acp-cli: Instructions file for Claude Code

CLAUDE.md

acp-cli CLAUDE.md is an instructions file for Claude Code from motosan-dev/acp-cli. It costs 1,060 tokens per session, scanned A, original, MIT.

Project instructions for acp-cli, a command-line client for the Agent Client Protocol written in Rust. They describe its commands, source folders, architecture, and required checks.

In plain words
What is it for?
They help develop the CLI, locate command and agent code, configure agents, and run Rust checks, including the documented macOS linker workaround.
Why use it?
They give an agent the repository map and the exact formatting, linting, compilation, and testing commands needed for changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is motosan-dev/acp-cli's own configuration. It tells Claude Code how to work on acp-cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything acp-cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to motosan-dev/acp-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/motosan-dev/acp-cli/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/motosan-dev/acp-cli

Made for: Claude Code.

Wrote 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.

agentmods badge for acp-cli CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/motosan-dev/acp-cli/claude-md/github.svg)](https://agentmods.dev/instructions/motosan-dev/acp-cli/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/motosan-dev/acp-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/motosan-dev/acp-cli/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.

agentmods 80×15 button for acp-cli CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/motosan-dev/acp-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/motosan-dev/acp-cli/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,060 This file is loaded in full into every session.
When invoked 1,060 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01060 $0.01060
Opus 5.5 $0.00424 $0.00424
Sonnet 5.5 $0.00212 $0.00212
Haiku 4.5 $0.00106 $0.00106

Measured 2mo ago against content hash 32ec937d39ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

acp-cli 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.

CLAUDE.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

acp-cli

Headless CLI client for the Agent Client Protocol (ACP). Rust port of ACPX.

Commands

cargo fmt                    # format
cargo clippy -- -D warnings  # lint
cargo test                   # test (needs LIBRARY_PATH on macOS, see below)
cargo check                  # fast compile check

macOS linker fix (libiconv):

LIBRARY_PATH="/opt/homebrew/opt/libiconv/lib" cargo test

Source Structure

src/
├── main.rs              # CLI entry point, clap parsing, command dispatch
├── lib.rs               # Public library API (re-exports)
├── config.rs            # AcpCliConfig — global + project config loading/merging
├── error.rs             # AcpCliError enum (thiserror)
├── agent/
│   └── registry.rs      # Agent name → command resolution (14 built-in agents)
├── bridge/
│   ├── mod.rs           # AcpBridge — spawn_blocking + LocalSet bridge to !Send ACP futures
│   ├── commands.rs      # BridgeCommand enum (Prompt, Cancel, SetMode, SetConfig, Shutdown)
│   └── events.rs        # BridgeEvent enum (TextChunk, ToolUse, PermissionRequest, etc.)
├── cli/
│   ├── mod.rs           # Cli struct (clap), Commands/SessionAction/ConfigAction enums
│   ├── init.rs          # `acp-cli init` interactive setup
│   ├── prompt.rs        # run_prompt() (persistent session) + run_exec() (one-shot)
│   ├── prompt_source.rs # Resolve prompt from args, file, or stdin
│   └── session.rs       # Session subcommands (new, list, show, close, history, cancel, status)
├── client/
│   ├── mod.rs           # BridgedAcpClient — ACP client handler (tool use, permissions)
│   └── permissions.rs   # PermissionMode (ApproveAll, ApproveReads, DenyAll)
├── output/
│   ├── mod.rs           # OutputRenderer trait
│   ├── text.rs          # TextRenderer (streaming + spinner)
│   ├── json.rs          # JsonRenderer (NDJSON events)
│   └── quiet.rs         # QuietRenderer (final text only)
├── queue/
│   ├── mod.rs           # Queue system overview
│   ├── owner.rs         # QueueOwner — holds agent connection, IPC server
│   ├── client.rs        # QueueClient — connects to owner via Unix socket
│   ├── ipc.rs           # IPC protocol (Unix socket)
│   ├── lease.rs         # Lease/heartbeat management
│   └── messages.rs      # IPC message types
└── session/
    ├── mod.rs
    ├── scoping.rs       # Session key: SHA-256(agent + dir + name), git root resolution
    ├── persistence.rs   # Session record JSON (create, load, update, close)
    ├── history.rs       # Conversation history (JSONL append)
    └── pid.rs           # PID file management

Read the full file on GitHub · 92 lines

Changes

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.

  1. 2mo ago First seen · 92 lines · 1,060 tokens per session scan A 32ec937d39ca

Subscribe to this mod's changes

acp-cli CLAUDE.md is an instructions file published in the GitHub repository motosan-dev/acp-cli (14 stars, last pushed 7mo ago), licensed MIT. It adds 1,060 tokens to every session, about $0.0042 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.

Related

acp-cli CLAUDE.md compared with instructions from other repositories

acp-cli CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
acp-cli CLAUDE.mdmotosan-dev/acp-cliInstructions file147mo agoMITA1,060Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode