msolecki

msolecki/founder-os

Plugin Claude Code

Know what matters today with one source-linked daily decision from your goals, cash, pipeline, and commitments.

msolecki/founder-os

Instructions file CodexOpenCode

Instructions for msolecki/founder-os: Read and follow founder-os/CLAUDE.md as the canonical project guidance. It is shared by Claude Code and Codex; do not duplicate or weaken its house rules in this file.

msolecki/founder-os

Plugin Claude Code

Know what matters today with one source-linked daily decision from your goals, cash, pipeline, and commitments.

msolecki/founder-os

MCP server Claude CodeCodexCursor +2

MCP server "founder-os-state" as configured in msolecki/founder-os. Runs ${CLAUDE_PLUGIN_ROOT}/mcp/founder_os_state.py with python3.

msolecki/founder-os

Agent

Decides whether a plan survives contact with reality. Use to red-team a plan, audit its assumptions, or run a premortem before something becomes irreversible.

msolecki/founder-os

Agent

Decides what gets published and where, and owns how the founder sounds. Use for the content plan, drafting, audience research, and capturing the founder's voice.

msolecki/founder-os

Agent

Decides whether the company can afford something and whether it actually makes money. Use for the monthly close, runway, profitability, and rate raises. Gives no tax or legal advice.

msolecki/founder-os

Agent

Decides what deserves the founder's attention right now and which specialist handles it. Use for the daily brief, the weekly and monthly review, triage of a pile of obligations, the work queue, or when you don't know who to ask.

msolecki/founder-os

Agent

Decides whether the company can take work on and whether what it ships is good enough. Use for capacity checks, scope creep, client health, and delivery retros.

msolecki/founder-os

Agent

Decides what goes in the calendar and what comes out. Use for the week plan, calendar audits, and reading energy from the record.

msolecki/founder-os

Agent

Decides who to talk to and when to follow up. Use for relationship mapping and the follow-up sweep.

msolecki/founder-os

Agent

Decides what to automate and what to tolerate. Use for automation audits and reviewing the tool stack.

msolecki/founder-os

Agent

Decides what happens next with each prospect. Use for pipeline review, outreach and proposal drafts, and win/loss analysis.

msolecki/founder-os

Agent

Decides how the founder's hours and cash split across businesses. Use for the portfolio review, for "which business gets me this week", and whenever two businesses both claim the same block of time or the same money.

msolecki/founder-os

Agent

Decides exactly who the company serves and what it sells them. Use for ICP definition, offer design, and pricing.

msolecki/founder-os

Agent

Decides which capability to build next and how. Use for skill-gap analysis and learning plans.

msolecki/founder-os

Agent

Decides what bet the company makes this quarter and what it kills. Use for quarterly planning, sizing a bet, kill-or-continue calls, and the annual review.

msolecki/founder-os

Hook

Runs when a session starts on startup, resume, clear and compact, executing session-context.py via python3. From msolecki/founder-os.

msolecki/founder-os

Hook

Runs when a subagent starts, executing record-agent.py via python3. From msolecki/founder-os.

msolecki/founder-os

Hook

Runs before the agent uses a tool for ^(Read, Write, Edit, NotebookEdit, Glob, Grep, apply_patch, Bash, WebFetch, WebSearch, Task, Agent and mcp__.*)$ tool calls, executing ownership-guard.py via python3. From msolecki/founder-os.

msolecki/founder-os

Skill Claude CodeCodex

Read twelve months of decisions back and score the judgment rather than the outcome — run once a year, from decisions/ and nothing else.

msolecki/founder-os

Skill Claude CodeCodex

List what must be true for a plan to work, strike what is already evidence, and rank the rest by cost to test — run before the plan is expensive.

msolecki/founder-os

Skill Claude CodeCodex

Collect what the ICP actually says about their problem, verbatim and sourced — run before a content plan, and whenever the founder is about to write about a topic instead of a question.

msolecki/founder-os

Skill Claude CodeCodex

Decide whether a manual task is worth automating using payback arithmetic — run before building anything internal, and especially when the founder is enjoying it.