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/destiner/faucet-mcp/agents-mdgit clone --depth 1 https://github.com/Destiner/faucet-mcpWrote 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/destiner/faucet-mcp/agents-md)<a href="https://agentmods.dev/instructions/destiner/faucet-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/destiner/faucet-mcp/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 | $0.01721 | $0.01721 |
| Opus 5 | $0.00860 | $0.00860 |
| Sonnet 5 | $0.00344 | $0.00344 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
faucet-mcp AGENTS.md 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 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.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Faucet
MCP server that lets a coding agent request small amounts of ETH/WETH/USDC/USDT from a personal hot wallet, with safety rails so a misbehaving agent can't drain it.
Motivation
Agent work on smart wallet flows constantly needs small dev funds: top up a fresh smart account, fund a session key, seed a test on a new chain. Public faucets are unreliable and rate-limited; topping up by hand is friction. This is a self-hosted faucet over MCP that the agent can call directly, behind tight per-call and 24h budgets so "i just spent all your money" is not a possible outcome.
Threat model is agent stupidity, not malice or prompt injection — if someone can get arbitrary code execution, the funding key in .env is the cheaper attack anyway. The caps exist to protect against the agent doing dumb things while you're not watching.
Design
Two-layer caps, scoped by (chain class, token pool):
- Soft caps — enforced unconditionally; first line of defense.
- Hard caps (10× soft) — enforced unconditionally and not bypassable, even with a valid approval code.
When a request exceeds the soft cap but is under the hard cap, the call returns NEEDS_APPROVAL. The agent asks the user for a 6-digit TOTP code (stored in 1Password / Apple Passwords as a verification code). The agent retries with code=...; on valid code the transfer goes through. Codes are single-use within a 90s replay window.
Pools
Limits are per pool, not per token:
STABLE: USDC + USDT share one windowETHWETH: ETH + WETH share one window
So 0.5 USDC and 0.5 USDT in the same 24h count as 1.0 against the stable window.
Caps
| Chain class | Pool | Soft/call | Soft 24h | Hard/call | Hard 24h |
|---|---|---|---|---|---|
| mainnet | stable | 0.10 | 1.0 | 1.0 | 10.0 |
| mainnet | eth | 0.00002 | 0.0005 | 0.0002 | 0.005 |
| testnet | stable | 2 | 20 | 20 | 200 |
| testnet | eth | 0.001 | 0.01 | 0.01 | 0.1 |
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 · 127 lines · 1,721 tokens per session scan A 7d69b7aa47ca
faucet-mcp AGENTS.md is an instructions file published in the GitHub repository Destiner/faucet-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 1,721 tokens to every session, about $0.0086 per session on Opus 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.
Other instructions, from other repositories
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
plamen CLAUDE.md
Claude Code instructions for PlamenTSV/plamen, covering plamen — security auditor, execution model, reference files and shared.
experiencer CLAUDE.md
Claude Code instructions for vincentlaucsb/experiencer: The canonical repository instructions are in AGENTS.md. Read and follow that file; this compatibility entrypoint intentionally defines no independent rules.
pip-web CLAUDE.md
Claude Code instructions for playpip/pip-web, covering claude.md — agent guide for pip, read first (by task), the three layers (respect the boundaries), non-negotiables and commands / definition of done.
kya-hub AGENTS.md
AGENTS.md instructions for UMBRAXON/kya-hub, covering agents.md — instructions for ai agents, 1. what kya-hub is, in one paragraph, 2. should you integrate?, 3. quickstart for an llm agent and 4. signing rules — the part that breaks everyone.
bitcoin-mcp copilot-instructions.md
Instructions for Bortlesboat/bitcoin-mcp, covering bitcoin-mcp copilot instructions, rules, satoshi api reference and verification.