CTRL

A skill for building automated workflows on Base, a blockchain network, such as recurring purchases, price-triggered swaps, launchpad purchases, or following large-wallet activity. The workflow runs after one wallet approval and uses preset spending limits.

In plain words
What is it for?
Creating capped recurring buys, price-based swaps, launchpad sniping, or whale-following workflows on Base mainnet.
Why use it?
It turns a described trading workflow into an on-chain automation setup, so the wallet does not need to approve every later execution.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/aaronjmars/aeon-agent/ctrl
Any agent
npx skills add aaronjmars/aeon-agent --skill ctrl
Clone the repo
git clone --depth 1 https://github.com/aaronjmars/aeon-agent

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00046 $0.02995
Opus 5 $0.00023 $0.01497
Sonnet 5 $0.00009 $0.00599
Haiku 4.5 $0.00005 $0.00299

Measured 2d ago against content hash 392baa3e2705, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CTRL 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 2d 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.

curl -m 10 -s "https://ctrl.build/api/mcp/block-catalog" \
skills/ctrl/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

${var} — Natural-language description of the workflow to build, e.g. DCA 0.005 ETH into USDC every week. Required. If empty, log CTRL_NO_INTENT and exit cleanly (no notify).

CTRL runs on Base mainnet only. It compiles a trigger → action graph into a V3 vault, the wallet signs once — an EIP-5792 batch deploys the vault and registers spending rules — and a Render-hosted keeper polls every ~5s and executes from there. The security boundary is the user's signature at activate-time, not an API key at create-time, so the create + read REST endpoints are anonymous. Activation requires a real wallet session, which the user provides by opening the CTRL activate landing page in their browser.

Read the last 2 days of memory/logs/ so a re-run can reference an existing workflow id instead of provisioning a new one.

Config

  • API root = https://ctrl.build/api/mcp. No key required for the endpoints used here.
  • Chain = Base mainnet (chainId 8453). Always send "chain": "base" and "network": "mainnet" — CTRL does NOT support Ethereum, Arbitrum, Solana, or any other chain. If the user asks for another chain, log CTRL_CHAIN_UNSUPPORTED and exit before creating anything.
  • Sensible defaults the agent should adopt if the user does not state them: per-swap ≤ 0.01 ETH, per-day ≤ 0.1 ETH, slippage ≤ 1% for stable-pair DCA, 15% only for launchpad sniping. Caps are signed at activate-time, never embedded in the workflow body.

Steps

1. Read the live block catalog

CTRL exposes 24 blocks across four categories (triggers, actions, conditions, utilities). Every key under each node's data.config MUST match a fields[].key in the catalog — invented keys are silently dropped by the keeper.

curl -m 10 -s "https://ctrl.build/api/mcp/block-catalog" \
  | jq '{
      triggers:   [.triggers[].id],
      actions:    [.actions[].id],
      conditions: [.conditions[].id],
      utilities:  [.utilities[].id]
    }'

Pick the trigger + action ids that match ${var}. The most common shapes:

Read the full file on GitHub · 227 lines

Changes

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.

  1. 2d ago First seen · 227 lines · 46 tokens per session scan A 392baa3e2705

Subscribe to this mod's changes

CTRL is a skill published in the GitHub repository aaronjmars/aeon-agent (11 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 2,995 once invoked, about $0.0002 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 2026-08-30.