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/sls-dashboard-builderWrote 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/sls-dashboard-builder)<a href="https://agentmods.dev/skills/alibaba/loongsuite-pilot/sls-dashboard-builder"><img src="https://agentmods.dev/badge/skills/alibaba/loongsuite-pilot/sls-dashboard-builder/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/sls-dashboard-builder"><img src="https://agentmods.dev/badge/skills/alibaba/loongsuite-pilot/sls-dashboard-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 105 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 142 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00072 | $0.03406 |
| Opus 5 | $0.00036 | $0.01703 |
| Sonnet 5 | $0.00014 | $0.00681 |
| Haiku 4.5 | $0.00007 | $0.00341 |
Grade A, and why
sls-dashboard-builder 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 13d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SLS Dashboard Builder
创建或修改完整、可导入的阿里云 SLS dashboard JSON。
必备运维技能： 若任务涉及真实 Project 或大盘，且需要通过 aliyun sls ... 查看或复用线上大盘，必须基于最新线上 JSON 操作。
总览
本技能以任务为先，不以「先选图表模板」为先。
对线上大盘，还以当前线上状态为先。
若用户已提供以下任意一项或多项，不要从随意图表模板起手：
- 已有 dashboard JSON
- 大盘 URL 或大盘名称
- 指标需求或查询方案
- 已校验的查询结果文件
- 明确的「做这 2 张大盘」之类需求说明
上述情况下应先还原任务结构，再把每个已校验的视图映射到 SLS 图表，最后拼出 dashboard JSON。
若大盘已在线存在，应在最新线上 JSON 上打补丁，而不是推送更早的本地草稿。
何时使用
适用于：
- 新建 dashboard JSON
- 修改、扩展、重排已有 dashboard
- 将一份分析 / 监控需求包落实为 1 张或多张 dashboard
- 生成可直接通过 SLS API 导入的 dashboard 配置
- 参考现有 dashboard 的成熟写法做最小改造
不适用于：
- 单纯解释 SQL / PromQL
- 复杂前端可视化开发
- 非 SLS dashboard 配置
默认行为
- 默认输出形态：
api-ready - 新建大盘：现代格式（modern）
- 已有老格式大盘：保持 legacy，仅做最小补丁
- 用户提供了现有 JSON：保留未知字段与未改动的图表
- 未明确要求发布，或用户尚未确认预览效果前，只生成或修改本地 dashboard JSON，不 create/update 线上大盘
- create/update 线上大盘时，以用户确认后的 dashboard JSON 为准
- 发布到 SLS 时使用插件命令
aliyun sls update-dashboard/create-dashboard，显式传--display-name、--charts、--description、--attribute remark=<具体修改原因> type=grid update=<ms> version=<version>；不要用 CamelCase OpenAPI 入口UpdateDashboard --body-file发布。 - 公开 SLS Dashboard API 的
UpdateDashboard/aliyun sls update-dashboard是覆盖式更新当前大盘；attribute.version/update/remark只影响当前版本展示元数据，不会自动追加控制台「历史版本」归档。 - 用户说「先给一版」：默认
single-dashboard-mvp - 用户提供完整任务包或设计文档：默认
single-dashboard-full - 用户明确要求多张大盘：使用
multi-dashboard-suite
模式
1. 更新已有大盘
- 先拉取或读取当前 JSON
- 复用现有结构，只改被要求的图表或布局
- 不相关的图表与字段保持不动
2. 创建单张大盘
适用于用户需要一张盘，包含概览、关键趋势与表格等。
3. 创建大盘套件（多张）
适用于用户需要多个决策面，例如 留存与活跃 + 业务与成本。
多张盘之间保持命名、筛选器、标题风格与版式节奏一致。
任务包工作流
当输入包含需求文档、查询方案、结果文件或参考大盘时，按以下顺序：
- 判定任务形态：更新、新建，还是套件
- 建立视图清单：指标、展示意图、project 或 logstore、时间范围、阻塞项
- 若有名称或 URL，优先拉取真实参考大盘
- 将视图归组为大盘区块，例如
概览、趋势、TOP、Cohort、钻取 - 按视图意图选图表配方，不按产品营销名称选
- 仅当图表查询确实可被过滤或可被 token 替换时才加筛选器
- 受阻指标写成简短
markdownpro说明，或明确省略；绝不编造缺失的源数据 - 每张大盘输出完整 JSON
针对此类分析套件任务，请阅读：
references/task-driven-workflow.mdreferences/view-recipes.md
What ships with it
60 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.
