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 agentmods add instructions/smartcontractkit/chainlink-agent-skills/claude-mdgit 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/instructions/smartcontractkit/chainlink-agent-skills/claude-md)<a href="https://agentmods.dev/instructions/smartcontractkit/chainlink-agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/smartcontractkit/chainlink-agent-skills/claude-md.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 | $0.01127 | $0.01127 |
| Opus 5 | $0.00563 | $0.00563 |
| Sonnet 5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
chainlink-agent-skills CLAUDE.md 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 5d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chainlink Agent Skills - Development Guide
Project Structure
This is a monorepo of Chainlink agent skills. Each skill lives in its own top-level directory (e.g., chainlink-ccip-skill/, chainlink-cre-skill/, chainlink-data-feeds-skill/).
Each skill directory contains:
SKILL.md- The skill definition with YAML frontmatter (name, description, version) and markdown instructionsreferences/- Supporting reference docs the skill reads at runtimeagents/(optional) - Platform-specific agent configs (e.g.,openai.yaml)assets/(optional) - Supplementary assets like doc indexes
Evals live in evals/<skill-name>/ with test cases, rubrics, and promptfoo configs.
Versioning
Each skill tracks its own version in its SKILL.md frontmatter under metadata.version using semver (e.g., "0.0.3").
When you modify any file within a skill directory, bump that skill's patch version (the 0.0.x component) in its SKILL.md frontmatter. Only bump the skill that was actually changed. Do not bump versions for other skills that were not touched.
Skill Format
Skills follow the Agent Skills specification. The SKILL.md frontmatter must include:
name- Skill identifier (matches directory name)description- Trigger description used by agents to decide when to activate the skilllicensecompatibilityallowed-toolsmetadata.version- Semver string
Running Evals
Each skill has an eval suite in evals/<skill-name>/ containing test cases, grading rubrics, and a promptfoo config. Evals are organized into tiers:
| Tier | Cases | Method | When to use |
|---|---|---|---|
| Smoke | ~20 | Agent-powered or promptfoo | Quick feedback during development |
| Full | All 95 | Promptfoo | Before releases, after major refactors |
Cases included in the smoke tier are tagged with smoke: true in their metadata block in the promptfoo configs.
Agent-powered (no API keys needed)
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.
- 5d ago First seen · 96 lines · 1,127 tokens per session scan A 0363c966f9ce
chainlink-agent-skills CLAUDE.md is an instructions file published in the GitHub repository smartcontractkit/chainlink-agent-skills (125 stars, last pushed 7d ago), licensed MIT. It adds 1,127 tokens to every session, about $0.0056 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 instructions, from other repositories
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
plamen CLAUDE.md
Claude Code instructions for PlamenTSV/plamen, covering plamen — security auditor, execution model, reference files and shared.
experiencer CLAUDE.md
Claude Code instructions for vincentlaucsb/experiencer: The canonical repository instructions are in AGENTS.md. Read and follow that file; this compatibility entrypoint intentionally defines no independent rules.
pip-web CLAUDE.md
Claude Code instructions for playpip/pip-web, covering claude.md — agent guide for pip, read first (by task), the three layers (respect the boundaries), non-negotiables and commands / definition of done.
kya-hub AGENTS.md
AGENTS.md instructions for UMBRAXON/kya-hub, covering agents.md — instructions for ai agents, 1. what kya-hub is, in one paragraph, 2. should you integrate?, 3. quickstart for an llm agent and 4. signing rules — the part that breaks everyone.
bitcoin-mcp copilot-instructions.md
Instructions for Bortlesboat/bitcoin-mcp, covering bitcoin-mcp copilot instructions, rules, satoshi api reference and verification.