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-ace-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-ace-skill)<a href="https://agentmods.dev/skills/smartcontractkit/chainlink-agent-skills/chainlink-ace-skill"><img src="https://agentmods.dev/badge/skills/smartcontractkit/chainlink-agent-skills/chainlink-ace-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 | $0.00168 | $0.02661 |
| Opus 5 | $0.00084 | $0.01331 |
| Sonnet 5 | $0.00034 | $0.00532 |
| Haiku 4.5 | $0.00017 | $0.00266 |
Grade C, and why
chainlink-ace-skill scanned grade C with 2 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
2. Do not refuse mainnet or production questions solely because they involve ACE. Instead, call out production licensing, security review, and explicit approval requirements. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. If WebFetch is available, use it first. If it returns insufficient content, try `curl -L <official-url>`. How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chainlink ACE Skill
Overview
Help users build with Chainlink ACE. For open-source contract integration, treat the public smartcontractkit/chainlink-ace repository as the source of truth. For managed ACE Platform, Beta scope, product APIs, supported networks, and auditor/reporting workflows, treat official Chainlink ACE docs on docs.chain.link/ace as the source of truth and verify freshness when claims could have changed.
Progressive Disclosure
- Keep this file as the default guide.
- Read references/platform-and-beta.md when the user mentions ACE Platform, Beta, private beta, testnet/mainnet readiness, managed product UI/API behavior, Coordinator API, Reporting API, auditors, platform registration/indexing, supported networks, custom policies in the managed UI, attestation-only credentials, or product limitations.
- Read references/getting-started-and-scope.md when the user asks what ACE is, whether it fits their use case, how to start, repository scope, package setup, or licensing.
- Read references/onchain-contracts.md when the user mentions the
chainlink-aceGitHub repo, self-deployment, Foundry, audited contracts, custom policies/extractors/mappers, upgrade an existing contract, or BUSL/prod licensing. - Read references/architecture.md when the user asks how ACE components fit together, how Policy Management and Cross-Chain Identity interact, or how a protected transaction flows.
- Read references/policy-management.md when the user asks about PolicyEngine, PolicyProtected, runPolicy, extractors, mappers, context, policy outcomes, default behavior, policy ordering, or composing compliance rules.
- Read references/policy-library.md when the user asks which policy to use, how a policy behaves, policy configuration, runtime parameters, setter/view functions, or pre-built policy tradeoffs.
- Read references/cross-chain-identity.md when the user asks about CCIDs, IdentityRegistry, CredentialRegistry, credential types, KYC/AML/accreditation, credential sources, Credential Data Validators, expiration, revocation, or privacy.
- Read references/contracts-and-source.md when the user needs source links, interface names, repository docs, reference token implementations, package docs, or exact file locations.
- Read references/official-sources.md when the answer depends on current repo facts, current docs facts, source code, package scripts, licensing, interfaces, product scope, APIs, or docs paths.
- Read assets/ace-docs-index.md only when you need a map of public repository documentation covered by this skill.
- Do not load reference files speculatively.
What ships with it
12 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 256 B
- assets/ace-docs-index.md 4.2 KB
- assets/chainlink-icon.png 38 KB
- references/architecture.md 4.0 KB
- references/contracts-and-source.md 3.9 KB
- references/cross-chain-identity.md 5.7 KB
- references/getting-started-and-scope.md 5.3 KB
- references/official-sources.md 6.6 KB
- references/onchain-contracts.md 6.4 KB
- references/platform-and-beta.md 7.0 KB
- references/policy-library.md 8.0 KB
- references/policy-management.md 4.8 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 · 120 lines · 168 tokens per session scan C d97b5a6b3e8c
chainlink-ace-skill is a skill published in the GitHub repository smartcontractkit/chainlink-agent-skills (126 stars, last pushed 2d ago), licensed MIT. It adds 168 tokens to every session and 2,661 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 2 findings (tells the agent never to refuse, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
signature-replay
Signature replay attacks — missing nonces, missing chain ID, ecrecover zero address, signature malleability, cross-chain replay.
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
bridge
Cross-chain token transfers using Wormhole and CCTP.
onchainkit
Build onchain apps with Coinbase's OnchainKit React components - wallets, swaps, NFTs, payments.