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 triage-a-surfacegit 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/triage-a-surface)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/triage-a-surface"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/triage-a-surface/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/akiotanaka847/qaio-desktop/triage-a-surface"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/triage-a-surface.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00091 | $0.01465 |
| Opus 5 | $0.00046 | $0.00732 |
| Sonnet 5 | $0.00018 | $0.00293 |
| Haiku 4.5 | $0.00009 | $0.00146 |
Grade A, and why
triage-a-surface 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 7d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage A Surface
Classify + rank two surfaces eat week: inbox, calendar. Never draft replies (that draft-a-message), never edit events (that book-a-meeting).
When to use
surface=inbox- "triage my inbox" / "what's in my email" / "summarize my inbox" / "inbox roundup".surface=calendar- "scan my calendar" / "find conflicts" / "how's my week" / "rebalance my week".
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 for
surface=inbox. Pulls last-24h threads so I can classify and rank. - Calendar (Google Calendar, Outlook) - Required for
surface=calendar. Reads the next 7 days for conflicts and unprotected slots.
If you ask for inbox triage and no inbox is connected, I stop and ask you to connect your inbox first. Same for calendar.
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.
- Operating context doc - Required. Why I need it: anchors priorities, key contacts, hard nos so I rank what actually matters. If missing I ask: "Want me to set up your operating context first? Triage gets sharper after."
- VIPs - Required. Why I need it: VIPs ride to the top of the inbox and trigger unprotected-slot alerts on the calendar. If missing I ask: "Who are the people whose threads always need a same-day reply - investors, key customers, anyone else?"
- Focus blocks - Required for
surface=calendar. Why I need it: I flag meetings that crash into your deep-work time. If missing I ask: "When are your protected focus blocks - specific days, specific hours?" - Max meetings per day - Required for
surface=calendar. Why I need it: drives the overload flag. If missing I ask: "What's a normal-busy versus over-loaded day for you in number of meetings?" - Your timezone - Required. Why I need it: reads windows in your time, not UTC. If missing I ask: "What timezone do you work in most of the time?"
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.
- 7d ago First seen · 79 lines · 91 tokens per session scan A 1ea4c202f1ac
triage-a-surface is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 91 tokens to every session and 1,465 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
anti-sleep
Keep a Mac awake with caffeinate during long builds, downloads, or supervised automation runs.
pipa-follow-up-reminders
Create and cancel simple one-shot email follow-up reminders through Pipa. Use this when the user wants Pipa to email them a specific reminder at a future time, such as “email me tomorrow at 9 to follow up,” “remind me by email next Friday,” or “send me a reminder in two hours.” Also use it to cancel a previously…
pipa-time-tracking
Track work time through Pipa generic agent utility records. Use when user asks to start, stop, switch, inspect, backfill, update, archive, or summarize time entries.
pipa-huddle-beta
Use when the user wants to talk through work with Pipa or their current agent in a live voice huddle: Pipa Huddle, Pipa voice session, talk this through, walking work session, plan this by voice, voice call with my agent, or discuss this out loud. Starts a voice huddle with agent context and optional handoff. Do not…
pipa-daily-shutdown
Use only when pipa-daily-shutdown is explicitly invoked or pipa-improve-operations delegates to it.
pipa
Use when the user invokes Pipa or asks to plan a service-business workday, shut down work for the day, or prepare tomorrow. Routes business operations to get work, define work, deliver work, get paid, keep clients, improve operations, Manage Pipa, or Pipa Tools.