chainlink-oracle

chainlink-oracle is a skill for Claude Code, Codex from tenzro/tenzro-network. It costs 61 tokens per session (1,567 once invoked), scanned A, original, Apache-2.0.

A set of tools for Chainlink, a blockchain service that provides data, messaging, randomness, and automated actions to smart contracts. It covers cross-chain transfers, price data, fast market data, verifiable randomness, reserve checks, automation, and Functions subscriptions.

In plain words
What is it for?
Use it to send messages or tokens between blockchains, read market data, request provably fair random values, check reserves, manage automated tasks, and work with Functions subscriptions.
Why use it?
It puts several Chainlink services behind one agent-accessible connection instead of requiring separate manual integrations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to send messages or tokens between blockchains, read market data, request provably fair random values, check reserves, manage automated tasks, and work with Functions subscriptions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tenzro/tenzro-network/chainlink-oracle
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.

Any agent
npx skills add tenzro/tenzro-network --skill chainlink-oracle
Clone the repo
git clone --depth 1 https://github.com/tenzro/tenzro-network

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for chainlink-oracle

README.md
[![agentmods](https://agentmods.dev/badge/skills/tenzro/tenzro-network/chainlink-oracle/github.svg)](https://agentmods.dev/skills/tenzro/tenzro-network/chainlink-oracle)
Your own site
<a href="https://agentmods.dev/skills/tenzro/tenzro-network/chainlink-oracle"><img src="https://agentmods.dev/badge/skills/tenzro/tenzro-network/chainlink-oracle/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.

agentmods 80×15 button for chainlink-oracle

Your own site · 80×15
<a href="https://agentmods.dev/skills/tenzro/tenzro-network/chainlink-oracle"><img src="https://agentmods.dev/badge/skills/tenzro/tenzro-network/chainlink-oracle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,567 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00061 $0.01567
Opus 5 $0.00030 $0.00783
Sonnet 5 $0.00012 $0.00313
Haiku 4.5 $0.00006 $0.00157

Measured 9d ago against content hash 11f782c2c78b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

chainlink-oracle 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 9d 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.

skills/chainlink-oracle/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The most complete Chainlink MCP server available. 20 tools covering the full Chainlink product surface: CCIP v1.6+ cross-chain messaging with token pools and allowOutOfOrderExecution=true, on-chain Data Feeds via AggregatorV3, sub-second Data Streams, VRF v2.5 verifiable randomness, Proof of Reserve verification, Automation upkeeps, and Functions subscriptions.

MCP Endpoint

Service URL Description
Chainlink MCP https://chainlink-mcp.tenzro.xyz/mcp Chainlink MCP Server (port 3007)

For local development, use http://localhost:3007/mcp.

Key Concepts

  • CCIP — Cross-Chain Interoperability Protocol for secure messaging and token transfers
  • Router — Per-chain CCIP entry point contract
  • Chain Selector — uint64 identifier for each chain in CCIP
  • Token Pool — CCIP v1.6+ Lock/Release or Burn/Mint pool for cross-chain tokens (CCT)
  • Data Feeds — On-chain price oracles via AggregatorV3Interface (~1 min updates)
  • Data Streams — Off-chain sub-second latency market data (crypto, forex, equities, commodities)
  • VRF v2.5 — Verifiable Random Function for provably fair onchain randomness
  • Proof of Reserve — On-chain reserve verification for wrapped/synthetic assets
  • Automation — Decentralized keeper network for contract maintenance
  • Functions — DON-hosted serverless compute for off-chain data

Tools (21)

CCIP Cross-Chain (8 tools)

ccip_get_fee

Estimate CCIP messaging fee via Router.getFee() on-chain call.

ccip_send_message

Build Router.ccipSend() calldata with automatic fee estimation.

ccip_track_message

Track CCIP message delivery via OffRamp.getExecutionState().

ccip_get_supported_chains

List CCIP-supported chains from Chainlink REST API.

ccip_get_supported_tokens

List CCIP-supported tokens from Chainlink REST API.

ccip_get_lanes

Get available CCIP lanes (chain pairs).

ccip_get_token_pool

Get CCT token pool info — token address, owner, pool type (v1.5+).

Read the full file on GitHub · 152 lines

Files

What ships with it

1 file 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.

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. 9d ago First seen · 152 lines · 61 tokens per session scan A 11f782c2c78b

Subscribe to this mod's changes

chainlink-oracle is a skill published in the GitHub repository tenzro/tenzro-network (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,567 once invoked, about $0.0003 per session on Opus 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 2026-08-31.