agent-setup

Commands for installing or refreshing qkrpc agent integrations in the quicker-rpc repository. They copy skills, rules, and MCP settings into supported coding-agent environments.

In plain words
What is it for?
First-time setup, upgrades, configuration checks, project-level setup, and installing the integration for multiple agent hosts.
Why use it?
It avoids manually copying configuration after installing the CLI or changing the repository's agent documentation.

Command for Cursor

Install

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.

agentmods
npx agentmods add commands/quickerhub/quicker-rpc/agent-setup
Clone the repo
git clone --depth 1 https://github.com/QuickerHub/quicker-rpc

Made for: Cursor.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,244 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01244
Opus 5 $0.00000 $0.00622
Sonnet 5 $0.00000 $0.00249
Haiku 4.5 $0.00000 $0.00124

Measured 2d ago against content hash c4660eb269aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-setup 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.

.cursor/commands/agent-setup.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.

qkrpc Agent 一键安装 / 刷新 skills + MCP

quicker-rpc 仓库根目录 执行。说明见 docs/agent-mcp-integration.mddocs/agent-skill-distribution.md

何时执行

场景 命令
首次安装(交互选 Cursor / Codex / …) qkrpc agent install
首次在本机 Cursor 接入 qkrpc(非交互) qkrpc agent setup
热更新 / 升级 CLI 后刷新 skills、rules qkrpc agent setup --upgrade
研发中改了 docs/skills/*docs/agent-rules/* qkrpc agent setup --upgrade(在仓库根目录,自动从 docs/skills 复制)
检查本机配置是否与 CLI 版本一致 qkrpc agent setup --check
团队仓库要 commit MCP 配置 qkrpc agent setup --project --workspace <path>(可选 --project-skills
多宿主(VS Code、Claude Desktop 等) qkrpc agent setup --all

向后兼容别名: qkrpc mcp install(与 agent setup 相同)。

前置

  1. 已安装 qkrpc.exe(Release 安装包或 build.ps1 -t 后的 %LOCALAPPDATA%\Programs\qkrpc)。
  2. Quicker 已运行且已加载 QuickerRpc 插件(MCP 连通性与此无关,但使用工具时需要)。
  3. 在仓库根目录执行时,--upgrade 会优先从本仓库 docs/skills/docs/agent-rules/qkrpc.mdc 复制(无需 --skill-source)。

执行(研发默认)

# 仅刷新 skills + rules + Claude 指引,不覆盖已有 MCP 配置
qkrpc agent setup --upgrade

首次安装或需重写 MCP 配置:

qkrpc agent setup --workspace D:\your-quicker-workspace

block_until_ms15000。期望退出码 0,stderr 列出写入路径。

写入产物(用户级默认)

产物 路径
MCP ~/.cursor/mcp.json(stdio: qkrpc mcp
Skills ~/.cursor/skills/qkrpcquicker-rpc-knowledgequicker-authoringquicker-eval-expressionquicker-run
Rules ~/.cursor/rules/qkrpc.mdc
Manifest ~/.qkrpc/agent-setup.jsoncliVersion 用于 --check

验证

qkrpc agent setup --check
# JSON for automation:
qkrpc agent setup --check --json

期望:qkrpc agent setup: OK (CLI x.y.z.r),或 JSON 中 "ok": true

然后在 Cursor:重载 MCP(Settings → MCP → 重启或 Reload)后应出现 user-qkrpc 工具。

可选连通性:

# MCP 工具 qkrpc_health 等价
qkrpc ping --json

研发 skill 时注意

  • Skill 源码目录:docs/skills/<name>/(发布时由 publish/publish-rpc.ps1 打入安装包 skills/)。
  • 单 skill 调试:qkrpc agent setup --upgrade --skill-source docs/skills/qkrpc
  • 第三方 MCP 不提供文件读写;磁盘编辑走宿主文件工具 + workspace_program patch;说明见 quicker-authoring / quicker://workspace/readme
  • Codexqkrpc agent setup --codex --project --workspace <根>;Agent 逐步说明见 docs/agent-mcp-self-install.md
  • npm @quickerhub/qkrpc-mcp 仅 spawn qkrpc mcpskills 仍须 agent setup

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. 2d ago First seen · 92 lines · 0 tokens per session scan A c4660eb269aa

Subscribe to this mod's changes

agent-setup is a command published in the GitHub repository QuickerHub/quicker-rpc (13 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,244 tokens. 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.