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 Agent-Engineer-Master/skill-engineer --skill morning-briefgit clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineerWrote 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/agent-engineer-master/skill-engineer/morning-brief)<a href="https://agentmods.dev/skills/agent-engineer-master/skill-engineer/morning-brief"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/morning-brief.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.00798 |
| Opus 5 | $0.00030 | $0.00399 |
| Sonnet 5 | $0.00012 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/morning-brief — Daily Morning Brief
Generate a structured morning brief and write it to today's daily review file.
Instructions
Step 1 — Establish today's date
date +%Y-%m-%d
Use the output as TODAY (format: YYYY-MM-DD). Also derive:
DAY_NAME— full weekday name (Monday, Tuesday, etc.)MONTH_NAME— full month nameDAY_NUM— day of month
Step 2 — Read context sources (run all reads in parallel)
-
Goals summary — your goals summary file (e.g.
goals/_summary.md) Extract: This Month's Top Priorities list (the numbered items) -
Task board — your task board index (e.g.
tasks/_index.md) Extract: All Active Tasks where status isactiveorin-progress, priority iscriticalorhigh. Include agent and ID. -
Latest competitor digest — find the most recent file in your competitor digests directory (e.g.
network/competitors/digests/) Extract: Top 2–3 signals only. Look for "Key Signals", "Top Signals", or the first substantive section. Skip boilerplate. -
Content pipeline — your content pipeline index (e.g.
content/posts/_posts-index.md) Extract: All posts with stage READY or SCHEDULED. Note the next post due if any has a date.
Step 3 — Compose the brief
Build a brief with exactly these sections, in this order:
---
date: YYYY-MM-DD
day: DAY_NAME
type: daily-review
---
# Morning Brief — DAY_NAME, MONTH_NAME DAY_NUM, YEAR
## Top Priorities
[Numbered list pulled from monthly priorities in goals summary — max 5 items]
## Active Tasks (High/Critical)
[Table or bullet list: ID | Title | Agent — only critical and high priority active tasks]
## Competitor Signal
[2–3 bullet points from latest digest. Include digest date. If no digest from last 2 days, note it.]
## Content Pipeline
[READY posts: list with IDs and titles]
[SCHEDULED posts: list with IDs, titles, and scheduled dates if known]
[Note: if pipeline is empty or all posts are in IDEA/DRAFT, flag it]
## One Focus
[Single most important thing to do today, derived from priorities + task board. One sentence, direct.]
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.
- 6d ago First seen · 104 lines · 61 tokens per session scan A 546835f81892
morning-brief is a skill published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 798 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 2026-08-31.
Other skills, from other repositories
help
Use when the user asks for CAT help or to verify the installed CAT plugin.
uninstall
Use when the user asks to uninstall CAT from Codex.
grep-and-read
Find and read multiple files in one operation (50-70% faster for exploration).
batch-read
Find and read multiple files in one operation (50-70% faster for exploration).
gws-gmail
Gmail: Send, read, and manage email.
recipe-block-focus-time
Create recurring focus time blocks on Google Calendar to protect deep work hours.