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/gm)<a href="https://agentmods.dev/commands/mimurchison/claude-chief-of-staff/gm"><img src="https://agentmods.dev/badge/commands/mimurchison/claude-chief-of-staff/gm/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/gm"><img src="https://agentmods.dev/badge/commands/mimurchison/claude-chief-of-staff/gm.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 | $0.00684 |
| Opus 5 | $0.00000 | $0.00342 |
| Sonnet 5 | $0.00000 | $0.00137 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
gm 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 12d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gm — Morning Briefing
Description
Start your day with a structured briefing: today's calendar, priority tasks, urgent messages, and upcoming deadlines. Know exactly what matters before you open your inbox.
Instructions
You are running the morning briefing for {{YOUR_NAME}}. Follow these steps in order, collecting information before presenting the final briefing.
Step 0: Get Current Time
Call the Google Calendar get-current-time tool to get the authoritative
date and time. Extract the day of week, date, and timezone. Never guess
the day of week — always verify.
Step 1: Calendar Review
Fetch today's calendar events using list-events with today's date range.
For each event, note:
- Time and duration
- Title and attendees
- Whether it requires preparation
- Any conflicts or back-to-back meetings
Flag:
- Meetings that conflict with hard constraints (e.g., dinner time)
- Back-to-back meetings with no buffer
- Meetings with no clear agenda or purpose
Step 2: Task Review
Read ~/.claude/my-tasks.yaml and identify:
- Tasks due TODAY (urgent)
- Tasks OVERDUE (critical — should have been done)
- Tasks due in the next 3 days (approaching)
- Tasks that can be completed today given the calendar
Step 3: Goals Check
Read ~/.claude/goals.yaml and briefly assess:
- Which goals have stalled (no progress update in 7+ days)?
- Does today's calendar align with the highest-priority goals?
- Any goal-aligned work that should be scheduled today?
Step 4: Inbox Quick Scan (if email MCP is connected)
Do a quick scan of email for anything urgent:
- Search for emails from the last 12 hours
- Flag Tier 1 items (from key contacts, marked urgent, or time-sensitive)
- Don't do a full triage — just surface what's critical
Step 5: Present the Briefing
Format the briefing as follows:
Good morning. It's [Day], [Date]. Here's your day:
CALENDAR ([count] meetings)
- [time] [title] ([duration]) [any flags]
- ...
[If applicable: "Heads up: [conflict or concern]"]
TASKS
- DUE TODAY: [list or "Nothing due today"]
- OVERDUE: [list or "All clear"]
- APPROACHING: [list of next 3 days]
GOALS
- [Brief status on top 1-2 goals, especially if stalled]
URGENT
- [Any Tier 1 items from inbox, or "No urgent items"]
FOCUS RECOMMENDATION
Based on your calendar and priorities, here's what I'd focus on today:
1. [Top priority]
2. [Second priority]
3. [Third priority, if time allows]
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.
- 12d ago First seen · 95 lines · 0 tokens per session scan A ed559e8ce41d
gm is a command published in the GitHub repository mimurchison/claude-chief-of-staff (432 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 684 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
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.