- examples/charts/aggpro/流图-基础流图.json 17 KB
- examples/charts/barpro/柱状图-基础柱状图.json 12 KB
- examples/charts/barpro/柱状图-标签多种形态.json 13 KB
- examples/charts/burgauge/计量图-刻度盘.json 10.0 KB
- examples/charts/burgauge/计量图-基础计量图.json 34 KB
- examples/charts/crosstable/交叉表-基础交叉表.json 25 KB
- examples/charts/filter/基础过滤器（场景一）.json 5.5 KB
- examples/charts/filter/基础过滤器（场景三）.json 6.4 KB
- examples/charts/filter/基础过滤器（场景二）.json 5.6 KB
- examples/charts/filter/基础过滤器（场景四）.json 11 KB
- examples/charts/histogram/直方图-基础直方图.json 19 KB
- examples/charts/histogram/直方图-多维度堆叠和合成.json 8.1 KB
- examples/charts/linepro/线图-最大值、弹性最大值.json 14 KB
- examples/charts/linepro/线图-最小值、弹性最小值.json 14 KB
- examples/charts/linepro/线图-堆叠.json 11 KB
- examples/charts/linepro/线图-多轴图.json 13 KB
- examples/charts/linepro/线图-大数据.json 3.6 KB
- examples/charts/linepro/线图-数据补全.json 14 KB
- examples/charts/linepro/线图-时序模式.json 7.9 KB
- examples/charts/linepro/线图-时间范围.json 7.5 KB
- examples/charts/linepro/线图-普通线图.json 24 KB
- examples/charts/linepro/线图-线条形状.json 12 KB
- examples/charts/linepro/线图-阈值.json 7.7 KB
- examples/charts/map/地图-世界地图.json 6.8 KB
- examples/charts/map/地图-中国地图.json 18 KB
- examples/charts/map/地图-热力图.json 4.6 KB
- examples/charts/map/地图-高德地图.json 4.6 KB
- examples/charts/markdownpro/MarkdownPro.json 42 KB
- examples/charts/piepro/饼图-基础饼图.json 12 KB
- examples/charts/piepro/饼图-多查询合并.json 10 KB
- examples/charts/piepro/饼图-环形图和南丁玫瑰图.json 7.6 KB
- examples/charts/radarchart/雷达图-基础雷达图.json 12 KB
- examples/charts/scatterchart/散点图-基础散点图.json 17 KB
- examples/charts/scatterchart/散点图-阈值.json 24 KB
- examples/charts/statpro/统计图-基础统计图.json 70 KB
- examples/charts/statpro/统计图-对比值模式.json 13 KB
- examples/charts/tablepro/表格-值映射.json 8.4 KB
- examples/charts/tablepro/表格-基础表格.json 17 KB
- examples/charts/tablepro/表格-行列转换.json 6.6 KB
- examples/charts/tablepro/表格-进度条.json 24 KB
- examples/charts/tablepro/表格-迷你图.json 14 KB
- examples/charts/tablepro/表格-高亮显示.json 24 KB
- examples/charts/topologypro/拓扑图-不同布局方式.json 16 KB
- examples/charts/topologypro/拓扑图-基础拓扑图.json 23 KB
- examples/charts/topologypro/拓扑图-显示节点 ID.json 11 KB
- examples/charts/topologypro/拓扑图-连线指标.json 12 KB
- examples/dashboards/legacy/Data Transformation Troubleshooting.json 25 KB
- examples/dashboards/legacy/Nginx访问日志.json 27 KB
- examples/dashboards/legacy/数据加工诊断.json 25 KB
- examples/dashboards/legacy/老图访问.json 1.4 KB
- examples/dashboards/modern/ai-agent-business-cost.json 24 KB
- examples/dashboards/modern/ai-agent-retention-activity.json 21 KB
- references/chart-templates.md 20 KB
- references/chart-types.md 2.5 KB
- references/datasources.md 5.6 KB
- references/layout.md 2.1 KB
- references/query-syntax.md 16 KB
- references/schema.md 3.2 KB
- references/task-driven-workflow.md 4.1 KB
- references/view-recipes.md 5.7 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.
- 13d ago First seen · 218 lines · 72 tokens per session scan A cb01a74bb8cd
sls-dashboard-builder is a skill published in the GitHub repository alibaba/loongsuite-pilot (179 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 3,406 once invoked, about $0.0004 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 skills, from other repositories
workflow-authoring
Reference for writing a Workflow tool script (script API and gotchas, agent() options, pipeline() vs parallel(), verification and convergence patterns, resume, worked example). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.
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.