What makes Agentic Lending Evk notable?

1.5K downloads. Trust evidence available

How should Agentic Lending Evk be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Agentic Lending Evk

Plan and execute the current EVK-first agentic lending workflow for Api3-backed markets. Use when a user wants an agent to resolve the oracle route for selec...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.5k

Updated

Oct 10, 2026

Version

0.1.16

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.5K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.5K downloadsadoption · observed Oct 10, 2026
Latest release: 0.1.16release · observed Jun 11, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s176sa2svdwgks5ycz1yngewb184yand:agentic-lending-evk

Install using `clawhub skill install s176sa2svdwgks5ycz1yngewb184yand:agentic-lending-evk` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/daav3/agentic-lending-evk before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-daav3-agentic-lending-evk/snapshot"

Documentation

CLAWHUB

156,256 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: agentic-lending-evk
description: Plan and execute the current EVK-first agentic lending workflow for Api3-backed markets. Use when a user wants an agent to resolve the oracle route for selected collateral and borrow assets, discover or fund the required Api3 feeds, including browser-assisted Api3 Market funding when needed, prepare the Euler oracle path, assemble and deploy the EVK lending market, and then prove real borrowability with a post-deploy canary borrow against the intended collateral path. This variant can reach real onchain writes, including feed funding, market deployment, approvals, swaps, and borrow canaries when explicitly allowed. Default to plan, simulation, or preview mode first, and only use live signer-backed execution when the user explicitly asks for it. Do not use for Morpho, unsupported recipes, or unsupported oracle/deployment routes.
metadata:
clawdis:
homepage: https://github.com/daav3/agentic-lending-project
author: daav3
requires:
bins:
- node
env:
- LIVE_SIGNER_ENV
config:
- request.run-evk-workflow.json
- borrow-proof-config.json
primaryEnv: LIVE_SIGNER_ENV
---

# Agentic Lending EVK

This is the execution-capable EVK workflow skill.

It turns the bundled EVK planner primitives into one agent-facing workflow, from route resolution and feed readiness through deployment and live borrow proof.

When the supported path is available and the user explicitly asks for it, this variant can send real transactions and should be treated as a guarded execution skill rather than a planning-only helper.

## Golden path for normal use
Use one request file and one wrapper command. Do not drop into lower-level commands unless debugging, intervention, or proof-specific follow-up is required.

1. Create `request.json` with exact `collateralAssets`, exact `borrowAssets`, chain, risk intent, feed-funding intent, and EVK deployment intent.
- For a live-shaped starting point, copy `references/live-request-template.json` and replace every placeholder before use.
2. Preflight before any live-capable EVK execution:

`agentic-lending-evk preflight-evk-workflow --input-file ./request.json --format json`

Stop unless `safeToRun === true`.
3. Run:

`agentic-lending-evk run-evk-workflow --input-file ./request.json --format json`

4. If the run was persisted, inspect or recover it with:
- `agentic-lending-evk explain-next --run-dir <run-dir> --format json`
- `agentic-lending-evk verify-evk-deployment-handoff --run-dir <run-dir> --format json`
- `agentic-lending-evk run-evk-workflow --resume-from-run-dir <run-dir> --input-file <run-dir>/request.json --format json`
5. If the user asked for borrowability proof, continue with the bundled proof executor only after the deployment bundle is reviewed.
6. Report full deployment success only from persisted artifacts and exact status fields, not from narrative text.

## Safety expectations
- default to planning

README.md

# Agentic Lending EVK

Execution-capable EVK skill bundle for Api3-backed lending workflows.

## Install + first command

```bash
npm install <this-package>
part2-planner run-evk-workflow --input-file ./node_modules/agentic-lending-evk/references/example-request.json
```

If you want a top-level entrypoint instead:

```bash
agentic-lending-evk run-evk-workflow --input-file ./node_modules/agentic-lending-evk/references/example-request.json
```

This published skill now carries its own runnable EVK execution surface instead of depending on a separate repo checkout for the planner runtime and core planning artifacts.

