agentleFS
EskyeeEskyee/agentbot-opensource/skills/aeon-defi-monitor/SKILL.md

aeon-defi-monitor

Skill17 starsChanged 5 months agoMITView on GitHub

Watchlist monitor for DeFi pools, lending markets, and vaults. Surfaces only changed entries — APR floor breached, utilization ceiling hit, TVL delta above threshold, health factor approaching liquidation, or position PnL crossed your alert. Bankr-ready Submit payload attached when an alert recommends action. Silent on quiet members. Triggers: "check my defi positions", "monitor these pools", "yield check on Aave/Compound", "is my LP underwater", "pool health for X".

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When an alert recommends action, output includes a ready-to-paste Submit payload:

    line 57
  2. Distinctive:

    Read-only by default. Execution requires explicit operator input.

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

aeon-defi-monitor

Tracks a configured list of DeFi entries — DEX pools, lending positions, vault deposits — and pings on meaningful change. Designed to pair with Bankr Submit so the operator can act directly on alerts.

Watchlist

protocols:
  - id: aerodrome-base
    type: dex
    pool_address: 0x...
    alert_apr_floor: 8.0
    alert_tvl_delta_pct: 20

  - id: aave-v3-base-usdc
    type: lending
    market_address: 0x...
    asset: USDC
    position_address: 0x...   # optional — your EOA / safe
    alert_util_ceiling: 85
    alert_health_factor: 1.3  # ping if borrow position approaches liquidation

  - id: pendle-arb-pt-eeth
    type: vault
    market_id: ...
    position_size_usd: 5000
    alert_implied_apy_floor: 12.0

Per-type checks

  • DEX — TVL + 24h delta, fee APR + incentive APR + emission token, slippage estimate on $1k swap.
  • Lending — total supplied / borrowed, utilization, supply + borrow APYs split by real vs incentive, health factor if a position is tracked.
  • Vault — TVL, implied APY (with what drives it), position value if tracked, withdrawal liquidity.

Alert triggers

APR drops below floor, utilization above ceiling, TVL delta above threshold, position PnL crossed threshold, health factor approaches 1.0, pool depegs > 1%, vault APY drops below floor. Health-factor alerts always fire when approaching 1.0 regardless of other thresholds.

Sources

DefiLlama (api.llama.fi + yields.llama.fi), on-chain via Bankr-compatible RPC / Quicknode / Alchemy. Position data sanity-checked vs on-chain state every run.

Bankr execution hook

When an alert recommends action, output includes a ready-to-paste Submit payload:

Submit: deposit 1000 USDC into aerodrome-base pool 0x... via Aerodrome router
Submit: withdraw position from aave-v3-base USDC market 0x...

Rules

  • Read-only by default. Execution requires explicit operator input.
  • Silent on unchanged.
  • Stale-data flag if last update > 1h old.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.