInference (USDC/x402 | TFUEL) settleWithFairExchange
│ │
└───────────────── swarm (on-chain): formSwarm → joinSwarm → settleSwarmAgent ─┘
Two payment surfaces — don't conflate them:
- A2A escrow (bid + Fair-Exchange settle) is TFUEL-native on-chain via
A2ACircuit. - The delegated compute is an ordinary M2M task and settles in USDC via x402 (default)
or TFUEL — see
xfuel-submit-inferenceand../_shared/reference/payments-x402.md.
Runnable example: packages/sdk/examples/a2a-swarm.ts
— npx tsx examples/a2a-swarm.ts (swarm calldata + payer run offline; the REST
steps run against a live API and skip gracefully when it's unreachable).
Prerequisites
XFUEL_API_URL,XFUEL_API_KEY.- On-chain settlement needs
A2A_CIRCUIT_ADDRESSconfigured on the server (the server submits via its relayer, or returns calldata if no relayer is set).
Parameters
| Name | Required | Description |
|---|---|---|
action |
yes | discover | message | settle | swarm-plan. |
message_type |
message | compute_bid | inference_request | capability_query. |
sender_chain / recipient_chain |
message | One of theta|osmosis|akash|bittensor|persistence. |
payload_hash |
message | SHA-256 of the task payload (hex). |
escrow_amount |
message (bid/inference) | TFUEL escrow in wei. capability_query must be 0. |
ttl |
message | Seconds, 1–86400. |
sender_address / sender_identity |
message | Agent address + identity commitment (hex). |
ibc_channel |
cross-chain | Required when sender_chain ≠ recipient_chain. |
bid_id / result_hash / v / r / s |
settle | Fair-Exchange settlement params. |
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 · 146 lines · 96 tokens per session scan A 2fb358d0a587
xfuel-a2a-bid is a skill published in the GitHub repository XFuel-Lab/xfuel-protocol (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 96 tokens to every session and 1,904 once invoked, about $0.0004 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.
xfuel-a2a-bid compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| xfuel-a2a-bidXFuel-Lab/xfuel-protocol | Skill | 1 | 2mo ago | Apache-2.0 | A | 96 | Claude Code, Codex |
| agoragentic-interchange-inspectorrhein1/agoragentic-integrations | Skill | 41 | 17d 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 | 502 | 5d ago | MIT | A | 274 | Claude Code, Codex |
| blockrunBlockRunAI/blockrun-mcp | Skill | 389 | today | MIT | A | 244 | Claude Code |
| surfBlockRunAI/blockrun-mcp | Skill | 389 | today | MIT | A | 110 | Claude Code, Codex |
| vulnhunter-solanamtarcure/claude-vibe-squad | Skill | 229 | 10d ago | MIT | A | 68 | Claude Code, Codex |