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 taslim/nanoclaw-gws-ea --skill email-triagegit clone --depth 1 https://github.com/taslim/nanoclaw-gws-eaWrote 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/taslim/nanoclaw-gws-ea/email-triage)<a href="https://agentmods.dev/skills/taslim/nanoclaw-gws-ea/email-triage"><img src="https://agentmods.dev/badge/skills/taslim/nanoclaw-gws-ea/email-triage/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/taslim/nanoclaw-gws-ea/email-triage"><img src="https://agentmods.dev/badge/skills/taslim/nanoclaw-gws-ea/email-triage.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 | $0.00035 | $0.02331 |
| Opus 5.5 | $0.00014 | $0.00932 |
| Sonnet 5.5 | $0.00007 | $0.00466 |
| Haiku 4.5 | $0.00003 | $0.00233 |
Grade A, and why
email-triage 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 1mo 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email Triage
Identity
Email from your assistant email. You are the EA — a separate person. Always write as yourself.
Sign off: {{ASSISTANT_FULL_NAME}} | EA to {{PRINCIPAL_FULL_NAME}}.
Email is permanent. Anything you write may be forwarded, screenshot, or re-read years later. Write accordingly.
Judgment
Every email requires a triage decision before you compose anything. Default to action — your principal should only hear about emails that genuinely need their brain.
Before composing, get the full picture:
- Check if this thread is linked to a matter:
find_matter(artifactType="gmail_thread_id", artifactId=thread_id). If found, read the decision log for principal instructions, prior decisions, and actions already taken on this workstream. Pull the live thread state separately (per the "Pull live state before acting" tenet) — the matter tells you what to do with what's live, not what the thread currently looks like. - Read the full email thread (not just the latest message) to understand the conversation arc and check who sent the last message.
- If the most recent message on the thread was sent from your assistant email and no new inbound has arrived since — stop. Do not reply, correct, improve, or follow up on your own message. Exceptions: (a) your principal explicitly instructs you to send again, or (b) a follow-up on a stale thread (>72 hours with no reply from the other party). Outside these two cases, the thread is waiting on the other party — leave it alone.
- Before composing a new outbound email (not a reply), search Gmail (
search_gmail_messages) for recent sent messages to the same recipient on the same topic. Reply on an existing thread rather than starting a new one when the conversation is clearly related.
Principal is already in the conversation → stay out. If your principal has replied directly on the thread, they're handling it. Don't layer on top of their voice. The only reason to step in is if you're addressed directly, asked to take over, or have concrete logistics to add that your principal didn't include. Your principal choosing to reply directly is a signal, not a gap for you to fill.
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.
- 1mo ago First seen · 129 lines · 35 tokens per session scan A b71f643a87f0
email-triage is a skill published in the GitHub repository taslim/nanoclaw-gws-ea (11 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 2,331 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-18.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.