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 akiotanaka847/qaio-desktop --skill draft-a-messagegit clone --depth 1 https://github.com/akiotanaka847/qaio-desktopWrote 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/akiotanaka847/qaio-desktop/draft-a-message)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/draft-a-message"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/draft-a-message.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 | $0.00077 | $0.01770 |
| Opus 5 | $0.00039 | $0.00885 |
| Sonnet 5 | $0.00015 | $0.00354 |
| Haiku 4.5 | $0.00008 | $0.00177 |
Grade A, and why
draft-a-message 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft A Message
One drafting primitive for every outbound. Your voice, your approval, your send button - never send, never commit, never sign.
When to use
type=reply- "draft responses" / "reply to {name}" / "draft replies to inbound emails in my triage".type=followup- "track this follow-up" (TRACK sub-mode) / "remind me to follow up with {X}" (TRACK) / "handle my due follow-ups" (HANDLE).type=vendor- "draft renewal-negotiation email" / "write cancel email for {SaaS}" / "reach out to {supplier} for trial" / "reference-check email for {vendor}".
Connections I need
I run external work through Composio. Before this skill runs I check the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.
- Inbox (Gmail, Outlook) - Required. Pulls the thread I'm replying to, samples your voice, and saves the draft back to your inbox so you can review and send.
- Files (Google Drive) - Optional. Lets me read vendor contracts when drafting renewal or cancel emails.
If no inbox is connected I stop and ask you to connect your inbox first.
Information I need
I read your operations context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.
- Your voice - Required. Why I need it: replies sound like you instead of a template. If missing I ask: "Best way is to connect your inbox so I can sample 20 to 30 sent messages. Otherwise paste 3 to 5 recent replies you've written and I'll work from those."
- Operating context doc - Required. Why I need it: anchors priorities and key contacts so replies stay on-message. If missing I ask: "Want me to set up your operating context first? Replies sharpen a lot once I have it."
- VIPs - Optional. Why I need it: shapes tone and deference. If you don't have it I keep going with TBD and treat everyone equally.
- Vendor posture - Required for
type=vendor. Why I need it: drives renewal asks and walk-away language. If missing I ask: "How do you approach vendor talks - push hard for terms, or keep it light? Who's allowed to sign?"
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 · 96 lines · 77 tokens per session scan A 6d24890f41e1
draft-a-message is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 4d ago), licensed MIT. It adds 77 tokens to every session and 1,770 once invoked, about $0.0004 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
status-card-query
Create and maintain agent-authored Paperclip status cards, or compile a prose interest prompt into bounded CompanySearchQuery objects and write the first summary from the assigned Summarizer run.
anti-sleep
Keep a Mac awake with caffeinate during long builds, downloads, or supervised automation runs.
after-action-report
Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event.…
email-deliverability
Make sure email actually reaches inboxes. Use this skill when setting up email authentication (SPF, DKIM, DMARC), diagnosing emails landing in spam, planning a domain reputation strategy, monitoring sender reputation, or hardening against email spoofing. Triggers on email deliverability, SPF, DKIM, DMARC, spam folder…
incident-response
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers…
media-asset-management
Plan and run a media pipeline for images, video, and downloadable assets. Use this skill when designing image storage and delivery, choosing formats (WebP, AVIF), setting up responsive images, picking a video host, organizing a brand asset library, or auditing a slow image pipeline. Triggers on image pipeline, asset…