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/setup)<a href="https://agentmods.dev/commands/loganhc-09/claude-chief-of-staff/setup"><img src="https://agentmods.dev/badge/commands/loganhc-09/claude-chief-of-staff/setup/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/setup"><img src="https://agentmods.dev/badge/commands/loganhc-09/claude-chief-of-staff/setup.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 | $0.00023 | $0.00739 |
| Opus 5 | $0.00012 | $0.00369 |
| Sonnet 5 | $0.00005 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
setup 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are setting up the user's personal chief-of-staff system. Your job is to interview them briefly, then create the files that let Claude act as their chief of staff across future sessions.
Where to put it
Default to ~/chief-of-staff/ unless the user specified a location in: $ARGUMENTS
Confirm the location with the user before creating anything. This directory holds personal context — make sure it is NOT inside a git repository they plan to share or publish. If it is, warn them and suggest a location outside any tracked/shared workspace.
Step 1 — Interview
Ask the user, conversationally and a few at a time (don't interrogate — infer what you can and only ask what you genuinely need):
- Name, what they do (roles — plural is fine), time zone.
- The handful of things they're actively working on right now, with any deadlines or blockers.
- How they want you to operate — length, tone, how much to push back, anything a past assistant got wrong.
- Their writing voice, for things you'll draft on their behalf. Ask for one or two short real samples.
- Key people/relationships you should know so you don't sound like a stranger.
- Any standing cadences (weekly review, morning brief) and hard rules (e.g. never send without showing them first).
Keep it light. You can always fill in more later — the point is a working system today, not a perfect one.
Step 2 — Create the files
Using the templates bundled with this skill (in the skill's templates/ directory), create in the chosen location:
CHIEF_OF_STAFF.md— filled in from the interview, not left as blanks. This is the most important file.MEMORY.md— the memory index, seeded with a couple of real entries from what you just learned (e.g. auser-memory for their communication style).<memory-dir>/— the memory folder (can be the same directory). Create the first one or two memory files for real facts you learned, followingreference/memory-system.md.tasks.md— a plain-text task list seeded with the open loops they mentioned. Simple format:- [ ] task — context.daily-brief.md— copy the template so/chief-of-staff:briefhas a shape to follow.
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 · 47 lines · 23 tokens per session scan A 254ace031e73
setup is a command published in the GitHub repository loganhc-09/claude-chief-of-staff (75 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 739 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
obsidian-catchup
Review and process everything captured on the go from the Telegram journal bot - voice, text, images, PDFs, links - waiting in the catchup queue. You pull it when you are back at the laptop; nothing is processed autonomously.
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.
retex
Retex - Capture lesson learned dans memory après fix, rollback, erreur.