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 agentmods add instructions/xfuel-lab/xfuel-protocol/agents-mdgit 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/instructions/xfuel-lab/xfuel-protocol/agents-md)<a href="https://agentmods.dev/instructions/xfuel-lab/xfuel-protocol/agents-md"><img src="https://agentmods.dev/badge/instructions/xfuel-lab/xfuel-protocol/agents-md.svg" alt="Measured on agentmods" 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 | $0.01075 | $0.01075 |
| Opus 5 | $0.00537 | $0.00537 |
| Sonnet 5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
xfuel-protocol AGENTS.md scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Windows: use `curl.exe` for raw HTTP — PowerShell `curl` is not real curl. How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XFuel — Agent Index
Entry point for agents and automation.
- docs/STRATEGY.md — company strategy (build-from source)
- docs/RUNTIME_STATE.md — as-deployed truth
- docs/POSITIONING.md — messaging
- WHITEPAPER.md — design
XFuel is the book. This agent spent Y on this job. You hold hub, model, and amount. Not a smart router. Not a model shop. POST /v1/chat/completions is $0.01 USDC on Base and Solana. GET|POST /v1/agents/:agent_id/book is possession-gated. Signed receipt is table stakes.
Beachhead: crypto-native agent teams — docs/BEACHHEAD_ICP.md.
Provider COGS floats: docs/PROVIDER_FLOAT_TREASURY.md · ADR 0005.
Pricing: docs/PRICING_STRATEGY.md · docs/SPEND_INTELLIGENCE_THESIS.md.
Mainnet USDC go-live: docs/MAINNET_X402_CHECKLIST.md.
Privacy thesis (Private Spend): docs/PRIVATE_SPEND_THESIS.md.
Design partners: docs/DESIGN_PARTNER_ONBOARDING.md.
Seed scaffold: docs/SEED_READINESS.md.
Try the demo
Public gateway: https://api.xfuel.app (demo key xfuel-demo, rate-limited). First hour is POST /v1/chat/completions — no wallet. Working copy: docs/DESIGN_PARTNER_ONBOARDING.md.
Windows: use curl.exe for raw HTTP — PowerShell curl is not real curl.
Status: GET /task-status?task_id=
OpenAI: POST /v1/chat/completions, GET /v1/models, GET /llms.txt
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.
- 4d ago First seen · 94 lines · 1,075 tokens per session scan A e9a9765216da
xfuel-protocol AGENTS.md is an instructions file published in the GitHub repository XFuel-Lab/xfuel-protocol (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,075 tokens to every session, about $0.0054 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
agoragentic-integrations AGENTS.md
AGENTS.md instructions for rhein1/agoragentic-integrations, covering agents.md, what this repository is, machine-readable index, repository structure and acp namespace rule.
agoragentic-integrations copilot-instructions.md
Copilot instructions for rhein1/agoragentic-integrations: This GitHub Copilot surface uses Agoragentic Skill Pack v2. For an Agoragentic request, load or read only the smallest matching skill before acting.
xenarch-mcp CLAUDE.md
Claude Code instructions for xenarch-ai/xenarch-mcp, covering xenarch-mcp, structure, stack, commands and design principle.
lithium-vault-mcp CLAUDE.md
Claude Code instructions for ciinkwia/lithium-vault-mcp, covering lithium-vault-mcp, why model a (and the seam to model c), the price-ceiling guard (important), tools and testing.
HyperXosist-Agent AGENTS.md
AGENTS.md instructions for KG-NINJA/HyperXosist-Agent, covering agents.md — hyperxosist agent, what this is, dual output, fast path (copy this) and a) tool-calling agents (openai / anthropic / grok / llama).
agoragentic-integrations GEMINI.md
Gemini CLI instructions for rhein1/agoragentic-integrations: This Gemini CLI surface uses Agoragentic Skill Pack v2. For an Agoragentic request, load or read only the smallest matching skill before acting.