evlog is a TypeScript-first logging and observability project built around wide events and structured errors across runtimes. It is intended to help developers record application behavior and diagnose failures.
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 HugoRCD/evlog --skill daily-digestgit clone --depth 1 https://github.com/HugoRCD/evlogWrote 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/hugorcd/evlog/daily-digest)<a href="https://agentmods.dev/skills/hugorcd/evlog/daily-digest"><img src="https://agentmods.dev/badge/skills/hugorcd/evlog/daily-digest/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/hugorcd/evlog/daily-digest"><img src="https://agentmods.dev/badge/skills/hugorcd/evlog/daily-digest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.00653 |
| Opus 5.5 | $0.00027 | $0.00261 |
| Sonnet 5.5 | $0.00014 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
daily-digest 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 1mo 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daily digest
A summary of the last 24 hours, most attention-worthy first. Gathering is read-only; the only write is the Linear document below.
Delivery: a Linear document, not a chat wall. Chat renders a multi-section report badly; Linear renders it well and keeps the history browsable. On the scheduled run (and whenever Hugo asks for "the digest"):
- Write the full digest as a Linear document via
linear__save_document, on the evlog team, titledDaily digest — YYYY-MM-DD, with real markdown headings per section. - Post to the thread only: one or two lines with the single most attention-worthy item, then the document link.
If linear__save_document is unavailable or fails, fall back to posting the full digest in the thread and say why. An ad-hoc question in conversation ("what happened this week?") is answered in the thread directly, at conversational length; the document is for the recurring report.
When the request names a different window ("this week", "since Monday"), keep the structure and widen the window; the 24-hour default is for the scheduled morning run.
Sections, in order
- GitHub (last 24h). New and updated issues, merged and open pull requests, CI state on
main(getCiFailureContextwhen red). Lead with whatever needs attention: a red build, a stalled community PR, an issue with activity. Skip empty categories with one word, never with an apology. - AI Gateway spend (last 24h).
ai_gateway__reporttotals, with a one-line callout only when spend is unusual against recent days. - Visitors (last 24h).
vercel__get_web_analytics(mode: 'count',dataset: 'visits') for the docs site and the other evlog projects. - CLI usage (last 7d).
telemetry-statsandtelemetry-adoption: runs, success rate, top command, and one interesting signal when there is one, such as a CLI version rolling out, a flag gaining traction, an error code creeping up, or a source-mix shift. One or two lines; one word when the numbers are flat. - Worth reading. 2 or 3 short items of AI or ecosystem news worth Hugo's time today, each with a link and a date.
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.
- 1mo ago First seen · 32 lines · 68 tokens per session scan A 04df9ec4cfd0
daily-digest is a skill published in the GitHub repository HugoRCD/evlog (1,903 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 653 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
delivering-morning-briefings
Weather + news morning briefing: fetch live weather and headlines, compose a plain-text briefing, deliver it. Multi-step; load before acting.
gh-issue
Size-audit, write, and split BanyanDB issues that somebody else or an automated TDD workflow can implement. Use whenever the user asks to file or revise an issue, decide whether an issue is too large, make an issue TDD-ready, turn a design into tickets, or split an umbrella into executable leaves. Do not draft or file…
gh-pull-request
Create a GitHub pull request for SkyWalking BanyanDB. Use when the user asks to create a PR, submit changes, or open a pull request.
vendor-update
Upgrade Go/Node.js vendor dependencies and sync tool versions. Use whenever the user says "upgrade dependencies", "update vendors", "vendor update", "run vendor-upgrade", "bump dependencies", "update packages", or asks to run the vendor-update Make target. This skill also checks scripts/build/version.mk after…
automation-flows
Use when building or fixing a no-code automation on n8n, Make, or Zapier — trigger to multi-app steps with data mapping, dedup, retries and an error path — or picking the platform by billing unit (task vs credit vs execution). NOT a typed API client in code (that is api-connector-builder), NOT a webhook receiver in…
bydbql
Generate, validate, and optionally execute read-only BanyanDB BydbQL for STREAM, MEASURE, TRACE, and PROPERTY resources. Use when the user asks to query BanyanDB, translate natural language to BydbQL, inspect BanyanDB schema or data, validate BydbQL, or fetch raw BanyanDB records.