morning-brief

morning-brief is a skill for Claude Code, Codex from ndunl075/alfred-pennyworth. It costs 33 tokens per session (651 once invoked), scanned A, original, Apache-2.0.

A morning-brief skill that retrieves Alfred Core's prepared summary of overdue items, today's work, upcoming items, calendar conflicts, and GitHub notifications, then may rewrite its wording.

In plain words
What is it for?
Use it when asking what is on your agenda today or when delivering a scheduled daily brief.
Why use it?
It gives you one short daily overview without changing the facts, dates, links, or existing ranking.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when asking what is on your agenda today or when delivering a scheduled daily brief.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ndunl075/alfred-pennyworth/morning-brief
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.

Any agent
npx skills add ndunl075/alfred-pennyworth --skill morning-brief
Clone the repo
git clone --depth 1 https://github.com/ndunl075/alfred-pennyworth

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 morning-brief

README.md
[![agentmods](https://agentmods.dev/badge/skills/ndunl075/alfred-pennyworth/morning-brief/github.svg)](https://agentmods.dev/skills/ndunl075/alfred-pennyworth/morning-brief)
Your own site
<a href="https://agentmods.dev/skills/ndunl075/alfred-pennyworth/morning-brief"><img src="https://agentmods.dev/badge/skills/ndunl075/alfred-pennyworth/morning-brief/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.

agentmods 80×15 button for morning-brief

Your own site · 80×15
<a href="https://agentmods.dev/skills/ndunl075/alfred-pennyworth/morning-brief"><img src="https://agentmods.dev/badge/skills/ndunl075/alfred-pennyworth/morning-brief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 651 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00033 $0.00651
Opus 5 $0.00016 $0.00326
Sonnet 5 $0.00007 $0.00130
Haiku 4.5 $0.00003 $0.00065

Measured 11d ago against content hash d54669b5010e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

morning-brief 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 11d 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.

hermes-profile/skills/productivity/morning-brief/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Morning brief

Overview

Alfred Core already does all the gathering, ranking, and formatting for the morning brief deterministically, with zero model involvement -- overdue items, items due today, upcoming items, calendar conflicts, and GitHub notifications are bucketed and sorted before you ever see them. Your only job here is to fetch that brief and, optionally, make it sound like a person wrote it -- never to re-derive or re-rank anything yourself.

When to use

  • The user asks for their brief, agenda, or "what's on today."
  • A scheduled/cron trigger asks for the daily brief to be delivered unprompted.

Steps

  1. Call the brief_get MCP tool (optionally with now as an ISO-8601 override, for a brief as of a specific time). This returns the complete, already-ranked, already-formatted plain-text brief -- including a freshness line and any late-delivery disclosure.
  2. If the brief is empty or trivially short (nothing due, nothing overdue), say so plainly rather than padding the response.
  3. Optionally, rewrite the brief's tone to be short and warm -- but under the same hard constraint BriefingService.write_brief() uses internally for Alfred Core's own optional LLM pass: preserve every fact, date, and link exactly as given. Do not add or invent anything not present in the brief. If you're not confident you can do this without altering a fact, deliver the deterministic text from step 1 verbatim instead -- that's always a safe, correct answer.
  4. Deliver the result in the current conversation.

Common pitfalls

  • Re-sorting, re-grouping, or "improving" the ranking brief_get already did -- Alfred Core owns due-date logic and calendar-conflict detection; duplicating it here risks disagreeing with the one system of record.
  • Dropping the freshness line or a late-delivery disclosure when rewriting for tone -- both are load-bearing information, not boilerplate to trim.
  • Calling agenda_get instead when a specific now override is needed -- agenda_get takes no time argument; use brief_get whenever the moment matters.

Read the full file on GitHub · 65 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. 11d ago First seen · 65 lines · 33 tokens per session scan A d54669b5010e

Subscribe to this mod's changes

morning-brief is a skill published in the GitHub repository ndunl075/alfred-pennyworth (0 stars, last pushed 23d ago), licensed Apache-2.0. It adds 33 tokens to every session and 651 once invoked, about $0.0002 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 2026-08-31.