quicker-rpc: Instructions file for Codex

AGENTS.md

quicker-rpc AGENTS.md is an instructions file for Codex, OpenCode from QuickerHub/quicker-rpc. It costs 4,811 tokens per session, scanned A, original, MIT.

A project instruction file for Quicker RPC, a tool that lets command-line programs call functions inside the Quicker application. It provides routing rules for code changes, builds, hot updates, testing, publishing, and release actions.

In plain words
What is it for?
Use it when changing the RPC plugin, documentation, agent interface, voice runtime, publishing configuration, or frontend. It guides the correct build, reload, frontend check, publishing, and release steps.
Why use it?
It tells an agent which checks or build commands belong to each area of the project, reducing the risk of claiming a fix works without rebuilding or validating it. It also identifies actions that should not be performed.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is QuickerHub/quicker-rpc's own configuration. It tells Codex and OpenCode how to work on quicker-rpc 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 quicker-rpc configures →

Reuse

Borrowing it

Nothing to install: this file belongs to QuickerHub/quicker-rpc. 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/QuickerHub/quicker-rpc/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/QuickerHub/quicker-rpc

Made for: Codex, OpenCode.

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 quicker-rpc AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/quickerhub/quicker-rpc/agents-md/github.svg)](https://agentmods.dev/instructions/quickerhub/quicker-rpc/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/quickerhub/quicker-rpc/agents-md"><img src="https://agentmods.dev/badge/instructions/quickerhub/quicker-rpc/agents-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 quicker-rpc AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/quickerhub/quicker-rpc/agents-md"><img src="https://agentmods.dev/badge/instructions/quickerhub/quicker-rpc/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,811 This file is loaded in full into every session.
When invoked 4,811 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.04811 $0.04811
Opus 5.5 $0.01924 $0.01924
Sonnet 5.5 $0.00962 $0.00962
Haiku 4.5 $0.00481 $0.00481

Measured today against content hash 369ae45eb4c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quicker-rpc AGENTS.md scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **shell_exec**:删除/写入类命令需用户确认;拒绝 `format`、`diskpart`、`curl | iex` 等危险模式(agent-gui 侧)。
AGENTS.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

遵循 AGENTS.md 开放格式:面向 coding agent 的操作说明;人类贡献者请读 README.md。

Quicker 插件 + qkrpc.exe CLI,通过 命名管道 + StreamJsonRpc 让外部命令行调用 Quicker 内能力。

接 Agent/GUI/qkrpc 功能任务时,先按 docs/agents/README.md 的关键词定位功能域,再进入代码;产品状态以 docs/product/README.md 为准。

Quick routing(改什么 → 做什么)

改了什么 Agent 必做 不要
QuickerRpc/src/**、QuickerRpc/build.yaml、QuickerRpc/version.json 根目录 pwsh -NoProfile -File ./build.ps1 -t(或 /hot-update);必须等构建日志出现 plugin runaction + CLI Installed 只改代码不构建、让用户代跑、未重载就声称 Plugin 已修好
docs/action-authoring-src/**、build.ps1、build.yaml、publish/publish-rpc.ps1 同上 -t —
仅 agent-gui/** 自动 dev_frontend_check 直到 ok: true(或 /frontend-check);见 quicker-agent-gui-frontend 跑 build.ps1 -t;未检查就声称无错
agent-gui/llm-publish.config.json 或用户说 发布 publish config publish/Sync-LlmPublishConfig.ps1 → BUNDLED_LLM_CONFIG + Bitiful 加密 OSS;skill quicker-agent-llm-apikey-config / /publish-llm-config commit 该文件;勿 -t
仅 README.md、AGENTS.md、.cursor/**(未动 C#) 无构建 —
docs/agent-mcp-integration.md 等纯文档 无构建 —
第三方 Agent 接入(MCP/skills) Agent 自执行 docs/agent-mcp-self-install.md;Cursor qkrpc agent setup --workspace <root>(项目级);全局插件仅 --cursor-plugin;Codex --codex --project 只把命令丢给用户
公开发布 / getquicker 正式包 /publish;第三段 +1,见 quicker-qkbuild-version-publish 仅用 -t revision 代替发布

热更新后验证:Invoke-RestMethod http://127.0.0.1:9477/health 或 qkrpc action list --limit 1 --json。

Dev environment tips

  • 前置:Quicker 已运行且已加载 QuickerRpc 插件;勿先 ping 探活。
  • Shell 调 qkrpc / rg:QuickerAgent 的 shell_exec 会在 spawn 时自动把 qkrpc 与 rg(ripgrep)目录 prepend 到 PATH(agent-gui/lib/qkrpc-toolchain-env.mjs、agent-gui/lib/rg-bin.mjs);qkrpc mcp install 也会写入工作区 .vscode/settings.json 的 terminal.integrated.env。仍优先 qkrpc MCP 工具。
  • qkrpc 连不上时:先 qkrpc_wait / qkrpc wait --json(或 MCP qkrpc_wait)轮询等待;仍失败则告知用户检查 Quicker / 插件。禁止 shell 连环探活,除非用户明确要求修复环境。详见 skill quicker-rpc-knowledge(docs/skills/quicker-rpc-knowledge/)。
  • Cursor / MCP:用 qkrpc_health 或 qkrpc 工具;勿用 shell 代替 qkrpc CLI。
  • qkrpc 是本机 CLI(qkrpc / %LOCALAPPDATA%\Programs\qkrpc\qkrpc.exe)。在终端 直接调用 qkrpc <子命令>,不要当成只能由用户手动的文档。
  • 自描述优先:qkrpc help --json;CLI/MCP/QuickerAgent 改现有 V1 动作:program-source(CLI qkrpc guide get --topic program-source --json);创建/兼容 JSON:authoring-workflow;子程序:subprogram-workflow。人类可读:docs/cli-commands.md。
  • 高频 / agent-gui:优先 qkrpc serve(http://127.0.0.1:9477,GET /health);未启动时 agent-gui 回退为 CLI 子进程。
  • SDK:.NET 10(CLI);Plugin 为 net472。agent-gui 需 Node 20+、pnpm。启动开发环境:pwsh ./dev.ps1(见 agent-gui/AGENTS.md、docs/dev-supervisor-design.md)。
  • 管道:每次插件 bootstrap 使用当前用户命名空间内的专属 endpoint;CLI/serve/MCP 绑定发现结果的 instance/session/endpoint。固定 QuickerRpc_Server_QRPC2026 仅兼容读取,不用于写入或断线后的自动换宿主。

Read the full file on GitHub · 191 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. today Changed · +12 lines · +680 tokens per session 369ae45eb4c9
  2. 1mo ago First seen · 179 lines · 4,131 tokens per session scan A 416bbce5a38b

Subscribe to this mod's changes

quicker-rpc AGENTS.md is an instructions file published in the GitHub repository QuickerHub/quicker-rpc (14 stars, last pushed today), licensed MIT. It adds 4,811 tokens to every session, about $0.0192 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens