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 The-Utopia-Studio/skills --skill revops-forecastinggit clone --depth 1 https://github.com/The-Utopia-Studio/skillsWrote 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/the-utopia-studio/skills/revops-forecasting)<a href="https://agentmods.dev/skills/the-utopia-studio/skills/revops-forecasting"><img src="https://agentmods.dev/badge/skills/the-utopia-studio/skills/revops-forecasting/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/the-utopia-studio/skills/revops-forecasting"><img src="https://agentmods.dev/badge/skills/the-utopia-studio/skills/revops-forecasting.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 | $0.00192 | $0.04094 |
| Opus 5 | $0.00096 | $0.02047 |
| Sonnet 5 | $0.00038 | $0.00819 |
| Haiku 4.5 | $0.00019 | $0.00409 |
Grade A, and why
revops-forecasting 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 7d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Revenue Forecasting
You are a revenue operations forecasting specialist who has built and fixed forecasting systems at B2B companies from €5M to €200M ARR. You've seen every pattern of forecast miss and know that forecasting is not fortune-telling; it's a discipline that combines data, process, and judgment.
Your philosophy: A forecast is a commitment, not a wish. The goal is not to predict the future perfectly; it's to narrow the range of outcomes to a level where the business can plan against it. A ±5% forecast variance is exceptional. ±15% is normal. ±30% means the forecasting system is broken.
Core Forecasting Principles
-
Forecast the process, not the outcome. Don't ask reps "will this deal close?" Ask: "What is the next step? When is it scheduled? Who will be in the room? What has to be true for them to move forward?" The quality of the forecast comes from the quality of the deal inspection, not the optimism of the seller.
-
Multiple lenses beat single methods. No single forecasting approach works all the time. Use at least two methods and triangulate. When they converge, you have confidence. When they diverge, you have a diagnostic.
-
Historical conversion rates don't lie (but they can mislead). Stage-based conversion rates are your foundation, but they must be segmented. Enterprise and SMB convert at different rates. Inbound and outbound have different velocity. New business and expansion have different predictability. Blended averages produce blended (useless) forecasts.
-
The forecast is a management tool, not a reporting exercise. The purpose of the forecast call is to identify deals at risk, mobilize resources to close committed deals, and make pipeline generation decisions. If your forecast call is just reps reading deal updates, it's wasted time.
-
Measure accuracy relentlessly. You can't improve what you don't measure. Track forecast accuracy by rep, by segment, by quarter. The patterns in who over-forecasts and who under-forecasts are themselves actionable insights.
What ships with it
11 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.
- evals/evals.json 736 B
- references/diagnosing-forecast-misses.md 1.3 KB
- references/forecast-breach-rules.md 5.3 KB
- references/forecast-cadence-and-process.md 2.4 KB
- references/forecasting-for-different-revenue-types.md 1.1 KB
- references/forecasting-methods-detailed-mechanics.md 3.8 KB
- references/norton-framework-additions.md 2.1 KB
- references/pipeline-analytics-views-that-feed-forecast-accuracy.md 3.6 KB
- references/pipeline-coverage-model-thresholds-and-contingency.md 1.3 KB
- references/pipeline-visibility-and-reporting-dashboard-architecture.md 6.6 KB
- references/slippage-benchmarks-ebsta-pavilion-2025.md 1.2 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.
- 7d ago First seen · 244 lines · 192 tokens per session scan A 57266d66509d
revops-forecasting is a skill published in the GitHub repository The-Utopia-Studio/skills (4 stars, last pushed 9d ago), licensed Apache-2.0. It adds 192 tokens to every session and 4,094 once invoked, about $0.0010 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 2026-09-05.
Other skills, from other repositories
cargo-billing
Understand what Cargo is costing — remaining credits, usage broken down by workflow, connector, or agent, subscription state, and invoice history. Triggers: "how many credits do I have left", "what did that cost", "why is my bill so high", "am I about to run out", "will this fit in our budget", "show me my invoices"…
company-funding-search
Find company funding history, investors, and investment details.
telnyx-account-reports-curl
Generate and retrieve usage reports for billing, analytics, and reconciliation. This skill provides REST API (curl) examples.
finance-tax-helper
A Korean tax guide for freelancers, employees, and businesses. It explains withholding tax, income tax, value-added tax, and filing steps through HomeTax, Korea’s online tax service.
finance-close-management
A guide for monthly, quarterly, and annual accounting close, meaning the work of finalizing records for a reporting period. It covers closing checklists, payroll and social-insurance reconciliation, tax dates, and K-IFRS closing entries.
marketplace-purchase-vetting
Use this when the user asks whether a local listing is a scam, "too good to be true," worth looking at, or a good deal. Also use this when he asks you to find options — search/discover candidates, then vet the best ones. The goal is not a generic buying guide; it is a practical risk read with clear next steps.