Borrowing it
Nothing to install: this file belongs to keep-starknet-strange/starknet-agentic. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/keep-starknet-strange/starknet-agentic/main/CLAUDE.mdgit clone --depth 1 https://github.com/keep-starknet-strange/starknet-agenticWrote 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/keep-starknet-strange/starknet-agentic/claude-md)<a href="https://agentmods.dev/instructions/keep-starknet-strange/starknet-agentic/claude-md"><img src="https://agentmods.dev/badge/instructions/keep-starknet-strange/starknet-agentic/claude-md/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.
<a href="https://agentmods.dev/instructions/keep-starknet-strange/starknet-agentic/claude-md"><img src="https://agentmods.dev/badge/instructions/keep-starknet-strange/starknet-agentic/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04054 | $0.04054 |
| Opus 5 | $0.02027 | $0.02027 |
| Sonnet 5 | $0.00811 | $0.00811 |
| Haiku 4.5 | $0.00405 | $0.00405 |
Grade A, and why
starknet-agentic 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 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.
How it starts
The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Starknet Agentic -- Development Context
Canonical behavioral instructions live in AGENTS.md. This file provides
repository implementation context and operational references.
| Component | Technology | Version |
|---|---|---|
| Smart contracts | Cairo (Scarb + snforge) | Cairo 2.14.0, Scarb 2.14.0 |
| Contract deps | OpenZeppelin Cairo | v3.0.0 |
| TypeScript packages | pnpm workspaces, tsup | Node 24+ |
| MCP server | @modelcontextprotocol/sdk |
^1.0.0 |
| Starknet interaction | starknet.js | ^9.2.1 |
| DeFi aggregation | @avnu/avnu-sdk |
^4.0.1 |
| Schema validation | zod | ^3.23.0 |
| TS testing | Vitest | -- |
| Cairo testing | snforge | 0.54.1 |
| Skills format | SKILL.md (YAML frontmatter + markdown) | AgentSkills spec |
| Website | Next.js 16 + React 19 + Tailwind | -- |
starknet-agentic/
├── packages/
│ ├── create-starknet-agent/ # CLI scaffolding tool (COMPLETE)
│ ├── starknet-mcp-server/ # MCP server (PRODUCTION - 9 tools)
│ ├── starknet-a2a/ # A2A protocol adapter (FUNCTIONAL)
│ ├── starknet-agent-passport/ # Capability metadata client (FUNCTIONAL)
│ ├── x402-starknet/ # X-402 payment protocol (FUNCTIONAL)
│ └── prediction-arb-scanner/ # Cross-venue arb detection (MVP)
├── contracts/
│ ├── erc8004-cairo/ # ERC-8004 Cairo contracts (PRODUCTION)
│ │ ├── src/ # Contract source (identity, reputation, validation)
│ │ ├── tests/ # Unit tests (snforge)
│ │ └── e2e-tests/ # E2E tests (Sepolia)
│ ├── agent-account/ # Agent Account contract (TESTED — 110 tests)
│ └── huginn-registry/ # Thought provenance registry (WIP)
├── skills/
│ ├── starknet-wallet/ # Wallet management skill (COMPLETE)
│ ├── starknet-mini-pay/ # P2P payments + Telegram bot (COMPLETE)
│ ├── starknet-anonymous-wallet/ # Privacy-focused wallet (COMPLETE)
│ ├── starknet-defi/ # DeFi operations skill (TEMPLATE)
│ ├── starknet-identity/ # Identity & reputation skill (TEMPLATE)
│ └── huginn-onboard/ # Cross-chain onboarding skill (COMPLETE)
├── examples/
│ ├── hello-agent/ # Minimal E2E proof (WORKING)
│ ├── defi-agent/ # Arbitrage bot example (~337 lines)
│ ├── onboard-agent/ # E2E agent onboarding flow (WORKING)
│ ├── crosschain-demo/ # Base Sepolia ↔ Starknet demo (WORKING)
│ └── scaffold-stark-agentic/ # Frontend reference
├── references/
│ ├── agentskills/ # AgentSkills format specs
│ └── starknet-docs/ # Official Starknet docs (git submodule)
├── docs/
│ ├── ROADMAP.md # Detailed roadmap with MVP/Nice-to-have/Future
│ ├── SPECIFICATION.md # Technical architecture & component specs
│ ├── AGENTIC_ECONOMY_PLAN.md # Use cases, apps, token economy vision
│ ├── ERC8004-PARITY.md # ERC-8004 cross-chain parity document
│ ├── GETTING_STARTED.md # Quick-start onboarding guide
│ ├── GOOD_FIRST_ISSUES.md # Contributor starter issues
│ └── TROUBLESHOOTING.md # Common issues and solutions
├── website/ # Next.js documentation site (Vercel)
├── .agents/
│ └── skills/ # Codex discovery bridge symlinked to skills/*
├── AGENTS.md # Canonical agent mission and coordination
├── CLAUDE.md # This file
└── package.json # Root monorepo (pnpm workspaces)
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.
- 9d ago First seen · 305 lines · 4,054 tokens per session scan A 2caff71883b2
starknet-agentic CLAUDE.md is an instructions file published in the GitHub repository keep-starknet-strange/starknet-agentic (80 stars, last pushed today), licensed MIT. It adds 4,054 tokens to every session, about $0.0203 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.