LoongSuite Pilot is a local telemetry collector that gathers activity from AI coding agents, converts their different records into a shared event format, and exports the data to selected destinations. Development teams use it to inspect agent usage, token consumption, sessions, tools, traces, and security-sensitive data. Its catalogue add-ons support working with and configuring the collector for coding-agent telemetry.
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 skills add alibaba/loongsuite-pilot --skill loongsuite-pilot-opsgit clone --depth 1 https://github.com/alibaba/loongsuite-pilotWrote 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.
[](https://agentmods.dev/skills/alibaba/loongsuite-pilot/loongsuite-pilot-ops)<a href="https://agentmods.dev/skills/alibaba/loongsuite-pilot/loongsuite-pilot-ops"><img src="https://agentmods.dev/badge/skills/alibaba/loongsuite-pilot/loongsuite-pilot-ops/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.
<a href="https://agentmods.dev/skills/alibaba/loongsuite-pilot/loongsuite-pilot-ops"><img src="https://agentmods.dev/badge/skills/alibaba/loongsuite-pilot/loongsuite-pilot-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00169 | $0.03825 |
| Opus 5 | $0.00084 | $0.01912 |
| Sonnet 5 | $0.00034 | $0.00765 |
| Haiku 4.5 | $0.00017 | $0.00382 |
Grade C, and why
loongsuite-pilot-ops scanned grade C with 2 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 12d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LoongSuite Pilot — 安装 / 配置 / 卸载
LoongSuite Pilot 是面向研发团队的 AI Coding 数据采集与效能评估工具,支持 Cursor、Qoder IDE/CLI、Claude Code、Codex 的数据自动采集与上报。
诊断排查请查阅
~/.loongsuite-pilot/skills/loongsuite-pilot-ops/references/diagnostics.md; 观测面板与运维手册请查阅~/.loongsuite-pilot/skills/loongsuite-pilot-ops/references/monitoring.md。 以上两个文件在 pilot 安装完成后自动写入本地,可直接打开阅读。
重要说明
所有命令必须在完整权限环境下执行(Shell 工具调用时设置
required_permissions: ["all"])。 沙箱环境下nvm、sudo及 PID 读取会受限,导致安装或诊断结果不可信。
1. 前置条件
- Node.js >= 18,必须通过 nvm 安装并使用 nvm 管理的 Node(推荐 v22)
- 支持 Mac / Linux 8U 开发机 / Linux ECS(Linux 需
sudo权限) - Linux 7U 开发机:需额外执行 glibc 兼容补丁(见第 5 节)
⚠️ 务必使用 nvm 的 Node,不要使用任何 Agent 自带的 Node 环境
部分 AI Coding Agent(例如 Codex、以及其他自带运行时的 CLI 工具)会在安装时 内置一份 Node,并可能把
node指向其私有目录(例如~/.codex/...或 Agent 自身安装目录下的版本)。这类 Node 仅供该 Agent 内部使用,用它安装 pilot 会导致依赖错乱、hook 失效等问题。安装前务必确认:which node # 路径应包含 .nvm,例如 ~/.nvm/versions/node/v22.x.x/bin/node node -v # 输出应 >= v18.0.0若
which node指向任一 Agent 的私有目录(如~/.codex/、Agent 安装目录等), 请先执行nvm use 22(或在新终端中确认nvm已加载)后再继续安装。
2. 安装
执行以下两步完成标准安装(Mac / Linux 8U / ECS):
# 步骤一:安装 nvm + Node.js(已有 node >= 18 可跳过)
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash
nvm install 22
# 步骤二:安装 LoongSuite Pilot(将 <工号> 替换为 6 位员工号,含前导 0)
curl -fsSL https://aliyun-observability-release-cn-shanghai.oss-cn-shanghai.aliyuncs.com/loongsuite/loongsuite-pilot/loongsuite-pilot-installer-inner.sh \
| bash -s -- install --user.id <工号>
安装成功后验证:
~/.local/bin/loongsuite-pilot status
~/.local/bin/loongsuite-pilot info
# diagnostics 与 monitoring 参考文档已自动写入 loongsuite-pilot-ops/references/
ls -l ~/.loongsuite-pilot/skills/loongsuite-pilot-ops/references/
3. 自定义 Logstore(可选)
安装时或安装完成后,询问用户是否需要使用自定义 Logstore 上报数据。
- 如果用户不需要自定义 Logstore,跳过本节,使用默认配置即可。
- 如果用户需要自定义 Logstore,先询问用户选择哪种访问方式,然后按对应流程操作:
询问用户:是否使用 AK/SK 进行访问?
What ships with it
18 files 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.
- references/claude-code-diagnostics.md 15 KB
- references/codex-diagnostics.md 9.4 KB
- references/cursor-diagnostics.md 11 KB
- references/diagnostics.md 5.3 KB
- references/monitoring.md 3.5 KB
- references/opencode-diagnostics.md 7.6 KB
- references/qoder-cn-diagnostics.md 10 KB
- references/qoder-diagnostics.md 17 KB
- references/qoder-jetbrains-diagnostics.md 12 KB
- references/qoder-work-cn-diagnostics.md 9.9 KB
- references/qoderwork-diagnostics.md 19 KB
- references/qwen-code-cli-diagnostics.md 8.2 KB
- references/service-diagnostics.md 12 KB
- references/sls-diagnostics.md 9.8 KB
- references/sqlite-diagnostics.md 13 KB
- references/updater-diagnostics.md 10 KB
- references/watchdog-diagnostics.md 7.3 KB
- references/wukong-diagnostics.md 10 KB
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.
- 12d ago First seen · 355 lines · 169 tokens per session scan C d8adc26f8f1f
loongsuite-pilot-ops is a skill published in the GitHub repository alibaba/loongsuite-pilot (177 stars, last pushed yesterday), licensed Apache-2.0. It adds 169 tokens to every session and 3,825 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.
computer-use
Control local desktop applications through Computer Use for tasks that require reading or operating app UI. Prefer purpose-built connectors, APIs, or CLIs when available.