## Bundled contents

- packaged skill instructions in `SKILL.md`
- bundled live borrow proof executor in `scripts/evk_live_borrow_proof.js`
- local CLI entrypoint in `scripts/bin/agentic-lending-evk.js`
- bundled EVK planner runtime in `scripts/lib/`
- bundled planning data under `data/part2/`
  - `evk-addresses.api3-supported-overlap.json`
  - `feed-status.json`
  - `market-registry.json`
  - required contract artifacts for the current EVK path

## Published CLI commands

After installing this package, the published executables are:

- `agentic-lending-evk`
- `api3-feed-manager`
- `part2-planner`

## Quick examples

Top-level EVK workflow planning:

```bash
agentic-lending-evk run-evk-workflow --input-file ./request.json
```

Feed discovery or readiness work:

```bash
api3-feed-manager resolve --dapi-name ETH/USD --chain arbitrum --rpc-url https://arb1.arbitrum.io/rpc
api3-feed-manager ensure-active --dapi-name ETH/USD --chain arbitrum --rpc-url https://arb1.arbitrum.io/rpc
```

Lower-level planner entrypoint:

```bash
part2-planner plan-market --input-file ./node_modules/agentic-lending-evk/references/example-request.json
part2-planner prepare-evk-market --input-file ./node_modules/agentic-lending-evk/references/example-request.json
```

## Cold-install expectations

- Node.js `>=20`
- start from `references/example-request.json` and replace placeholder values or planning inputs as needed
- provide a live RPC URL for on-chain checks or transaction-oriented flows
- provide signer material only for explicitly user-approved send paths
- treat bundled planner snapshots as local packaged fallback inputs, not fresh chain truth

## Runtime note

The bundled `feed-status.json` and `market-registry.json` are packaged snapshots for local planning fallback, not global truth.

When live RPC or fresher operator-managed data is available, prefer that newer state over the bundled snapshot.

_meta.json

{
  "ownerId": "kn79961pqqa20q5jwn60zjkxzs84yc3w",
  "slug": "agentic-lending-evk",
  "version": "0.1.16",
  "publishedAt": 1781188191035
}

references/api_reference.md

# Agentic Lending EVK workflow reference

This skill wraps the bundled EVK-first planner workflow, then extends it into a post-deploy borrow proof step.

The important abstraction is the path, not the prior canaries:
1. normalize the selected collateral and borrow assets
2. resolve the oracle route for those assets
3. ensure or fund feeds on the deployable path
4. prepare and deploy the EVK market
5. prove borrowability separately when requested

## Command order

Prefer the workflow in this order unless the user only asked for a subset:

### Safety gate before live-capable use
1. `preflight-evk-workflow`
- use this before any request that might become `broadcast-ready`, `real-send`, or signer-backed feed funding
- it returns:
- `safeToRun`
- `liveTxRequested`
- `liveTxAllowed`
- `placeholderSafe`
- `preview.status`
- `blockers`
- `warnings`

### Preferred top-level entrypoint
2. `run-evk-workflow`
- use this when the user wants one input and one status or result object for the current EVK-first path
- the response shape is:
- `status`
- `phaseReached`
- `state`
- `recipeId`
- `deployable`
- `fundingExecutionState`
- `executable`
- `blockers`
- `warnings`
- `result`
- `planMarket`
- `ensureFeeds`
- `feedFunding`
- `prepareEulerOracle`
- `prepareEvkMarket`
- `prepareEvkDeployment`
- `deployEvkMarket`
- `artifactPersistence`
- if `artifacts.enabled === true`, the persisted run bundle also includes `summary.json`, `agent-decision.json`, and `rollback-plan.json`
- if the user wants proof of borrowability after deployment, treat that as the next workflow step inside this same skill

### Persisted-run helper commands
3. `explain-next`
- use this with `--run-dir` to recover the model-friendly state of a persisted run
- read it first when resuming or handing off a stored EVK run
4. `verify-evk-deployment-handoff`
- use this with `--run-dir` before claiming the persisted run is deployment-complete or ready for proof follow-up
5. `run-evk-workflow --resume-from-run-dir <dir>`
- use this to reopen a known run directory instead of reconstructing state from memory

