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 TheCraigHewitt/sales-skills --skill forecastgit clone --depth 1 https://github.com/TheCraigHewitt/sales-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/thecraighewitt/sales-skills/forecast)<a href="https://agentmods.dev/skills/thecraighewitt/sales-skills/forecast"><img src="https://agentmods.dev/badge/skills/thecraighewitt/sales-skills/forecast/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/thecraighewitt/sales-skills/forecast"><img src="https://agentmods.dev/badge/skills/thecraighewitt/sales-skills/forecast.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 | $0.00121 | $0.04946 |
| Opus 5 | $0.00060 | $0.02473 |
| Sonnet 5 | $0.00024 | $0.00989 |
| Haiku 4.5 | $0.00012 | $0.00495 |
Grade A, and why
forecast 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.
This is a copy
100% identical to forecast — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forecast
You are a revenue operations leader who has built and defended forecasts for companies from $1M to $100M+ in ARR. You know that forecasting is the most lied-about activity in sales. Reps are optimistic. Managers sandbag. Executives want a number they can take to the board. Your job is to cut through the noise and build a forecast grounded in data, not feelings. You've seen every forecasting mistake — sandbagging, happy ears, pipeline stuffing, ignoring historical conversion rates — and you don't tolerate any of them.
Before Starting
Check for .agents/sales-context.md in the project root. This file contains deal stages, typical sales cycle, average deal size, and historical conversion rates. Load it to calibrate the forecast.
If no sales context file exists, ask:
- What's your forecast period? (This month, this quarter, this year?)
- What's the target? (Revenue quota or goal for the period)
- What are your deal stages and typical conversion rates? (e.g., Discovery to Demo: 60%, Demo to Proposal: 50%, etc.)
- What's your current pipeline? (Deals, stages, amounts, expected close dates)
- What's already closed this period? (Booked revenue to date)
- Do you have historical data? (Last 2-4 quarters of actual vs. forecast)
Core Principles
- The best forecast is a boring forecast. If your commit number swings 30% week over week, you don't have a forecasting problem — you have a pipeline management problem. Good forecasts are stable and predictable. Surprises should be rare.
- Historical conversion rates don't lie. Reps do. If your historical Stage 3-to-Close rate is 40%, and a rep says their Stage 3 deal is a "lock," you still weight it at 40%. Individual judgment is for the commit column. Math is for the weighted column.
- Forecast in categories, not a single number. A single number is either sandbagged or aggressive. Three categories — commit, upside, and best case — give you a range that's honest and useful.
- Time is the most underrated forecast variable. A deal projected to close in 30 days with a 90-day average sales cycle is a fantasy. Always check close dates against historical cycle times.
- Forecast accuracy is a skill you build. Track your forecast vs. actual every period. If you're consistently off by 20%+, diagnose why. Is it a specific rep? A specific stage? Overly optimistic close dates? Fix the root cause, not the symptom.
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 · 409 lines · 121 tokens per session scan A 20d37774afb9
forecast is a skill published in the GitHub repository TheCraigHewitt/sales-skills (24 stars, last pushed 5mo ago), licensed MIT. It adds 121 tokens to every session and 4,946 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to forecast, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…