daily-digest

daily-digest is a skill for Claude Code, Codex from HugoRCD/evlog. It costs 68 tokens per session (653 once invoked), scanned A, original, MIT.

A daily activity report covering recent GitHub work, AI Gateway spending, visitor counts, command-line usage, and a short news section. It is normally saved as a Linear document.

In plain words
What is it for?
Use it for scheduled morning digests, recent-activity summaries, and broader reports such as everything that happened during the week.
Why use it?
It gathers several kinds of activity into one dated record, so the team can see what changed recently without searching each system separately.

Skill for Claude CodeCodex

About the project

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.

HugoRCD/evlog · 1,831 stars · on GitHub · evlog.dev

Install

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.

agentmods
npx agentmods add skills/hugorcd/evlog/daily-digest
Any agent
npx skills add HugoRCD/evlog --skill daily-digest
Clone the repo
git clone --depth 1 https://github.com/HugoRCD/evlog

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for daily-digest

README.md
[![agentmods](https://agentmods.dev/badge/skills/hugorcd/evlog/daily-digest.svg)](https://agentmods.dev/skills/hugorcd/evlog/daily-digest)
Your own site
<a href="https://agentmods.dev/skills/hugorcd/evlog/daily-digest"><img src="https://agentmods.dev/badge/skills/hugorcd/evlog/daily-digest.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 653 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.00653
Opus 5 $0.00034 $0.00327
Sonnet 5 $0.00014 $0.00131
Haiku 4.5 $0.00007 $0.00065

Measured 6d ago against content hash 04df9ec4cfd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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 6d 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.

apps/evi/agent/skills/daily-digest/SKILL.md · 32 lines

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"):

  1. Write the full digest as a Linear document via linear__save_document, on the evlog team, titled Daily digest — YYYY-MM-DD, with real markdown headings per section.
  2. 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

  1. GitHub (last 24h). New and updated issues, merged and open pull requests, CI state on main (getCiFailureContext when 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.
  2. AI Gateway spend (last 24h). ai_gateway__report totals, with a one-line callout only when spend is unusual against recent days.
  3. Visitors (last 24h). vercel__get_web_analytics (mode: 'count', dataset: 'visits') for the docs site and the other evlog projects.
  4. CLI usage (last 7d). telemetry-stats and telemetry-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.
  5. Worth reading. 2 or 3 short items of AI or ecosystem news worth Hugo's time today, each with a link and a date.

Read the full file on GitHub · 32 lines

Changes

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.

  1. 6d ago First seen · 32 lines · 68 tokens per session scan A 04df9ec4cfd0

Subscribe to this mod's changes

daily-digest is a skill published in the GitHub repository HugoRCD/evlog (1,831 stars, last pushed 4d ago), licensed MIT. It adds 68 tokens to every session and 653 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.

Related

Other skills, from other repositories

run-tests

Runs .NET tests with dotnet test. Use when user says "run tests", "execute tests", "dotnet test", "test filter", "tests not running", or needs to detect the test platform (VSTest or Microsoft.Testing.Platform), identify the test framework, apply test filters, or troubleshoot test execution failures. Covers MSTest…

exceptionless/Exceptionless · 114 tokens

foundatio-repositories

Use this skill when querying, counting, patching, or paginating data through Foundatio.Repositories Elasticsearch abstractions. Covers filter expressions, aggregation queries, partial and script patches, and search-after pagination. Apply when working with normal query/count/patch/pagination repository code; reserve…

exceptionless/Exceptionless · 76 tokens

frontend-architecture

Use this skill as the frontend entrypoint for the Svelte 5 app in ClientApp — adding routes, creating feature slices, writing Svelte components, applying TypeScript conventions, using shared UI/formatter components, handling accessibility, or adding frontend tests. The legacy Angular app still powers most of the…

exceptionless/Exceptionless · 94 tokens

backend-architecture

Use this skill when working on the ASP.NET Core backend — adding controllers, services, repositories, validators, authorization, WebSocket endpoints, jobs, Foundatio infrastructure, configuration, or Aspire orchestration. Prefer this as the backend entrypoint for project layering, C# conventions, logging…

exceptionless/Exceptionless · 74 tokens

serialization-audit

Use this skill when verifying serialization behavior across branches, testing for backwards compatibility in JSON serialization changes, or comparing API request/response/storage formats between implementations. Apply when migrating serializers (e.g., Newtonsoft to System.Text.Json), adding new JSON converters, or…

exceptionless/Exceptionless · 58 tokens

tanstack-form

Use this skill when building or modifying forms with TanStack Form and Zod validation. Covers createForm, field-level validation, error handling, and mapping ProblemDetails API errors to form fields. Apply when adding new forms, implementing validation logic, or handling form submission in the Svelte frontend.

exceptionless/Exceptionless · 62 tokens