forecast-accuracy-tracking

forecast-accuracy-tracking is a skill for Claude Code, Codex from gokulb20/crewm8-cfo-skills. It costs 86 tokens per session (2,776 once invoked), scanned A, original, MIT.

A process for comparing past forecasts with the results that actually happened. It measures errors over time and looks for forecast bias, such as repeatedly overestimating sales or underestimating customer loss.

In plain words
What is it for?
Use it to review forecast-versus-actual results, investigate missed targets, measure forecast accuracy, and improve the forecasting process.
Why use it?
It shows whether forecasts are improving and identifies recurring reasons they are wrong. This helps teams make decisions using more reliable estimates.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: positional $N argument; built for openclaw.

Good fit Use it to review forecast-versus-actual results, investigate missed targets, measure forecast accuracy, and improve the forecasting process.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gokulb20/crewm8-cfo-skills/forecast-accuracy-tracking
Install

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.

Any agent
npx skills add gokulb20/crewm8-cfo-skills --skill forecast-accuracy-tracking
Clone the repo
git clone --depth 1 https://github.com/gokulb20/crewm8-cfo-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for forecast-accuracy-tracking

README.md
[![agentmods](https://agentmods.dev/badge/skills/gokulb20/crewm8-cfo-skills/forecast-accuracy-tracking/github.svg)](https://agentmods.dev/skills/gokulb20/crewm8-cfo-skills/forecast-accuracy-tracking)
Your own site
<a href="https://agentmods.dev/skills/gokulb20/crewm8-cfo-skills/forecast-accuracy-tracking"><img src="https://agentmods.dev/badge/skills/gokulb20/crewm8-cfo-skills/forecast-accuracy-tracking/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.

agentmods 80×15 button for forecast-accuracy-tracking

Your own site · 80×15
<a href="https://agentmods.dev/skills/gokulb20/crewm8-cfo-skills/forecast-accuracy-tracking"><img src="https://agentmods.dev/badge/skills/gokulb20/crewm8-cfo-skills/forecast-accuracy-tracking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,776 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00086 $0.02776
Opus 5 $0.00043 $0.01388
Sonnet 5 $0.00017 $0.00555
Haiku 4.5 $0.00009 $0.00278

Measured 11d ago against content hash 5d1cdb511ca5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

forecast-accuracy-tracking 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.

skills/financial-planning-analysis/forecast-accuracy-tracking/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forecast Accuracy Tracking

Measure how good the company's forecasts actually are. Track forecast vs actuals over time, identify where and why you're consistently wrong, and improve the forecasting process. Goal: forecasts get more accurate over time, not less, and the business learns from its mistakes.

Purpose

Most startups track whether they hit their plan, but almost none track whether their forecasts are actually getting better. Systematic forecasting errors — consistently overestimating new logo revenue, consistently underestimating churn — compound over time and lead to bad decisions. This skill provides the methodology to measure forecast accuracy, identify persistent biases, and improve the process so decisions are made on increasingly reliable numbers.

When to Use

  • "How accurate were our forecasts?"
  • "Track forecast vs actuals over time"
  • "Why were we off last quarter?"
  • "Improve our forecasting process"
  • "What's our forecast track record?"
  • "Analyze forecast bias"

Inputs Required

  1. Historical forecasts — for each forecasting exercise: what was forecast, when, for what period, and the forecast value.
  2. Actual results — the realized values for each forecasted metric (revenue, costs, cash, headcount).
  3. Forecast assumptions — the key assumptions that drove each forecast (growth rate, churn, hiring velocity, etc.).
  4. Contextual notes — what was happening in the business when each forecast was made (new product launch, market shift, team changes).

Quick Reference

Metric Formula Target
MAPE Average of |Actual − Forecast| / |Actual| across periods < 10% excellent, 10-25% decent
Forecast Bias Average of (Forecast − Actual) / Actual Near 0 (neutral)
FE (Forecast Error) Actual − Forecast Positive = conservative, Negative = optimistic
Horizon MAPE MAPE broken out by 1mo/3mo/6mo/12mo horizons Higher for longer horizons
MAPE Range Interpretation
< 10% Excellent forecasting
10-25% Decent — room for improvement
25-50% Concerning — systematic issues likely
> 50% Forecasting is essentially guessing

Read the full file on GitHub · 226 lines

Changes

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.

  1. 11d ago First seen · 226 lines · 86 tokens per session scan A 5d1cdb511ca5

Subscribe to this mod's changes

forecast-accuracy-tracking is a skill published in the GitHub repository gokulb20/crewm8-cfo-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 86 tokens to every session and 2,776 once invoked, about $0.0004 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.

Related

Other skills, from other repositories