WeReply: Skill for Claude Code

.claude/skills/ipc-communication/SKILL.md

ipc-communication is a skill for Claude Code from cacr92/WeReply. It costs 107 tokens per session (4,243 once invoked), scanned A, original, MIT.

A guide for communication between separate programs using line-by-line JSON messages through standard input and output.

In plain words
What is it for?
Building communication between a Rust orchestrator and platform agents, including messages, commands, heartbeats, and status updates.
Why use it?
It defines message formats, directions, health checks, and error handling so an orchestrator and its agents can exchange data consistently.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is cacr92/WeReply's own configuration. It tells Claude Code how to work on WeReply 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 WeReply configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cacr92/WeReply. 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/cacr92/WeReply/main/.claude/skills/ipc-communication/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cacr92/WeReply

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 ipc-communication

README.md
[![agentmods](https://agentmods.dev/badge/skills/cacr92/wereply/ipc-communication/github.svg)](https://agentmods.dev/skills/cacr92/wereply/ipc-communication)
Your own site
<a href="https://agentmods.dev/skills/cacr92/wereply/ipc-communication"><img src="https://agentmods.dev/badge/skills/cacr92/wereply/ipc-communication/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 ipc-communication

Your own site · 80×15
<a href="https://agentmods.dev/skills/cacr92/wereply/ipc-communication"><img src="https://agentmods.dev/badge/skills/cacr92/wereply/ipc-communication.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,243 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00107 $0.04243
Opus 5 $0.00053 $0.02122
Sonnet 5 $0.00021 $0.00849
Haiku 4.5 $0.00011 $0.00424

Measured 8d ago against content hash 03898405c735, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ipc-communication 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 8d 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/skills/ipc-communication/SKILL.md · 707 lines

How it starts

The opening of the file, as written. The whole thing — 707 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IPC Communication Skill

Expert guidance for implementing Inter-Process Communication between Rust Orchestrator and Platform Agents using JSON protocol via stdin/stdout.

Overview

WeReply uses JSON-based IPC protocol for communication:

  • Protocol: JSON messages via stdin/stdout
  • Direction: Bidirectional (Orchestrator ↔ Agent)
  • Message Format: Line-delimited JSON (one message per line)
  • Character Encoding: UTF-8

Message Protocol Design

Message Types

use serde::{Deserialize, Serialize};
use specta::Type;

// Agent → Orchestrator 消息
#[derive(Serialize, Deserialize, Type, Debug)]
#[serde(tag = "type")]
pub enum AgentMessage {
    MessageNew {
        content: String,
        sender: String,
        timestamp: String,
    },
    CommandResponse {
        success: bool,
        #[serde(skip_serializing_if = "Option::is_none")]
        error: Option<String>,
    },
    HealthStatus {
        status: String,  // "ok", "degraded", "error"
        agent_type: String,  // "windows_wxauto", "macos_accessibility"
    },
    Heartbeat {
        timestamp: f64,
    },
    Error {
        message: String,
        #[serde(skip_serializing_if = "Option::is_none")]
        code: Option<String>,
    },
}

// Orchestrator → Agent 消息
#[derive(Serialize, Deserialize, Type, Debug)]
#[serde(tag = "type")]
pub enum OrchestratorCommand {
    WriteInput {
        content: String,
    },
    ClearInput,
    HealthCheck,
    Stop,
}

Message Format Examples

// Agent → Orchestrator: 新消息
{
  "type": "MessageNew",
  "content": "你好,最近怎么样?",
  "sender": "张三",
  "timestamp": "2024-01-23T10:30:00"
}

// Orchestrator → Agent: 写入输入框
{
  "type": "WriteInput",
  "content": "很好,谢谢!"
}

// Agent → Orchestrator: 命令响应
{
  "type": "CommandResponse",
  "success": true
}

// Agent → Orchestrator: 错误
{
  "type": "Error",
  "message": "无法访问微信窗口",
  "code": "ACCESS_DENIED"
}

Rust Orchestrator Implementation

Agent Process Manager

use tokio::process::{Child, Command};
use tokio::io::{AsyncBufReadExt, AsyncWriteExt, BufReader};
use std::process::Stdio;

pub struct AgentProcess {
    child: Child,
    stdin: tokio::process::ChildStdin,
    stdout_reader: BufReader<tokio::process::ChildStdout>,
}

impl AgentProcess {
    pub async fn spawn(agent_path: &str) -> anyhow::Result<Self> {
        let mut child = Command::new(agent_path)
            .stdin(Stdio::piped())
            .stdout(Stdio::piped())
            .stderr(Stdio::piped())
            .spawn()?;

        let stdin = child.stdin.take()
            .ok_or_else(|| anyhow!("无法获取 Agent stdin"))?;

        let stdout = child.stdout.take()
            .ok_or_else(|| anyhow!("无法获取 Agent stdout"))?;

        let stdout_reader = BufReader::new(stdout);

        Ok(Self {
            child,
            stdin,
            stdout_reader,
        })
    }

    pub async fn send_command(&mut self, command: OrchestratorCommand) -> anyhow::Result<()> {
        let json = serde_json::to_string(&command)?;
        self.stdin.write_all(json.as_bytes()).await?;
        self.stdin.write_all(b"\n").await?;
        self.stdin.flush().await?;
        Ok(())
    }

    pub async fn read_message(&mut self) -> anyhow::Result<AgentMessage> {
        let mut line = String::new();
        self.stdout_reader.read_line(&mut line).await?;

        if line.is_empty() {
            return Err(anyhow!("Agent 已关闭输出"));
        }

        let message = serde_json::from_str(&line)?;
        Ok(message)
    }

    pub async fn kill(&mut self) -> anyhow::Result<()> {
        self.child.kill().await?;
        Ok(())
    }
}

Read the full file on GitHub · 707 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 707 lines · 107 tokens per session scan A 03898405c735

Subscribe to this mod's changes

ipc-communication is a skill published in the GitHub repository cacr92/WeReply (6 stars, last pushed 7mo ago), licensed MIT. It adds 107 tokens to every session and 4,243 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

fastapi-router-py

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.

microsoft/skills · 46 tokens

migrate-segw-to-rap

Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…

arc-mcp/arc-1 · 106 tokens

telnyx-messaging-hosted-curl

Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.

team-telnyx/ai · 45 tokens