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 araxis33/aero-vote-radar --skill aero-vote-radargit clone --depth 1 https://github.com/araxis33/aero-vote-radarWrote 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/araxis33/aero-vote-radar/aero-vote-radar)<a href="https://agentmods.dev/skills/araxis33/aero-vote-radar/aero-vote-radar"><img src="https://agentmods.dev/badge/skills/araxis33/aero-vote-radar/aero-vote-radar/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/araxis33/aero-vote-radar/aero-vote-radar"><img src="https://agentmods.dev/badge/skills/araxis33/aero-vote-radar/aero-vote-radar.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 | $0.00097 | $0.01016 |
| Opus 5.5 | $0.00039 | $0.00406 |
| Sonnet 5.5 | $0.00019 | $0.00203 |
| Haiku 4.5 | $0.00010 | $0.00102 |
Grade A, and why
aero-vote-radar 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 21d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aero-vote-radar
Aerodrome pays each week's bribes and trading fees to whoever voted for that pool, split by weight. So the question is never "which pool has the highest APR" — it is "which pool pays best per veAERO, after my own vote dilutes it". This tool answers that from live on-chain data and hands back whole percentages that Aerodrome's voting UI accepts.
Every number comes from Aerodrome's own Sugar and Voter contracts plus DefiLlama prices. No API keys, no backend, no database, no wallet connection.
Start here
If the person has an address, run review first. It scores the vote they
already cast against the epoch that has closed, so every figure can be checked
against their own wallet. Nothing is predicted, so nothing has to be believed —
and it is the fastest way to find out whether they vote at all.
npx aero-vote-radar review --address 0x... # what last Thursday actually paid
npx aero-vote-radar my-veaero 0x... # their locks and voting power
Then the recommendation:
npx aero-vote-radar recommend --address 0x... --vote-ready
npx aero-vote-radar recommend --veaero 25000 --vote-ready --min-consistency 0.5
npx aero-vote-radar backtest --veaero 25000 --epochs 5
--vote-ready prints whole percentages summing to exactly 100. Rounding each
weight independently tends to total 101% or 102% and leaves the person fudging
the last row by hand.
Add --json to any command for machine-readable output.
As an MCP server
npx aero-vote-radar-mcp
Tools: list_pool_efficiency, recommend_allocation, backtest_strategy,
get_my_veaero, prepare_vote_calldata.
prepare_vote_calldata returns an unsigned Voter.vote transaction. It
never asks for a key and cannot send anything.
Things to get right
A vote expires. It only counts toward the epoch it is cast in, and epochs
flip Thursday 00:00 UTC. Always say how long is left — recommend prints it.
Don't chase the top row. A pool showing a four-figure "edge" on low
consistency is one large one-off bribe, not a repeatable weekly opportunity.
--min-consistency 0.5 filters that class out; pass the same value to
backtest so the backtest tests the strategy actually being run.
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.
- 21d ago First seen · 93 lines · 97 tokens per session scan A 6627d86f8a61
aero-vote-radar is a skill published in the GitHub repository araxis33/aero-vote-radar (2 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,016 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 2026-09-16.
Other skills, from other repositories
defi-protocols
DeFi protocol authority — flashloans, AMM design, lending markets, concentrated liquidity, MEV, triangular and cross-DEX arbitrage, stablecoin depeg dynamics, and on-chain capital routing across Uniswap V3, Aerodrome, Balancer, Curve, and Aave V3 on Ethereum, Base, Arbitrum, Optimism, and Polygon.
Aerodrome Slipstream
Swap tokens and manage concentrated liquidity positions on Aerodrome Slipstream (CLMM) on Base. Trigger phrases: aerodrome swap, aerodrome liquidity, aerodrome slipstream, add liquidity aerodrome, remove liquidity aerodrome, aerodrome position, aerodrome CL pool, concentrated liquidity base.
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.
base-l2-agent-kit
MCP server providing Base L2 DeFi tools for AI agents.
token-launcher
Revenue infrastructure for autonomous AI agents on Base. Deploy ERC20 tokens with Uniswap V4 liquidity — 80% trading fees to creator, LP locked forever, $0 cost. 148 tokens live. Own contracts (no Clanker dependency). Direct blockchain calls = zero downtime. CLI, MCP server, or smart contract.
pump-swarm
Coordinated multi-wallet trading on Pump.fun.