Borrowing it
Nothing to install: this file belongs to jdpolasky/ai-chief-of-staff. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jdpolasky/ai-chief-of-staff/main/.claude/skills/start/SKILL.mdgit clone --depth 1 https://github.com/jdpolasky/ai-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/skills/jdpolasky/ai-chief-of-staff/start)<a href="https://agentmods.dev/skills/jdpolasky/ai-chief-of-staff/start"><img src="https://agentmods.dev/badge/skills/jdpolasky/ai-chief-of-staff/start/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/jdpolasky/ai-chief-of-staff/start"><img src="https://agentmods.dev/badge/skills/jdpolasky/ai-chief-of-staff/start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00023 | $0.00509 |
| Opus 5 | $0.00012 | $0.00254 |
| Sonnet 5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
start 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.
What it actually says
Morning briefing.
Read the state (in parallel where possible)
Command Center.mdfrom the vault (path is inCLAUDE.md).To-Do.mdfrom the vault._system/last_session.md— what shipped last time, what's open. Frontmatter has the last session number and date._system/hot.md— low-fidelity in-progress snapshot from last/wrap.
If MCP servers are connected: check Gmail for unread human senders in the last 24 hours, and check today's Calendar.
Re-entry check
Look at the date: field in _system/last_session.md frontmatter (or the **Last updated:** line in Command Center if last_session.md hasn't been written yet).
- If today's date: this is a continuation of an active stretch. Brief normally.
- If 1-2 days ago: brief normally, mention the gap in passing only.
- If 3+ days ago: shorten the briefing. Lead with what's still in place from
last_session.md. Offer one easy entry point. No guilt about the gap.
Wins
If To-Do.md has tasks marked - [x] that haven't been moved to Done yet, acknowledge them as wins and offer to move them. (/wrap normally handles this; if /wrap didn't run last session, the items will still be in their quadrants.)
Briefing
Deliver a Must / Should / Could briefing per the structure in CLAUDE.md:
🔴 Must — the one thing that matters most today 🟡 Should — 1-2 items worth attention if momentum is good 🟢 Could — a quick win under 15 minutes to build early momentum
Pull from the Command Center's Top priority and the Do Now quadrant.
Flags
- Waiting For: scan the Waiting For table in
To-Do.mdfor any rows whereFollow Up Byhas passed. Flag each one. - Audit due: if the session number from
_system/last_session.mdis divisible by 7 and the audit hasn't run recently, mention it.
End with: "What do you want to work on?"
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 · 46 lines · 23 tokens per session scan A 13db65efd28c
start is a skill published in the GitHub repository jdpolasky/ai-chief-of-staff (100 stars, last pushed 7d ago), licensed MIT. It adds 23 tokens to every session and 509 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 skills, from other repositories
chief-of-staff
Act as the user's chief of staff, not a task-taker. Use for planning a day or week, triaging priorities, prepping for meetings or calls, drafting messages on the user's behalf, tracking commitments and follow-ups, reviewing what's in-flight, or any moment the user wants a trusted operator who knows their context.…
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
schedule
Reminders, automations, and recurring page, dashboard, or status monitoring (cron, RRULE, or fire-at).
inbox-management
Ongoing Gmail inbox management via scheduled runs. Archives known noise, flags urgent items, drafts replies in-thread (never auto-sends), and catches stale follow-ups. Empty polls spend no model tokens. Starts in flag-only mode.
inbox-cleanup
Run a high-recall, multi-pass email inbox cleanup. Pattern-based subject queries catch 25x more archivable email than sender scans alone. Includes urgency triage, classification signals, and post-cleanup filter setup.
notifications
Send notifications through the unified notification router.