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/loganhc-09/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/loganhc-09/claude-chief-of-staff/brief)<a href="https://agentmods.dev/commands/loganhc-09/claude-chief-of-staff/brief"><img src="https://agentmods.dev/badge/commands/loganhc-09/claude-chief-of-staff/brief/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/loganhc-09/claude-chief-of-staff/brief"><img src="https://agentmods.dev/badge/commands/loganhc-09/claude-chief-of-staff/brief.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 | $0.00022 | $0.00435 |
| Opus 5 | $0.00011 | $0.00217 |
| Sonnet 5 | $0.00004 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
brief 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 13d 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
Produce the user's brief. If $ARGUMENTS contains "evening", make it an end-of-day version (what closed today, what's still open, what tomorrow needs) instead of a morning one.
Before you write
- Read the user's
CHIEF_OF_STAFF.md. If it doesn't exist, tell them to run/chief-of-staff:setupfirst, then offer a lightweight brief from whatever you can see. - Read their
MEMORY.mdindex and open any memory files relevant to what's coming up today. - Read their
tasks.md(or wherever their open loops live). - Check whatever live sources are connected — calendar, email, messages. Pull actual state; don't guess.
Write the brief
Follow the shape in their daily-brief.md template. Default structure:
- Lead — one thing worth their attention up top. A pattern you noticed, a heads-up, or a genuine win to carry in. Not a task.
- Today — real calendar items with times, plus a one-line "here's what you'll want to have thought about" for anything that needs it.
- Overdue / slipping — aging commitments and follow-ups. VERIFY each is actually still open (check sent mail / notes / calendar) before listing it. A false "you forgot this" costs trust.
- Prep — anything today worth five minutes of prep, with the prep already started (a draft, the relevant thread pulled up).
- One nudge — a single suggestion, not a to-do list.
Rules
- Short enough to read in under a minute. Lead with something interesting, not a calendar dump.
- Celebrate wins specifically before pivoting to what's next.
- One recommendation in the nudge, not a menu.
- Everything you assert is verified against a real source. Flag anything you couldn't confirm as "unverified."
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.
- 13d ago First seen · 31 lines · 22 tokens per session scan A 9002523f6d1a
brief is a command published in the GitHub repository loganhc-09/claude-chief-of-staff (75 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 435 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
evolve
Cluster related instincts into skills, commands, or agents.
suggest-automation
A command that reviews recent Git commits and project instructions to find work patterns that happen repeatedly.
instinct-import
Import instincts from teammates, Skill Creator, or other sources.
instinct-export
Export instincts for sharing with teammates or other projects.
park
Park current session for later resume (append to Markdown file).
postmortem
Analyze the last session and extract instinct proposals.