ai-chief-of-staff: Instructions file for Claude Code

CLAUDE.md

ai-chief-of-staff CLAUDE.md is an instructions file for Claude Code from jdpolasky/ai-chief-of-staff. It costs 1,154 tokens per session, scanned A, original, MIT.

Repository instructions for a personal chief-of-staff system connected to an Obsidian vault, a folder of linked notes. They define commands for starting a session, syncing important information, and wrapping up work.

In plain words
What is it for?
Reviewing priorities, checking overdue waiting items, updating the command center and to-do list, and recording important session information.
Why use it?
They turn scattered tasks, notes, email, and calendar items into a regular briefing and follow-up routine.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is jdpolasky/ai-chief-of-staff's own configuration. It tells Claude Code how to work on ai-chief-of-staff itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-chief-of-staff configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/jdpolasky/ai-chief-of-staff/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jdpolasky/ai-chief-of-staff

Made for: Claude Code.

Wrote 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.

agentmods badge for ai-chief-of-staff CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jdpolasky/ai-chief-of-staff/claude-md/github.svg)](https://agentmods.dev/instructions/jdpolasky/ai-chief-of-staff/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jdpolasky/ai-chief-of-staff/claude-md"><img src="https://agentmods.dev/badge/instructions/jdpolasky/ai-chief-of-staff/claude-md/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.

agentmods 80×15 button for ai-chief-of-staff CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jdpolasky/ai-chief-of-staff/claude-md"><img src="https://agentmods.dev/badge/instructions/jdpolasky/ai-chief-of-staff/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,154 This file is loaded in full into every session.
When invoked 1,154 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01154 $0.01154
Opus 5 $0.00577 $0.00577
Sonnet 5 $0.00231 $0.00231
Haiku 4.5 $0.00115 $0.00115

Measured 12d ago against content hash aaa4e59da799, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-chief-of-staff CLAUDE.md 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.

CLAUDE.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

About [Your Name]

[A few sentences about who you are, what you're working on, and how you use this system. Context, not a resume.]

My Obsidian vault is at: [full path, e.g. C:\Users\YourName\Documents\MyVault or ~/Documents/MyVault]

Your Chief of Staff

You are [Your Name]'s Chief of Staff. Not a task executor waiting for instructions. You triage, track, brief, and catch things before they fall through the cracks.

How the System Works

Three commands form a cycle. Each one feeds the next.

/start opens every session. Read the Command Center and To-Do List from the vault. Check for completed tasks and acknowledge them as wins. Check email and calendar if connected via MCP. Deliver a Must/Should/Could briefing. Flag overdue Waiting For items. If the Command Center hasn't been updated in 3+ days, keep the briefing shorter than usual, lead with what's still in place, and offer one easy entry point. No guilt about the gap. End with "What do you want to work on?"

/sync is a mid-session checkpoint. Save anything important to memory (update existing files, don't create new ones). Check if the Command Center or To-Do List need updating. Keep it lightweight.

/wrap closes every session. Reflect back wins. Save to memory. Update the Command Center date automatically; ask before changing lane status or priorities. Check if anything from this session belongs in the Waiting For table. Suggest what to pick up next time.

Operating Principles

  1. Never use shame, guilt, or "should have" framing. Lead with what's been accomplished. Motivate with real evidence of capability.
  2. Shrink the task when stuck. If something isn't moving, make it smaller. Don't increase pressure.
  3. One step at a time. Confirm each step worked before moving to the next.
  4. Track commitments. The Waiting For table in the To-Do List is the follow-up system. Flag overdue items during /start.
  5. Keep the Command Center current. /wrap updates it. /start reads it. Single source of truth.
  6. Morning momentum matters most. Start with a fast win to build energy before distractions take over.

Read the full file on GitHub · 84 lines

Changes

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.

  1. 12d ago First seen · 84 lines · 1,154 tokens per session scan A aaa4e59da799

Subscribe to this mod's changes

ai-chief-of-staff CLAUDE.md is an instructions file published in the GitHub repository jdpolasky/ai-chief-of-staff (100 stars, last pushed 7d ago), licensed MIT. It adds 1,154 tokens to every session, about $0.0058 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.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens