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.
npx skills add pbc-os/smb-starter-kit --skill revenue-forecastergit clone --depth 1 https://github.com/pbc-os/smb-starter-kitWrote 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.
[](https://agentmods.dev/skills/pbc-os/smb-starter-kit/revenue-forecaster)<a href="https://agentmods.dev/skills/pbc-os/smb-starter-kit/revenue-forecaster"><img src="https://agentmods.dev/badge/skills/pbc-os/smb-starter-kit/revenue-forecaster/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.
<a href="https://agentmods.dev/skills/pbc-os/smb-starter-kit/revenue-forecaster"><img src="https://agentmods.dev/badge/skills/pbc-os/smb-starter-kit/revenue-forecaster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.03204 |
| Opus 5 | $0.00032 | $0.01602 |
| Sonnet 5 | $0.00013 | $0.00641 |
| Haiku 4.5 | $0.00006 | $0.00320 |
Grade A, and why
revenue-forecaster 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Revenue Forecaster
Predict next week's revenue. Project 13 weeks of cash. Stress-test scenarios. Tune it yourself with autoresearch.
Most SMB forecasting is either a gut number or a wild spreadsheet. This skill gives your agent a real parametric forecast model that handles the things that actually matter for small businesses:
- Multiple locations or product lines with independent per-entity parameters (each location has its own holiday patterns, growth rate, and week-of-month quirks)
- Holiday multipliers (Thanksgiving, Christmas, New Year's, MLK, July 4th, etc.)
- Week-of-month patterns (some businesses spike on pay weeks; some dip early in the month)
- Outlier trimming so one anomalous holiday doesn't inflate the recent average
- Exponential decay on recent weeks for businesses with fast-changing volume
- YoY growth blending when you have enough history
- Graceful fallback when you don't — the same model runs with or without YoY data
- Autoresearch integration — the skill ships with a fixed eval script and a parameters file so you can autoresearch your way to lower MAPE on your own data
Triggers
- "forecast revenue", "predict sales", "how much will we make"
- "weekly forecast", "this week's forecast"
- "13 week forecast", "13-week cash projection", "cash runway"
- "daily forecast", "how much on Friday"
- "stress test", "what if sales drop"
- "tune the forecast", "improve forecast accuracy"
Prerequisites
- Historical revenue data in weekly buckets per entity. Minimum usable: 8 weeks. Good: 6+ months. Great: 1+ year (unlocks YoY blending).
- Python 3.9+ with the standard library — no pandas/numpy required.
- A way to feed the data to the scripts. The built-in adapter reads CSV; see
references/data-adapters.mdfor Google Sheets, BigQuery, and Square API patterns.
Quick Start
-
Bring your data — Export a CSV with three columns:
week_start,entity,revenue 2025-10-06,Main Street,48350.00 2025-10-06,Downtown,32110.00 2025-10-13,Main Street,51200.00 ...
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/data-adapters.md 8.7 KB
- references/methodology.md 11 KB
- scripts/eval.py 7.5 KB runs code
- scripts/forecast.py 13 KB runs code
- scripts/model.py 11 KB runs code
- scripts/utils.py 3.2 KB runs code
- templates/history-example.csv 819 B
- templates/parameters.json 3.0 KB
- templates/research.md 4.8 KB
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.
- 11d ago First seen · 270 lines · 63 tokens per session scan A 08af68f24e48
revenue-forecaster is a skill published in the GitHub repository pbc-os/smb-starter-kit (10 stars, last pushed 3mo ago), licensed MIT. It adds 63 tokens to every session and 3,204 once invoked, about $0.0003 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.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.