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 skills/hugorcd/evlog/telemetrynpx skills add HugoRCD/evlog --skill telemetrygit clone --depth 1 https://github.com/HugoRCD/evlogWhat 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 | $0.00059 | $0.00488 |
| Opus 5 | $0.00030 | $0.00244 |
| Sonnet 5 | $0.00012 | $0.00098 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
telemetry 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.
What it actually says
Telemetry
Read-only production telemetry for the evlog CLI and anything else reporting through @evlog/telemetry, served by the telemetry app's MCP (telemetry__* tools). Ground every answer in the tools; never guess usage from memory.
The tools
telemetry-stats: aggregate for a range (24h/7d/30d) with the preceding equal window for comparison, breakdowns by environment, tool, source, Node major, tool version and OS, top commands, top error codes, duration percentiles, activity timeline.telemetry-adoption: version rollout over time, new vs returning machines, weekday/hour punchcard, flag/custom-field breakdown.telemetry-runs: the raw event list, filterable and sortable, with pagination.telemetry-run: everything recorded for one run by id (flags, custom fields, environment).
What is interesting
- Version adoption: are users moving to newer CLI versions? A release stalling in adoption is a signal that the upgrade path hurts.
- Source mix: terminal vs CI vs agents vs automation. A shift here changes what the numbers mean.
- Flags and custom fields: what people actually enable. A flag nobody uses may deserve deprecation; a custom field spreading suggests a workflow worth documenting.
- Errors: top error codes and their trend. A code climbing week over week is an incident lead, not a footnote.
- Period-over-period shifts:
telemetry-statsreturns the previous equal window; lean on it before calling anything a change.
Form
- Prefer
range: '7d'for stable signals,'30d'for adoption questions,'24h'only when asked about today. - Answer with numbers and a one-line interpretation. Cite the window. When the data is flat or empty, say so in one line instead of stretching it.
- The dashboard serves generated sample data until real events land; treat unusually clean numbers as suspect on a fresh deployment.
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 · 30 lines · 59 tokens per session scan A a0e7bb8eedf8
telemetry is a skill published in the GitHub repository HugoRCD/evlog (1,831 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 488 once invoked, about $0.0003 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
frontmcp-observability
Use when adding tracing, structured logging, metrics, or monitoring to a FrontMCP server. Covers zero-config OpenTelemetry distributed tracing across all flows; the this.telemetry API for custom spans, events, and attributes in tools, plugins, agents, and skills; structured JSON logging with trace correlation and…
golang-observability-opentelemetry
Instrumenting Go applications with OpenTelemetry for distributed tracing, Prometheus for metrics, and structured logging with slog.
Observability Checklist
Reviews a service or codebase against a full observability checklist — logs, metrics, traces, and alerting gaps.
anyrobot-shadcn-frontend-js
AnyRobot 前端开发核心指南：提供 JavaScript + React + shadcn/ui 开发的精简实用规范和最佳实践。 当用户需要前端开发指导、组件开发或项目结构建议时触发。 本技能提供实际可用于项目开发的核心代码示例和开发指南。.
数据模型文档生成
当用户要生成或更新 Doris 表的数据模型 Markdown（三一级标题：数据摘要、数据表列、JSON扩展字段）、从 Doris 拉取元数据与至少 100 行样本，并由脚本或 --llm 补全说明时启用。.
fix-loop
Use when a Java app that has stacktale installed is failing — after running it or its tests, to find what broke, fix it, and confirm the fix by re-running and checking for new errors. Also use when asked to "check the errors", "what's failing", or to work through errors-ai.log.