Borrowing it
Nothing to install: this file belongs to AgentlyHQ/use-agently. 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/AgentlyHQ/use-agently/main/CLAUDE.mdgit clone --depth 1 https://github.com/AgentlyHQ/use-agentlyWrote 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/agentlyhq/use-agently/claude-md)<a href="https://agentmods.dev/instructions/agentlyhq/use-agently/claude-md"><img src="https://agentmods.dev/badge/instructions/agentlyhq/use-agently/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/agentlyhq/use-agently/claude-md"><img src="https://agentmods.dev/badge/instructions/agentlyhq/use-agently/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 | $0.03129 | $0.03129 |
| Opus 5.5 | $0.01252 | $0.01252 |
| Sonnet 5.5 | $0.00626 | $0.00626 |
| Haiku 4.5 | $0.00313 | $0.00313 |
Grade A, and why
use-agently 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 2mo 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Bun-based TypeScript monorepo for use-agently, a CLI tool for the Agently platform — a decentralized marketplace for AI agents using ERC-8004 and the x402 payment protocol. The CLI manages local EVM wallets, discovers agents, and communicates with them via the A2A (Agent-to-Agent) protocol.
Commands
# Install dependencies
bun install
# Build all packages (compiles to standalone binary via bun build --compile)
bun run build
# Run the CLI in development mode
bun run --filter use-agently dev
# Format code
bun run format
# Run tests
bun run test
All top-level commands use Turborepo (turbo) to orchestrate across packages.
Local Dev Test Loop
packages/localhost-aixyz is the local testing infrastructure for the CLI. It is a private aixyz agent that serves a free A2A endpoint at http://localhost:3000 so you can test use-agently a2a without hitting production agents or spending real funds.
# Terminal 1 — start the local agent (requires OPENAI_API_KEY in packages/localhost-aixyz/.env.local)
bun run --filter localhost-aixyz dev
# Terminal 2 — send a message via the CLI
use-agently a2a send --uri http://localhost:3000 -m "Hello!"
The agent exposes a free endpoint (accepts: { scheme: "free" }), so no wallet balance is needed. Set OPENAI_API_KEY in packages/localhost-aixyz/.env.local before starting the dev server.
Always use this agent when developing or testing changes to use-agently to maintain conformity and ensure every change is exercised end-to-end.
Architecture
- Monorepo: Bun workspaces with
packages/*layout, Turborepo for task orchestration packages/localhost-aixyz: Local development agent (private, not published)aixyz.config.ts— Agent metadata and skillsapp/agent.ts— Free A2A endpoint (accepts: { scheme: "free" }) with echo toolapp/tools/echo.ts— Simple echo tool for testing
packages/use-agently-sdk(@use-agently/sdk): The SDK package (published to npm)client.ts—unstable_Clienttype,createClient(), fetch wrappers (dry-run, payment)agently.ts— Agently platform API (search,getAgentfor ERC-8004 resolution)a2a.ts— A2A protocol:sendMessage,sendMessageStream,getAgentCard, URL resolutionmcp.ts— MCP protocol:listMcpTools,callMcpTool, URL resolutionwallets/— Wallet interface and implementations (EVM private key)utils/— Chain config, transaction mode types
packages/use-agently: The CLI packagesrc/bin.ts— Executable entry point (#!/usr/bin/env bun)src/cli.ts— Commander.js program setup, registers all commandssrc/config.ts— Config persistence at~/.use-agently/config.json(load, save, backup)src/client.ts— CreatesdefaultClientviacreateClient()with CLI user-agent; all CLI commands use this clientsrc/commands/— One file per CLI command (init, whoami, balance, search, a2a)- Build output:
build/use-agently(standalone binary viabun build --compile)
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.
- 2mo ago First seen · 235 lines · 3,129 tokens per session scan A eb8bb7c843ae
use-agently CLAUDE.md is an instructions file published in the GitHub repository AgentlyHQ/use-agently (73 stars, last pushed 3mo ago), licensed MIT. It adds 3,129 tokens to every session, about $0.0125 per session on Opus 5.5. 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.
use-agently CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| use-agently CLAUDE.mdAgentlyHQ/use-agently | Instructions file | 73 | 3mo ago | MIT | A | 3,129 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |