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 smartcontractkit/chainlink-agent-skills --skill chainlink-vrf-skillgit clone --depth 1 https://github.com/smartcontractkit/chainlink-agent-skillsWrote 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/smartcontractkit/chainlink-agent-skills/chainlink-vrf-skill)<a href="https://agentmods.dev/skills/smartcontractkit/chainlink-agent-skills/chainlink-vrf-skill"><img src="https://agentmods.dev/badge/skills/smartcontractkit/chainlink-agent-skills/chainlink-vrf-skill.svg" alt="Measured on agentmods" 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 | $0.00117 | $0.02455 |
| Opus 5 | $0.00059 | $0.01228 |
| Sonnet 5 | $0.00023 | $0.00491 |
| Haiku 4.5 | $0.00012 | $0.00246 |
Grade A, and why
chainlink-vrf-skill 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 7d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chainlink VRF Skill
Overview
Route VRF requests to the simplest valid path while keeping side effects and credential exposure out of the agent runtime. Generate working VRF v2.5 code on first attempt when possible. Detect legacy V1/V2 patterns and refuse to emit them — offer migration guidance instead.
Progressive Disclosure
- Keep this file as the default guide.
- Read references/subscription.md only when the user wants to build a subscription-based consumer, manage a subscription, use
VRFConsumerBaseV2Plus, callrequestRandomWords, or handle thefulfillRandomWordscallback. 2a. Read templates/starter-kit/README.md and the files in templates/starter-kit when the user asks for a working example project, Foundry starter kit, runnable VRF example, or says something like "give me a working VRF project I can build and test." Use this starter-kit template instead of inventing project scaffolding. - Read references/direct-funding.md only when the user wants direct funding (no subscription), uses
VRFV2PlusWrapperConsumerBase, or asks about a one-off randomness request. - Read references/migration-from-v2.md when you detect V1 or V2 patterns in user-supplied code (
VRFConsumerBaseV2,VRFConsumerBase, positionalrequestRandomWords,uint64subscription IDs,VRFV2WrapperConsumerBase, ormemoryrandomWords in a subscription consumer) or when the user asks how to migrate. - Read references/billing.md only when the user asks about costs, LINK vs native payment, subscription funding, or premium percentages.
- Read references/supported-networks.md only when the user needs coordinator addresses, wrapper addresses, LINK token addresses, or key hashes for a specific network.
- Read references/security-and-best-practices.md only when the agent is developing consumer contracts with this skill and when the user asks about security, bias resistance, gas limit sizing, request cancellation, or production readiness.
- Read references/official-sources.md only when the answer depends on live data the reference files do not contain.
- Do not load reference files speculatively.
What ships with it
16 files 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.
- agents/openai.yaml 232 B
- assets/chainlink-icon.png 38 KB
- references/billing.md 5.1 KB
- references/direct-funding.md 7.1 KB
- references/migration-from-v2.md 6.5 KB
- references/official-sources.md 1.7 KB
- references/security-and-best-practices.md 6.9 KB
- references/subscription.md 7.8 KB
- references/supported-networks.md 7.1 KB
- templates/starter-kit/.gitignore 18 B
- templates/starter-kit/foundry.toml 97 B
- templates/starter-kit/README.md 5.3 KB
- templates/starter-kit/remappings.txt 130 B
- templates/starter-kit/script/VRFConsumerV2Plus.s.sol 2.4 KB
- templates/starter-kit/src/VRFConsumerV2Plus.sol 4.9 KB
- templates/starter-kit/test/VRFConsumerV2Plus.t.sol 2.4 KB
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.
- 7d ago First seen · 114 lines · 117 tokens per session scan A 39a77be5bf2e
chainlink-vrf-skill is a skill published in the GitHub repository smartcontractkit/chainlink-agent-skills (126 stars, last pushed 2d ago), licensed MIT. It adds 117 tokens to every session and 2,455 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
web3-fullstack-packaged-build
Systematic full-stack Web3 build with mandatory packaging and delivery phase.
web3-fullstack-systematic-build
Systematic approach to building full-stack Web3 applications layer by layer.
solana-dev
Use when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "fuzz my Solana program", "deploy to devnet", "send a v1 transaction", "support larger transactions", "fix maxSupportedTransactionVersion", or "explain…
devtools-event-client
Create typed EventClient for a library. Define event maps with typed payloads, pluginId auto-prepend namespacing, emit()/on()/onAll()/onAllPluginEvents() API. Connection lifecycle (5 retries, 300ms), event queuing, enabled/disabled state, SSR fallbacks, singleton pattern. Unique pluginId requirement to avoid event…
walkeros-create-destination
Use when creating a new walkerOS destination to send events to a vendor or API (GA4/gtag, Meta/Facebook Pixel, Mixpanel, Amplitude, a custom HTTP API, Measurement Protocol), web or server-side. Example-driven workflow: research the vendor SDK and define step examples before implementing the destination interface, env…
walkeros-create-source
Use when creating a new walkerOS source to capture events (browser source, dataLayer interception, server/HTTP source, webhook receiver, event capture), web or server-side. Example-driven workflow: research the input format and define step examples before implementing the push interface, createTrigger, and env pattern.