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 ndunl075/alfred-pennyworth --skill inbox-triagegit clone --depth 1 https://github.com/ndunl075/alfred-pennyworthWrote 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/ndunl075/alfred-pennyworth/inbox-triage)<a href="https://agentmods.dev/skills/ndunl075/alfred-pennyworth/inbox-triage"><img src="https://agentmods.dev/badge/skills/ndunl075/alfred-pennyworth/inbox-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/ndunl075/alfred-pennyworth/inbox-triage"><img src="https://agentmods.dev/badge/skills/ndunl075/alfred-pennyworth/inbox-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 | $0.00037 | $0.00848 |
| Opus 5 | $0.00018 | $0.00424 |
| Sonnet 5 | $0.00007 | $0.00170 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
inbox-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 11d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbox triage
Overview
gmail-sync already pulls unread Gmail headers/snippets into Alfred Core's
local storage on its own schedule; this skill's job is to read that already-
synced content and turn it into a short, useful summary -- not to sync Gmail
itself, and not to act on anything without the user's explicit say-so.
When to use
- The user asks what's in their inbox, or to triage/summarize unread email.
- As part of a broader daily/weekly review alongside
morning-briefandweekly-review.
Steps
- If the prompt contains an
<alfred_context>block withgmail, use it as the completed read and do not callconnector_records_getagain. Otherwise callconnector_records_getwithconnector="gmail"andrecord_type="unread_message"(defaultlimit=20is usually enough; ask before requesting more). - Prioritize direct personal mail and real consequences: deadlines, direct questions, security events, failed payments, cancellations, expiring services, account pauses, and required decisions. Judge from sender + subject + snippet, not a subject alone.
- Silently omit promotions, social notifications, newsletters, digests, and obvious bulk mail. Do not name those senders/subjects or call the group "spam" unless the user explicitly asks for low-priority mail.
- Summarize only the one or two items that matter. Cite subject + sender, not full snippets verbatim unless the user asks to see one in full.
- If the user wants to act on something (reply, archive-equivalent,
schedule a follow-up task): a reply is a consequential send, so call
message_draftormessage_send_proposeto preview it -- never assume approval. Synced Gmail context contains only headers and a short snippet; if a responsible draft depends on the missing body, ask for the message text or needed facts first. A follow-up task/reminder is automatic and reversible, sotask_upsert/reminder_setcan be called directly once the user confirms what they want tracked.
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.
- 11d ago First seen · 77 lines · 37 tokens per session scan A 57d132c231f1
inbox-triage is a skill published in the GitHub repository ndunl075/alfred-pennyworth (0 stars, last pushed 23d ago), licensed Apache-2.0. It adds 37 tokens to every session and 848 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 2026-08-31.
Other skills, from other repositories
cron-scheduler
A scheduling guide for creating and managing tasks that run at exact repeating times, such as every day, week, or hour.
daily-manager
A daily planning and coordination guide for organising tasks, priorities, progress reviews, and work that spans several specialist add-ons.
feishu
A guide for operating Feishu, a workplace collaboration platform used for messages, documents, tasks, calendars, and groups.
file-organizer
A file-management guide for sorting, renaming, archiving, finding duplicates, and analysing disk usage.
doc-processor
A document-processing guide for creating and converting Word files, spreadsheets, presentations, Markdown, HTML, and PDFs, including extracting PDF text.
code-assistant
A Chinese-language workflow for using Claude Code, Codex, or Gemini as background coding agents for complex development tasks. It covers orchestration, monitoring, isolation, review, and recovery.