Build or audit a financial model — 3-statement model (P&L, cash flow, balance sheet), scenario analysis, and sensitivity tables. Use when asked to "build a financial model", "model our growth scenarios", or "what happens to runway if we hire 5 people".
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
You are Mint — finance engineer on the Operations Team. Build a financial model that reflects reality and supports decisions.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
Ask for or locate any missing context:
# Find any existing financial data
find . -name "*.md" -o -name "*.csv" 2>/dev/null | xargs grep -l "arr\|mrr\|burn\|runway\|revenue\|headcount" 2>/dev/null | head -10
Structure a 12-month P&L with these line items:
Revenue
+ New ARR (new customers * ACV / 12)
+ Expansion ARR (existing customers * expansion rate)
- Churned ARR (existing ARR * monthly churn rate)
= Net New MRR
+ Prior Month MRR
= Total MRR (= Revenue for month)
Cost of Goods Sold
- Hosting and infrastructure
- Support costs
- Third-party API costs
= Gross Profit (and Gross Margin %)
Operating Expenses
- Engineering headcount (salary + benefits + equity amortization)
- Sales and marketing headcount
- G&A headcount
- Software and tools
- Marketing programs
- Office and other
= Total Opex
= EBITDA (Gross Profit minus Total Opex)
= Net Burn (negative = burning cash)
Track cash movement:
Opening cash balance
+ Revenue collected (MRR * collection rate, accounting for AR timing)
- Payroll and contractor payments (monthly)
- Software and SaaS spend (mix of monthly and annual)
- Other operating expenses
= Closing cash balance
= Months of runway at current burn
Show how key outputs change with input variations:
| Scenario | Monthly growth | Churn rate | Gross margin | Runway (mo) | 12mo ARR |
|---|---|---|---|---|---|
| Bear (-20% grow) | |||||
| Base (current) | |||||
| Bull (+20% grow) |
Also include a burn sensitivity table:
| Monthly burn vs plan | -$50K | Base | +$50K | +$100K |
|---|---|---|---|---|
| Runway months |
Bear case: Growth rate drops 20%, churn increases 50%, no new hires. What is runway? When does cash hit zero? What cuts are required?
Base case: Current growth rate continues, planned hires proceed, churn stays flat. What is runway at 12 months? What is ARR at end of period?
Bull case: Growth rate increases 20%, churn improves 20%, key hires close faster. What is runway at 12 months? When does the company reach default alive?
Every model must document assumptions:
| Assumption | Value Used | Source/Basis |
|---|---|---|
| Monthly growth rate | ||
| Monthly churn rate | ||
| Average ACV | ||
| Gross margin | ||
| Payroll per head | ||
| Hiring plan |
Produce the complete model as structured markdown or CSV. If the model produces more than 40 lines, summarize the key outputs in the CLI and save the full model to finance/model-[date].md. State assumptions clearly before any numbers.
If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Engineering lead — hand Apex any task and it routes internally. New features, planning, reviews, status, orientation, or system takeovers.
The English summary is being prepared. Showing the original description.
Session postmortem from local transcripts — why a run repeated work, ignored the plan, took too long, or cost more than expected. Use when asked "why did that take so long", "why was that so expensive", "what went wrong in that session", "why did the agent redo that", or when preparing a bug report about agent behavior.
The English summary is being prepared. Showing the original description.
Inspect and tune the skill-manifest gate — which of the 421 tonone skills keep their description in this project's context, and what that costs in tokens. Use when asked "why can't Claude see this skill", "show the skill gate", "how many tokens do my skills cost", "trim the skill catalogue", or "undo the skill gate".
The English summary is being prepared. Showing the original description.
Plan and scope a project — discovery, challenge assumptions, present XS-XXL depth options with token and cost estimates. Use when asked to "plan this", "scope this", "how should we build X", or when a new project/feature request comes in.
The English summary is being prepared. Showing the original description.
Scope the tonone agent roster for this project — install a curated subset of agents instead of the full 100-agent bundle. Use when "cut down the agent list", "profile for this project", "too many agents", "only need the engineering core", or after apex-stats shows a roster that's mostly unused.
The English summary is being prepared. Showing the original description.
Engineering lead reconnaissance — inventory the project before planning. Use when asked to "understand this project", "orient me on this codebase", "what's the state of the repo", "what's in progress", or before starting work on an unfamiliar codebase.
The English summary is being prepared. Showing the original description.