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.
git clone --depth 1 https://github.com/harperreed/office-admin-claudeWrote 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/commands/harperreed/office-admin-claude/triage-email)<a href="https://agentmods.dev/commands/harperreed/office-admin-claude/triage-email"><img src="https://agentmods.dev/badge/commands/harperreed/office-admin-claude/triage-email/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/commands/harperreed/office-admin-claude/triage-email"><img src="https://agentmods.dev/badge/commands/harperreed/office-admin-claude/triage-email.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 | $0.00000 | $0.00326 |
| Opus 5 | $0.00000 | $0.00163 |
| Sonnet 5 | $0.00000 | $0.00065 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
triage-email 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 9d 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.
What it actually says
Perform bulk email triage on your inbox:
- Use the office:email-management skill
- Search for unread emails in your inbox
- Categorize each email as:
- ACTION NEEDED - Requires response or calendar addition
- CALENDAR - Contains event information (extract and check conflicts)
- ARCHIVE - Informational only, no action needed
- For ACTION NEEDED emails, draft replies using your personal style from
~/.claude/office-admin-config.json - For CALENDAR emails, proactively add events and check for conflicts using office:calendar-management skill
- Present a comprehensive summary organized by priority
If there are more than 10 unread emails, use a Task tool with general-purpose subagent for efficient bulk processing.
Format the output as:
## 📧 Inbox Triage Summary
### 🔴 ACTION NEEDED ([count])
1. **From:** [sender] | **Subject:** [subject]
**Summary:** [brief summary]
**Draft:** [link to created draft or "Draft created in Gmail"]
### 📅 CALENDAR ([count])
1. **From:** [sender] | **Subject:** [subject]
**Event:** [event details]
**Conflicts:** [none | list conflicts]
**Status:** [added to calendar | hold created | awaiting confirmation]
### 📋 ARCHIVE ([count])
1. **From:** [sender] | **Subject:** [subject]
**Summary:** [brief summary]
---
**Total processed:** [count] emails
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.
- 9d ago First seen · 37 lines · 0 tokens per session scan A 89f9c3d22fa7
triage-email is a command published in the GitHub repository harperreed/office-admin-claude (5 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 326 tokens. 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 commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.