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.
npx agentmods add commands/quickerhub/quicker-rpc/cursor-cligit clone --depth 1 https://github.com/QuickerHub/quicker-rpcWhat 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 | $0.00000 | $0.01202 |
| Opus 5 | $0.00000 | $0.00601 |
| Sonnet 5 | $0.00000 | $0.00240 |
| Haiku 4.5 | $0.00000 | $0.00120 |
Grade A, and why
cursor-cli 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
命令索引 — Agent 自动化与动作学习
在 Cursor 聊天输入斜杠命令（如
/learn-authoring）。本页是选型地图，不是agentCLI 手册。
我想做什么 → 用哪个命令
| 目标 | 命令 | 说明 |
|---|---|---|
| 开始 / 续跑动作编写学习 | /learn-authoring |
IDE 内：读进度 → 动作库解构 / pattern / skill 晋升 → 真实宿主验证 |
| L3 benchmark（写动作） | /cursor-sdk |
Headless：@cursor/sdk + qkrpc MCP；F 轴使用真实 Quicker 调试证据 |
| L1 单模块维护（143/143 已完成） | /learn-modules |
新 step-runner 或 schema 变更时补 authored/ |
| qkrpc MCP / skills 安装 | /agent-setup |
qkrpc agent setup --upgrade |
| 改 Plugin/CLI 后热更新 | /hot-update |
build.ps1 -t |
| agent-gui 前端检查 | /frontend-check |
dev_frontend_check |
| 正式发布 | /publish |
getquicker + GitHub Release |
默认路径：人在 IDE 里学动作 → /learn-authoring；要无人值守批量 benchmark → /cursor-sdk。
学习体系速查
/learn-authoring L2 pattern + 动作库 + skill 晋升（IDE，可读可写）
/learn-modules L1 单模块 schema（维护态）
/cursor-sdk L3 authoring-tasks 实写（headless）+ 真实 Quicker 验证
进度文件：
- 动作级：
docs/authoring-references/action-patterns/.learning-progress.json - 模块级：
docs/authoring-references/step-modules/.learning-progress.json
计划：docs/superpowers/plans/2026-06-13-quicker-action-authoring-learning.md
Headless 选型（仅脚本 / CI）
| 场景 | 用 | 不用 |
|---|---|---|
| 批量 benchmark、定时 loop | /cursor-sdk → Invoke-CursorSdk.ps1 |
裸 agent 拼参数 |
| 通用仓库 coding、自定义 prompt | Invoke-CursorAgent.ps1 |
重复手写 agent --resume |
| IDE 内学动作、改文档 | /learn-authoring |
headless（缺交互、难审 retro） |
# SDK benchmark（推荐 headless 入口；完成后按 actionId 在真实 Quicker 中调试）
pwsh -NoProfile -File ./scripts/Invoke-CursorSdk.ps1 -Script benchmark -TaskId clip-lines-expr -Json
# 通用 agent 包装（会话复用 .cursor/agent-cli/last-chat-id.txt）
pwsh -NoProfile -File ./scripts/Invoke-CursorAgent.ps1 -Prompt "分析 action-patterns 进度" -Force
持续 loop（先手动跑一轮对应斜杠命令，再 arm）：
pwsh scripts/run-action-learning-loop.ps1 # 动作级
pwsh scripts/run-learning-loop.ps1 # 模块级
前置（学习 / benchmark 共用）
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.
- 2d ago First seen · 103 lines · 0 tokens per session scan A 183587743894
cursor-cli 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 1,202 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.
Other commands, from other repositories
claude-flow-swarm
Coordinate multi-agent swarms for complex tasks.
bootstrap
PACT session-start ritual — identify the session team (platform-provisioned), secretary spawn, paused-state surface, bootstrap marker.
ox-session-review
Command "ox-session-review" from sageox/ox, covering failure-mode watch-list (read first), from the ledger root. should print 0, phase 1 — scan & score (read-only), quality buckets (first match wins) and removal candidates.
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
handoff
Package current state for the next agent.
add-skill
Scaffold a new skill with validation, plugin generation, and README update.