working-with-me

working-with-me is a command for Claude Code from Pitchlab/founder-support-system. It costs 17 tokens per session (1,727 once invoked), scanned A, original, MIT.

An interactive command that creates a personal guide explaining how someone works, communicates, makes decisions, and supports colleagues.

In plain words
What is it for?
Use it when onboarding colleagues, starting a partnership, or documenting meeting habits, communication preferences, goals, boundaries, and management style.
Why use it?
It turns personal working preferences into a document that new teammates, partners, or clients can consult instead of learning everything through trial and error.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the founder-support-system plugin — 6 skills, 10 commands shipped together

Good fit Use it when onboarding colleagues, starting a partnership, or documenting meeting habits, communication preferences, goals, boundaries, and management style.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/pitchlab/founder-support-system/working-with-me
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Pitchlab/founder-support-system

Made for: Claude Code.

Or install founder-support-system, the plugin that ships this one along with the rest of its 6 skills, 10 commands.

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 working-with-me

README.md
[![agentmods](https://agentmods.dev/badge/commands/pitchlab/founder-support-system/working-with-me.svg)](https://agentmods.dev/commands/pitchlab/founder-support-system/working-with-me)
Your own site
<a href="https://agentmods.dev/commands/pitchlab/founder-support-system/working-with-me"><img src="https://agentmods.dev/badge/commands/pitchlab/founder-support-system/working-with-me.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,727 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00017 $0.01727
Opus 5 $0.00009 $0.00864
Sonnet 5 $0.00003 $0.00345
Haiku 4.5 $0.00002 $0.00173

Measured 8d ago against content hash 1bc32b62d753, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

working-with-me 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 8d 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.

commands/working-with-me.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working with Me Command

Create a comprehensive "Working with Me" document that serves as a user manual for how to work with you effectively.

Purpose

This command invokes the working-with-me skill to interactively create a personal user manual covering:

  • Your role and goals
  • Personality and communication preferences
  • Operating approach (meetings, 1:1s, cadence)
  • Management style and decision-making
  • How you support your team
  • Known pitfalls and how to work around them
  • Personal touch that makes work meaningful

When to use: When onboarding new colleagues, starting partnerships, or wanting to clearly document your work style.

Usage

/planning-strategy:working-with-me

No parameters needed - the skill guides you through an interactive interview.

How It Works

This command invokes the working-with-me skill, which:

  1. Fetches context from Notion:

    • Personal Operating Model (strengths, weaknesses)
    • Golden Rules (working principles)
    • Year Plan (current role, goals)
    • Quarterly Logs (for patterns)
  2. Guides you through 7 sections:

    • My Role
    • About Me (personality, communication, boundaries)
    • Operating Approach (1:1s, decision escalation, planning cadence)
    • Management Style (how you manage, decide, give feedback)
    • Supporting You and Your Team (career discussions, goals, inclusion)
    • Pitfalls and Working Around Them (honest weaknesses)
    • Personal Touch (what makes work fun)
  3. Compiles comprehensive document

  4. Saves to Notion as new page under Resources

Example Session

/planning-strategy:working-with-me

Claude:
I've reviewed your Personal Operating Model, Golden Rules, and Year Plan.

I'll guide you through creating your "Working with Me" document covering:
- Your role and goals
- Personality and communication preferences
- Operating approach and cadence
- Management style
- How you support your team

This will take about 20-30 minutes.

**Section 1: My Role**

What is your role and what are your primary goals?

Consider:
- Official title and what it means in practice
- Core responsibilities (what you own)
- Primary goals for 2026
- Who you serve (team, clients, partners)

User: "I'm a Strategy Consultant focused on AI agents and
multi-agent systems. My goals for 2026 are to hit €100K revenue,
establish thought leadership, and become expert in orchestration..."

Claude:
**Section 2: About Me - Personality**

How would you describe your personality at work?

[Continues through all 7 sections...]

Claude:
✅ "Working with Me" document saved to Notion!

📄 https://www.notion.so/Working-with-me-[new-id]

**Next Steps**:
- Review and refine as needed
- Share with new colleagues, partners, clients
- Update quarterly or when your role/style changes

Read the full file on GitHub · 225 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. 8d ago First seen · 225 lines · 17 tokens per session scan A 1bc32b62d753

Subscribe to this mod's changes

working-with-me is a command published in the GitHub repository Pitchlab/founder-support-system (2 stars, last pushed 8mo ago), licensed MIT. It adds 17 tokens to every session and 1,727 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 2026-08-31.