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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/alibaba/loongsuite-pilotnpx agentmods add skills/alibaba/loongsuite-pilot/agentloop-audit-dashboardWrote 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/agentloop-audit-dashboard)<a href="https://agentmods.dev/skills/alibaba/loongsuite-pilot/agentloop-audit-dashboard"><img src="https://agentmods.dev/badge/skills/alibaba/loongsuite-pilot/agentloop-audit-dashboard/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/agentloop-audit-dashboard"><img src="https://agentmods.dev/badge/skills/alibaba/loongsuite-pilot/agentloop-audit-dashboard.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 | $0.00149 | $0.02318 |
| Opus 5.5 | $0.00060 | $0.00927 |
| Sonnet 5.5 | $0.00030 | $0.00464 |
| Haiku 4.5 | $0.00015 | $0.00232 |
Grade A, and why
agentloop-audit-dashboard 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 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.
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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
审计报表
在本插件里
正文与 solutions/loongsuite-pilot-sls-dashboard 里的同一份技能一致。这里只改接法，不另写页面规则。
- 查询目标取
~/.loongsuite-pilot/audit/config-record.json的slsProject、regionId。登录用插件已保存的，不要传--profile test。 - 原文里的
cases/loongsuite-pilot-insight/input/和output/都改到~/.loongsuite-pilot/audit/reports/。不要把产物写进 skill 目录，也不要改 examples/ 里的文件。 - examples/ 是原方案
agent-events、business-team的副本，给模型参考版式和口径。用户的 HTML 仍按下面的 Workflow 新写。不要直接渲染 examples 里的文件。AgentLoop 托管索引没有gen_ai.tool.call.arguments.file_path，Skill 图用gen_ai.skill.name。 - 预览在插件根目录执行
python3 scripts/run.py report --dashboard ~/.loongsuite-pilot/audit/reports/<scenario>-dashboard.json。Windows 用scripts/run.ps1 report，参数相同。不要调用 skill 目录或本插件以外的render_report.py。 - 发布先执行
python3 scripts/run.py publish --dashboard <json> --remark "<修改原因>"，把将创建还是覆盖告诉用户；用户同意后再加--confirm。不要执行会卡在安装aliyun-cli-sls确认提示的aliyun sls create-dashboard/update-dashboard。 - 临时问一条数走 agentloop-audit-query。要报表时，从这次对话推测用户要放的，再用本技能
schema.md和示例里已经有的能力写成 spec。
Purpose
将 LoongSuite Pilot 采集的 AI Agent 事件转化为可复用的报表语义。用户应直接使用本 skill；本 skill 负责业务数据语义、指标口径和场景需求解释，再调用 sls-dashboard-builder 的通用能力生成或修改 SLS dashboard JSON。
References
| 参考 | 读取范围 |
|---|---|
| schema.md | 先读 Data Source Bindings 和 Source Composition，再按任务读取所需 Source 和查询构件；组织关联读 dept_roster，枚举展示读“枚举展示与交互” |
| value-labels.md | 生成枚举标签时查对应字段及父子分类表；普通 Token 报表无需读取 |
sls-dashboard-builder |
构建图表 JSON、预览或发布时，读取其入口及必要参考 |
| 筛选器与变量替换 | 配置筛选器或查询参数时先读；确定作用范围、模板、原值与标签、默认值和候选来源，再应用业务枚举 |
| 交互事件与下钻报表 | 制作总览与明细联动、日志下钻或业务页面链接时读取；先按查看环境选择纯 SLS 原生事件或 AgentLoop URL，场景 spec 写明点击入口、目标资源、变量映射和时间范围 |
Boundaries
- 新增报表先组合
schema.md的通用构件；仅在体现不同可复用查询模式时扩充 schema 示例。完整场景 SQL 放在场景 spec 和输出中。 - 生成产物只写入
~/.loongsuite-pilot/audit/reports/，不要写入 skill 目录。 - 不要把 LoongSuite Pilot 业务 schema、CTE、脚本或产物写进
sls-dashboard-builder。
What ships with it
7 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.
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.
- today First seen · 126 lines · 149 tokens per session scan A 1b1a7c96f31b
agentloop-audit-dashboard is a skill published in the GitHub repository alibaba/loongsuite-pilot (239 stars, last pushed yesterday), licensed Apache-2.0. It adds 149 tokens to every session and 2,318 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-11-06.
agentloop-audit-dashboard compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentloop-audit-dashboardalibaba/loongsuite-pilot | Skill | 239 | yesterday | Apache-2.0 | A | 149 | Claude Code, Codex |
| autofix-prQwenLM/qwen-code | Skill | 29k | yesterday | Apache-2.0 | A | 141 | Claude Code |
| workflow-authoringQwenLM/qwen-code | Skill | 29k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| stuckQwenLM/qwen-code | Skill | 29k | yesterday | Apache-2.0 | A | 57 | Claude Code |
| e2e-testingQwenLM/qwen-code | Skill | 29k | yesterday | Apache-2.0 | A | 94 | Claude Code, Codex |
| structured-debuggingQwenLM/qwen-code | Skill | 29k | yesterday | Apache-2.0 | A | 85 | Claude Code, Codex |
| batchQwenLM/qwen-code | Skill | 29k | yesterday | Apache-2.0 | A | 102 | Claude Code |