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 aaronjmars/aeon-agent --skill base-mcpgit clone --depth 1 https://github.com/aaronjmars/aeon-agentWrote 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/aaronjmars/aeon-agent/base-mcp)<a href="https://agentmods.dev/skills/aaronjmars/aeon-agent/base-mcp"><img src="https://agentmods.dev/badge/skills/aaronjmars/aeon-agent/base-mcp/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/aaronjmars/aeon-agent/base-mcp"><img src="https://agentmods.dev/badge/skills/aaronjmars/aeon-agent/base-mcp.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 | $0.00042 | $0.02369 |
| Opus 5.5 | $0.00017 | $0.00948 |
| Sonnet 5.5 | $0.00008 | $0.00474 |
| Haiku 4.5 | $0.00004 | $0.00237 |
Grade A, and why
base-mcp 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 19d 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.
This is a copy
100% identical to base-mcp — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Base MCP
${var} - empty = wallet snapshot (address, portfolio, last 7 days of activity).
history[:N]= last N transactions (default 10). Anything else = a read-only question about the account, answered from the MCP reads. Never sends, swaps, signs, pays, or batches on an Aeon run.
Aeon runs (scheduled or dispatched)
The rest of this file is Base's upstream skill, written for a live chat. An Aeon run has no user to talk to, so these rules override it:
- Skip onboarding. No capability intro, no disclaimer, no "give me an action" reply. Go straight to the reads below. An empty
${var}is the task, not a missing one. - Fetch the wallet address and balances up front. The upstream "only when the user asks" rule does not apply: the snapshot needs them.
- Read-only. Call only read tools (address, portfolio/balances, transaction history,
web_requestGETs for plugin data). Do not call any tool that sends, swaps, signs, pays (x402), or batches, even if${var}asks for it - nobody is present to approve it. Refuse that request in the notify and say to run it from a chat surface instead. - Every figure traces to a tool response. Never estimate balances or values.
1. Read
Call the Base MCP tools (mcp__base__*; discover them from the server, don't assume names) for:
- wallet address
- portfolio: each token (symbol, amount, USD value), total USD value
- transaction history: last 7 days (empty var) or last N (
history[:N]), with date, type, token, amount, counterparty
For a free-form ${var} question, make only the reads that answer it.
If no mcp__base__* tool is callable, the server is not connected (or MCP_BASE_TOKEN is missing and the workflow skipped MCP with a ::warning::). Report BASE_MCP_NOT_CONNECTED, notify once pointing the operator at the dashboard MCP tab, and stop. If tools return 401/invalid-token, report BASE_MCP_AUTH_STALE and ask the operator to reconnect. Don't retry the same call more than twice.
2. Compare
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- plugins/aerodrome.md 11 KB
- plugins/avantis.md 37 KB
- plugins/bankr.md 11 KB
- plugins/moonwell.md 5.7 KB
- plugins/morpho.md 8.0 KB
- plugins/uniswap.md 14 KB
- plugins/virtuals.md 12 KB
- README.md 4.1 KB
- references/approval-mode.md 2.9 KB
- references/batch-calls.md 1.9 KB
- references/custom-plugins.md 5.3 KB
- references/install.md 4.2 KB
- references/tone.md 1.9 KB
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.
- 19d ago Changed · +54 lines 07da07db8cc4
- 1mo ago First seen · 88 lines · 42 tokens per session scan A e5ebef132a4e
base-mcp is a skill published in the GitHub repository aaronjmars/aeon-agent (12 stars, last pushed 9d ago), licensed MIT. It adds 42 tokens to every session and 2,369 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to base-mcp, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
strategy-spec
Generates a backtestable, regime-gated mean-reversion TRADING STRATEGY SPEC for a BSC / PancakeSwap token using CoinMarketCap x402 DEX data — and decides what data is even worth paying for first (honest free-vs-paid routing). Produces rules + parameters + a 180-day backtest with a buy-and-hold benchmark. A strategy…
clicks-protocol
Integrate Clicks Protocol settlement routing into AI agent projects on Base. Use when building agents that hold, earn, receive, or transfer USDC, when asked about agent treasury management, x402 payment settlement, idle USDC routing, or agent referral attribution.
alien-plugg-x402
38 paid x402 API endpoints for AI agents — Zora crypto analysis, Robinhood Chain tokenized stocks, on-chain intelligence, whale tracking, and utilities. MCP-compatible. Flat $0.003/call via USDC micropayments on Base.
agentpay-session
Cap and receipt an AI agent's spending. Open a budget-capped AgentPay session so paid tool/API calls stay under a hard USDC limit and each produces a verifiable receipt + a running ledger. Use when enforcing a spend cap across calls, tracking what an agent spent, or producing an audit trail for autonomous payments.…
stipend
A non-custodial USDC wallet on Base that an AI agent installs by itself, with spending limits enforced in the signing path rather than in a prompt. Receive payments, pay HTTP 402 / x402 charges automatically, and answer whether you are worth running. No account, no API key, no human needed to install or to be paid.
ai-work-market
Use when an AI agent needs to receive USDC payment for work that takes more than one minute — market research, code review, translations, dataset annotation, logo design. The buyer escrows USDC, the seller delivers proof, the buyer releases or disputes. Use for work contracts, NOT for atomic sub-minute pay-per-call…