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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/yc-software/qmnpx agentmods add skills/yc-software/qm/email-draft-in-voiceWrote 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/email-draft-in-voice)<a href="https://agentmods.dev/skills/yc-software/qm/email-draft-in-voice"><img src="https://agentmods.dev/badge/skills/yc-software/qm/email-draft-in-voice.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.00518 |
| Opus 5 | $0.00017 | $0.00259 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
email-draft-in-voice 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 8d 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.
Draft email in the user's voice
Use this when the user asks you to write or reply to email as them — "draft a reply to this", "write back to her for me", "answer my inbox in my voice".
Load the profile first — never freehand
Read voice/email-voice-profile.md from the workspace. If it doesn't exist, run the
email-voice-profile skill first (personal DM only) — do not improvise a voice from
memory or from this conversation's tone. The profile's Hard rules and
Anti-patterns sections are constraints, not suggestions.
Draft
- Read the full thread you're replying to with
gmail.py thread THREAD_ID --full— never draft from a snippet or excerpt; a question below the fold would go silently unanswered. Match the register the profile prescribes for this audience. - Write the body to a file — plain text, one line per paragraph, blank line between. Plain text only — never styled HTML (fonts, colors, buttons); the gmail helper adds the correct unstyled HTML mirror itself.
- Self-check against the profile before showing anything: opener and sign-off drawn from their real ones, sentence rhythm right, no anti-pattern present. If a sentence could appear in anyone's email, rewrite it or cut it.
- Show the user the exact text and ask for approval before creating any draft.
Gmail
Use the google-workspace skill's helper (the user's OAuth token is already on your computer):
python3 skills/google-workspace/scripts/gmail.py draft --to [email protected] --subject '...' --body-file body.txt
python3 skills/google-workspace/scripts/gmail.py reply MESSAGE_ID --body-file body.txt [--all]
Sending (send-draft) only ever fires on a draft the user explicitly approved for
sending, per that skill's rules.
Afterward
Tell the user where the draft landed in Gmail Drafts and keep the draft id in the workspace so it can be updated. If they edit your text, notice what they changed — recurring corrections belong in the voice profile as hard rules; offer to add them.
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.
- 8d ago First seen · 51 lines · 35 tokens per session scan A 537c8ed7bac3
email-draft-in-voice is a skill published in the GitHub repository yc-software/qm (14,643 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 518 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
thisWeek
Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
agentic-loop-skill
Autonomous decision loop with reflection and iteration.
apify-skill
Run web scrapers and extract data from websites and social media platforms using Apify actors. Supports Instagram, TikTok, Twitter/X, LinkedIn, Facebook, YouTube, Google Search, and general web crawling.
browser-skill
Interactive browser automation - navigate, click, type, fill forms, take screenshots, get accessibility snapshots. Supports system Chrome/Edge via auto-detection.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.