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/mimurchison/claude-chief-of-staffWrote 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/mimurchison/claude-chief-of-staff/triage)<a href="https://agentmods.dev/commands/mimurchison/claude-chief-of-staff/triage"><img src="https://agentmods.dev/badge/commands/mimurchison/claude-chief-of-staff/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/commands/mimurchison/claude-chief-of-staff/triage"><img src="https://agentmods.dev/badge/commands/mimurchison/claude-chief-of-staff/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 | $0.00000 | $0.01000 |
| Opus 5.5 | $0.00000 | $0.00400 |
| Sonnet 5.5 | $0.00000 | $0.00200 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/triage — Inbox Triage
Description
Scan all connected communication channels, prioritize items by urgency, and draft responses in your voice. Clear your inbox in minutes.
Arguments
quick— Tier 1 items only, no drafts (fastest)digest— Full scan with summaries, drafts for Tier 1-2- (no argument) — Full scan with drafts for everything actionable
Instructions
You are running inbox triage for {{YOUR_NAME}}. The goal is to process all incoming messages quickly and surface what needs attention.
Step 0: Verify Time and Context
Get the current time so you know what "today" and "recent" mean. Check the calendar briefly to understand where the user is in their day.
Step 1: Scan Channels
Scan each connected channel. Only scan channels with active MCP servers. Report progress as you go.
Channels to scan (in order):
-
Work Email (Gmail) — Search for recent unread/unreplied emails
- Query: Messages from the last 24 hours (or since last triage)
- Focus on: Direct emails (not newsletters, automated, or CC-only)
-
Personal Email — If connected, same approach
- Focus on: Anything from key contacts or family
-
Slack — Check DMs and mentions
- Query: Recent DMs and @mentions
- Skip: Channel chatter unless directly relevant
-
WhatsApp — If connected, check recent messages
- Focus on: Direct messages requiring response
-
iMessage — If connected (macOS only)
- Focus on: Unreplied messages from contacts
Step 2: Classify Each Item
For each item found, assign a triage tier:
| Tier | Criteria | Action |
|---|---|---|
| Tier 1 | From key contacts, time-sensitive, blocking someone, or explicit urgency | Respond NOW |
| Tier 2 | Important but not urgent, requires thoughtful response, due today | Handle today |
| Tier 3 | FYI, newsletters, automated notifications, low-stakes | Archive or brief ack |
Tier assignment factors:
- Who sent it? (Key contacts and leadership = higher tier)
- Is someone blocked waiting for a response?
- Is there a deadline mentioned?
- Has it been waiting a long time? (Older = higher urgency)
- Does it align with active goals?
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 · 124 lines · 0 tokens per session scan A b27ce371fc56
triage is a command published in the GitHub repository mimurchison/claude-chief-of-staff (461 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,000 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 2026-08-30.
Other commands, from other repositories
ws
Word summary — anything told at N levels, from N words down to 1 word, for anything: a topic ("russian literature"), a URL, YouTube link, file, pasted text, a question, or "this". A leading number sets N (5 by default). Shortcut for the Fabric skill's WordSummary intent.
cancel-ralph
Cancel active Ralph Loop.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
r
Resume the last handoff and carry on with the outstanding work.
focus
You are an ADHD focus assistant. Help the user commit to ONE task and block mental distractions.
stuck
You are an ADHD-friendly unblocking assistant. Help users get unstuck when they don't know what to do.