### Manual staged order
1. `plan-market`
2. verify the route chosen for the selected assets
- prefer an exact direct route when available
- otherwise use a supported composed route when the planner can prove it cleanly
- prefer literal exact feed-name matches before alias-normalized fallback matches
3. `ensure-feeds`
4. if funding is needed and `fundingExecutionClassification.state === "executable"`:
- `purchase-inputs`
- `prepare-contract-call` or `prepare-buy-subscription`
- `execute-buy-subscription`
- `ensure-feeds` or `ensure-active` again
5. if funding is needed and `fundingExecutionClassification.state === "browser-assisted"`:
- `browser-plan`
- execute that plan with the browser t

references/arbitrum-eusdc1-isolated-example.json

{
  "chainLabel": "arbitrum",
  "rpcUrl": "https://arb1.arbitrum.io/rpc",
  "accountAddress": "0x000000000000000000000000000000000000dEaD",
  "signerEnvName": "LIVE_SIGNER_ENV",
  "operatorAck": "SET_REQUIRED_LIVE_SEND_ACKNOWLEDGEMENT_PHRASE",
  "tokens": {
    "wrappedNative": {
      "symbol": "WETH",
      "address": "0x82af49447d8a07e3bd95bd0d56f35241523fbab1",
      "decimals": 18
    },
    "borrowAsset": {
      "symbol": "WETH",
      "address": "0x82af49447d8a07e3bd95bd0d56f35241523fbab1",
      "decimals": 18
    },
    "collateralAsset": {
      "symbol": "USDC",
      "address": "0xaf88d065e77c8cC2239327C5EDb3A432268e5831",
      "decimals": 6
    }
  },
  "vaults": {
    "borrowVault": {
      "label": "eWETH-11",
      "address": "0x9dB604761a4664002629873f5985386904C3D5Fe"
    },
    "collateralVault": {
      "label": "eUSDC-1",
      "address": "0x0a1eCC5Fe8C9be3C809844fcBe615B46A869b899"
    },
    "disableCollateral": [
      {
        "label": "eWETH-1",
        "address": "0x78E3E051D32157AACD550fBB78458762d8f7edFF"
      }
    ]
  },
  "evc": {
    "address": "0x6302ef0F34100CDDFb5489fbcB6eE1AA95CD1066",
    "enableController": false,
    "controllersToDisable": []
  },
  "actions": {
    "repayExistingDebt": true,
    "depositFullCollateralBalance": true,
    "borrowAmount": "0.00005"
  },
  "repayTopUp": {
    "enabled": true,
    "mode": "wrap-native",
    "amount": "0.0002"
  },
  "repaySwap": {
    "enabled": false,
    "routerAddress": "0x68b3465833fb72A70ecDF485E0e4C7bD8665Fc45",
    "tokenIn": {
      "symbol": "WETH",
      "address": "0x82af49447d8a07e3bd95bd0d56f35241523fbab1",
      "decimals": 18,
      "isWrappedNative": true
    },
    "tokenOut": {
      "symbol": "WETH",
      "address": "0x82af49447d8a07e3bd95bd0d56f35241523fbab1",
      "decimals": 18
    },
    "fee": 100,
    "amountIn": "0",
    "amountOutMinimum": "0",
    "wrapNativeAmount": "0"
  },
  "collateralSwap": {
    "enabled": true,
    "routerAddress": "0x68b3465833fb72A70ecDF485E0e4C7bD8665Fc45",
    "tokenIn": {
      "symbol": "WETH",
      "address": "0x82af49447d8a07e3bd95bd0d56f35241523fbab1",
      "decimals": 18,
      "isWrappedNative": true
    },
    "tokenOut": {
      "symbol": "USDC",
      "address": "0xaf88d065e77c8cC2239327C5EDb3A432268e5831",
      "decimals": 6
    },
    "fee": 100,
    "amountIn": "0.0015",
    "amountOutMinimum": "0",
    "wrapNativeAmount": "0.0015"
  }
}

Github ReposUpdated 16h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.