QM is a shared work environment for coding agents that gives each employee and conversation an isolated workspace while allowing collaboration in Slack and on the web. Startups use it to run agents for individuals, teams, and company operations, with selectable harnesses and models. The catalogue entries extend QM with skills, instructions, and settings.
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 yc-software/qm --skill morning-digestgit clone --depth 1 https://github.com/yc-software/qmWrote 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/yc-software/qm/morning-digest)<a href="https://agentmods.dev/skills/yc-software/qm/morning-digest"><img src="https://agentmods.dev/badge/skills/yc-software/qm/morning-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/yc-software/qm/morning-digest"><img src="https://agentmods.dev/badge/skills/yc-software/qm/morning-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 | $0.00039 | $0.00666 |
| Opus 5 | $0.00019 | $0.00333 |
| Sonnet 5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
morning-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 9d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Morning digest
The aim: one message, first thing, that answers "what changed since yesterday that I need to know about?" — so the owner starts the day without opening five tools. It replaces scanning, not thinking. If nothing changed, it says so and stops.
It runs as a scheduled cron turn owned by one person and delivers to their DM. It adds no
new tool: it reads the connectors that person has already connected and the memory of this
scope, and writes with the memory, execute, and read primitives.
Sources
Use only what this deployment actually has, and say which sources you used. Check Connected apps and Your logins in your prompt — those blocks are the complete allowlist. Typically: mail and calendar (what lands today, what's unanswered), the issue tracker (what moved, what's assigned to them), the repositories they work in (merged, failing, waiting on their review), and any shared credential vended for a news or search feed. Never advertise or invent a source that isn't listed.
Steps
- Resume, don't repeat. Keep one checkpoint file per source under
ingest/(e.g.ingest/<source>.json, holding the last cursor and count) and pull only what is newer. A checkpoint older than the source's retention window means a gap — say so rather than implying continuity. - Write what's durable to memory. Save the genuinely notable items as facts in this
scope's memory with the
memorytool, then advance the checkpoint. Memory is an index: record the fact and its link, not the raw payload. - Synthesize for this person. Recall what's most relevant to the owner — this scope
only. Group by topic, not by source. Lead with what needs a decision or a reply today.
A cursor stops re-fetching, not re-delivering: read
ingest/delivered.json(the item ids already sent) and drop anything the owner has seen unless it genuinely moved, in which case lead with what changed. Append today's ids after delivering. - Voice and restraint. Write like a sharp colleague texting a friend: tight prose, every claim carrying its source link, no filler, no emoji headers. Nothing worth sending means "nothing notable today" — silence beats noise.
- Deliver to the owner's DM. The cron's destination is scope-validated at fire time; you can only deliver within the owner's scope.
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.
- 9d ago First seen · 51 lines · 39 tokens per session scan A 57217a2c6c05
morning-digest is a skill published in the GitHub repository yc-software/qm (14,693 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 666 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 2026-08-30.
Other skills, from other repositories
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
cron
Schedule reminders and recurring tasks.
ms-mail-skill
Send, read, search, reply to, and handle attachments of Outlook email via Microsoft Graph — for your own mailbox or a shared mailbox. Compose messages, list recent mail, search by text, reply/reply-all, and list or download file attachments (e.g. PDFs) for parsing.
shell-skill
Execute short-lived shell commands inside the per-workflow workspace. Uses Nushell when installed and otherwise the host shell. External tools on PATH (npm, node, python, git, ...) are available.
google-contacts-skill
Create, list, and search Google Contacts. Supports names, emails, phone numbers, and organizations.
cron-scheduler-skill
Schedule recurring tasks using cron expressions. Run workflows on schedules (daily, weekly, hourly, etc.).