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/worldcoin/agentkit/claude-mdgit clone --depth 1 https://github.com/worldcoin/agentkitWhat 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 | $0.00702 | $0.00702 |
| Opus 5 | $0.00351 | $0.00351 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
agentkit 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 2d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project Overview
Monorepo for the Worldcoin AgentKit — a toolkit for building AI agents that integrate with World ID and World Chain.
agentkit/— Core TypeScript library (@worldcoin/agentkit). Handles signature verification, x402 payments, AgentBook lookups, and agent registration validation.cli/— CLI tool (@worldcoin/agentkit-cli) for agent registration via World ID.contracts/— Solidity smart contracts (AgentBook registry). Built with Foundry.skills/— Claude AI integration skills for agentkit.
Dev Commands
# Install dependencies
bun install
# Build the library
bun run build:agentkit
# Run TypeScript tests (from agentkit/)
cd agentkit && bun test
# Run Solidity checks (from contracts/)
cd contracts && forge build && forge test -vvv
# Format code
npx prettier --write .
Pre-PR Checklist
CI only runs Solidity checks — TypeScript issues must be caught locally.
bun run build:agentkit— must compile cleanlycd agentkit && bun test— all tests must passnpx prettier --write .— format all files- If touching contracts:
cd contracts && forge fmt && forge build && forge test -vvv
Code Style
Prettier handles formatting (config in root package.json), but know the conventions:
- Tabs for indentation, no semicolons, single quotes
- 120 character line width
- Trailing commas in ES5 positions
- Imports sorted descending via
prettier-plugin-sort-imports-desc
Naming
camelCasefor functions and variablesPascalCasefor types and interfaceskebab-casefor file namesSCREAMING_SNAKE_CASEfor constants
Exports
- Named exports only — no default exports
- Barrel file at
agentkit/src/index.tsgrouped by category (constants, types, server, chain utilities, etc.) - New public exports must be added to the barrel file
TypeScript
- Strict mode is enabled — do not weaken it
- Use the
typekeyword for type-only imports:import type { Foo } from './bar' - Zod schemas co-located with their types, derive types via
z.infer<typeof Schema> - Bun native test runner (
bun:test) — not Jest, not Vitest
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.
- 2d ago First seen · 88 lines · 702 tokens per session scan A bb5f6df568b3
agentkit CLAUDE.md is an instructions file published in the GitHub repository worldcoin/agentkit (23 stars, last pushed 5d ago), licensed MIT. It adds 702 tokens to every session, about $0.0035 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
openbench CLAUDE.md
Instructions for groq/openbench, covering claude.md, essential setup, key commands, development setup and initial setup.
postfix copilot-instructions.md
Instructions for sous-chefs/postfix, covering copilot instructions for sous chefs cookbooks, repository overview, project structure, build and test system and environment setup.
postfix AGENTS.md
Instructions for sous-chefs/postfix: This cookbook manages Postfix through operating system packages and service/configuration files. It does not build Postfix from source.
varnish AGENTS.md
Instructions for sous-chefs/varnish, covering agents.md, agent guidance, package availability, apt (debian/ubuntu) and dnf/yum (rhel family).
ossec AGENTS.md
Instructions for sous-chefs/ossec, covering agents.md, cookbook purpose, agent findings, known limitations and package availability.
nfs AGENTS.md
Instructions for sous-chefs/nfs, covering agent notes, package availability, apt (debian/ubuntu), dnf/yum (rhel family, fedora, amazon linux) and zypper (suse).