# Runway Check

> Compute current runway, burn trend, and forecast end-of-runway. Use when boss or bookkeeper is asked for runway, on a scheduled monthly check, or before any fundraising conversation.

- Skill: `jezweb/runway-check` (Agent Skill)
- Install (CLI): `npx skillmds@latest add jezweb/runway-check`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jezweb/runway-check/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: jezweb (https://skillmd.com/u/jezweb)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/jezweb/runway-check

---


# Runway check

A founder should know their runway in months, not "uhhh we have a few months". This skill makes the answer reliable and current.

## When this skill fires

- Boss asks "how's our runway?"
- Pre-fundraising conversation prep
- Monthly scheduled check (1st of each month)
- After any major hire or significant expense

## The shape

1. **Pull bank balance**:
   - If Xero MCP wired: `xero_accounts get_balance`
   - Else: read most recent `wiki/finance/<year>/<month>/bank-balance.md`
   - Else: ask the founder to provide it

2. **Compute trailing 3-month average burn**:
   - Sum monthly burn for last 3 months from `wiki/finance/<year>/<month>/burn-summary.md`
   - Divide by 3
   - If trend is clearly increasing or decreasing, note it

3. **Compute runway**:
   - `runway_months = bank_balance / monthly_burn`
   - Express as both months AND end-of-runway date

4. **Surface a tighter view**:
   - "If burn stays flat at $32K/mo, runway is 7.5 months (out by 2027-01-10)"
   - "If we hire 1 more engineer (+$10K/mo), runway shortens to 5.8 months"

5. **Surface levers**:
   - "Current biggest expense category: payroll (60%)"
   - "Cheapest fast-impact lever: deprioritise the $4K/mo SaaS subscriptions we'd consolidate"

6. **Write to** `wiki/finance/<year>/<month>/runway-check.md` with frontmatter kind:runway-check
7. **Flag if** runway < 6 months — boss should know

## Anti-patterns

- Reporting runway without showing the burn assumption (always show both)
- Optimistic projections that assume a fundraise will close
- Ignoring upcoming known expenses (e.g. quarterly tax payments)
- Pretending we have data we don't ("our burn is around $30K" when it's actually unmeasured)