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 agentmods add instructions/alibaba/loongsuite-pilot/agents-mdgit 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/instructions/alibaba/loongsuite-pilot/agents-md)<a href="https://agentmods.dev/instructions/alibaba/loongsuite-pilot/agents-md"><img src="https://agentmods.dev/badge/instructions/alibaba/loongsuite-pilot/agents-md.svg" alt="Measured on agentmods" 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 | $0.02833 | $0.02833 |
| Opus 5 | $0.01417 | $0.01417 |
| Sonnet 5 | $0.00567 | $0.00567 |
| Haiku 4.5 | $0.00283 | $0.00283 |
Grade A, and why
loongsuite-pilot AGENTS.md 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 yesterday.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
loongsuite-pilot 项目导航
多 AI Agent 轻量数据采集平台 — 自动发现、多种采集方式、多目标数据输出
架构总览
┌──────────────────────────────────────────────────────────────────┐
│ Orchestrator │
│ (启动编排 / 生命周期管理) │
├─────────────┬─────────────┬───────────────┬──────────────────────┤
│ Discovery │ Deployment │ Input │ Output │
│ 发现 Agent │ 部署采集能力 │ 数据采集 │ 数据输出 │
├─────────────┼─────────────┼───────────────┼──────────────────────┤
│ AgentDiscov │ Deployment │ InputManager │ MultiFlusher │
│ eryService │ Manager │ │ ├─ SlsFlusher │
│ │ AgentDef │ BaseIdeInput │ ├─ JsonlFlusher │
│ AgentContro │ Loader │ BaseSqlite.. │ ├─ HttpFlusher │
│ lManager │ HookStrategy│ BaseHookInput │ └─ OtlpTraceFlusher │
│ │ PluginProbe │ BaseSession.. │ │
│ │ Strategy │ BaseCliForw.. │ │
├─────────────┴─────────────┴───────────────┴──────────────────────┤
│ File Collection (独立文件采集管道) │
│ FileCollectionManager → N × FilePipeline (FileTailer + SlsSender)│
├──────────────────────────────────────────────────────────────────┤
│ Checkpoint (StateStore / SnapshotStore) │ Updater (自动更新) │
└──────────────────────────────────────────┴───────────────────────┘
模块清单
| 模块 | 路径 | 职责 | 详细文档 |
|---|---|---|---|
| 核心编排 | src/core/ |
启动流程、生命周期、Agent 发现与准入控制 | 产品概览 |
| 输入源 | src/inputs/ |
6 种采集基类 + 各 Agent 实现 | 新 Agent 接入 |
| 数据输出 | src/flushers/ |
SLS / JSONL / HTTP 多目标扇出 | 配置指南 |
| 文件采集 | src/file-collection/ |
本地文件采集 → SLS 独立管道 | SLS 输出 |
| 部署管理 | src/deployment/ |
声明式 Agent 部署（Hook / Plugin-Probe） | Agent 定义 |
| 归一化 | src/normalization/ |
原始数据 → AgentActivityEntry 标准格式 | 输出事件 Schema |
| 持久化 | src/checkpoints/ |
StateStore + SnapshotStore 状态管理 | 临时异常下的 Checkpoint |
| 自动更新 | src/updater/ |
多版本管理、增量更新、灰度发布、自动回滚 | 安装与服务管理 |
| 运行时 | deploy/ |
安装、CLI、服务管理、版本指针 | 安装与服务管理 |
| 本地 Dashboard | src/dashboard/ + src/status-bar/metrics-summary-writer.ts |
默认随主进程启停的本地页面；生成并展示 metrics-summary.json 汇总 |
安装与服务管理 |
| 类型定义 | src/types/ |
ClientType、事件结构、配置类型 | 输出事件 Schema |
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.
- yesterday Changed · +17 tokens per session f50dfa20c552
- 6d ago First seen · 133 lines · 2,816 tokens per session scan A 24e9078ed2b0
loongsuite-pilot AGENTS.md is an instructions file published in the GitHub repository alibaba/loongsuite-pilot (162 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,833 tokens to every session, about $0.0142 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 2026-08-30.
Other instructions, from other repositories
teaql-agent-kit AGENTS.md
AGENTS.md instructions for teaql/teaql-agent-kit, covering agents.md — teaql agent kit and hard requirements.
parallel-code CLAUDE.md
Claude Code instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
roamcode AGENTS.md
AGENTS.md instructions for burakgon/roamcode, covering repository instructions for coding agents, public-repository safety, stable release and ota contract, releasing a stable version and ota changes.
awesome-grok-build AGENTS.md
Instructions for DominikTobureto/awesome-grok-build, covering agents.md, mission, operating principles, source policy and file conventions.
tidyfactor-design AGENTS.md
Instructions for alwkala/tidyfactor-design, covering ⚡ skill & 24 modular slash commands (7 lifecycle stages) and critical architecture (non-negotiable).
dev-flow AGENTS.md
Instructions for daphnee-ovo/dev-flow, covering dev-flow plugin, language policy, 注意事项, 命令 and 流程.