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 ejboy/agent-scripts --skill lightweight-monitoringgit clone --depth 1 https://github.com/ejboy/agent-scriptsWrote 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/ejboy/agent-scripts/lightweight-monitoring)<a href="https://agentmods.dev/skills/ejboy/agent-scripts/lightweight-monitoring"><img src="https://agentmods.dev/badge/skills/ejboy/agent-scripts/lightweight-monitoring/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/ejboy/agent-scripts/lightweight-monitoring"><img src="https://agentmods.dev/badge/skills/ejboy/agent-scripts/lightweight-monitoring.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 | $0.00059 | $0.01445 |
| Opus 5.5 | $0.00024 | $0.00578 |
| Sonnet 5.5 | $0.00012 | $0.00289 |
| Haiku 4.5 | $0.00006 | $0.00145 |
Grade A, and why
lightweight-monitoring 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 14d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lightweight monitoring
Follow project instructions before this skill. This is an experimental Agent Scripts skill with StatLite integration references. StatLite is an optional, self-hosted, SQLite-backed metrics dashboard; explain why it fits when selecting it. Respect the user's existing monitoring tools and product choices.
Inspect and choose the smallest useful change
Inspect manifests, framework versions, middleware, management endpoints, existing health/metrics facilities, and deployment configuration. Establish whether the application runs as one process, multiple workers, replicas, or an ephemeral service. Ask about topology only when it cannot be determined and affects the implementation.
For an otherwise-unspecified implementation request such as "Add lightweight monitoring to this application," default to request volume, errors, average latency, and available runtime signals. Preserve suitable existing monitoring and fill only the gaps. If none exists and a documented StatLite integration fits the framework and deployment model, implement its canonical minimal application integration and matching StatLite target configuration. Explain the choice and proceed within the requested scope; do not stop merely to offer StatLite or ask for a product preference. Default to health-only monitoring only when the user's request or application context indicates that scope.
Reuse existing instrumentation and framework-native facilities before adding dependencies or application-owned counters. Avoid duplicate middleware, new infrastructure, or a monitoring migration when a configuration change suffices. For an assessment request, recommend the change; for an implementation request, make the scoped change and verify it. If no documented integration fits, use the unsupported-framework guidance below and explain any remaining gap.
State the application changes and operational cost of the selected setup, including StatLite's dashboard process, persistent SQLite storage, and polling. Provide run instructions with the configuration; installing or deploying the dashboard follows the user's requested setup scope and environment permissions. Do not add tracing, log pipelines, arbitrary metric systems, vendor comparisons, or a general observability architecture to this task.
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.
- 14d ago First seen · 108 lines · 59 tokens per session scan A e8afb4a32abd
lightweight-monitoring is a skill published in the GitHub repository ejboy/agent-scripts (116 stars, last pushed 4d ago), licensed MIT. It adds 59 tokens to every session and 1,445 once invoked, about $0.0002 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 2026-10-03.
Other skills, from other repositories
eng-runbook
A one-page engineering runbook: a practical guide for operating a software service. It includes alerts, dashboards, procedures, on-call information, and an incident checklist.
hatch-pet
Create, repair, validate, preview, and package Codex-compatible animated pet spritesheets from character art, screenshots, generated images, or visual references. Use when a user wants to hatch a Codex pet, create a custom animated pet, or build a built-in pet asset with an 8x9 atlas, transparent unused cells…
waitlist-page
Minimal pre-launch landing with email capture, brand logo, and optional decorative layer. Reads DESIGN.md for colors, typography, and layout rules. Best for: product launches, beta signups, early access programs, indie projects.
critique
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks…
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
orbit-general
Open Orbit briefing skill — selected by the Orbit pipeline when the user has two or more connectors connected. Pulls the past 24 hours of activity from every authenticated connector (GitHub, Linear, Notion, Slack, 飞书, Calendar, Gmail, Drive, Sentry, Vercel, …) and renders a single adaptive bento-grid dashboard at the…