forecast-hygiene

forecast-hygiene is a skill for Claude Code from Doris-Labs/sales-skills. It costs 60 tokens per session (1,626 once invoked), scanned A, original, MIT.

A pipeline forecast review that checks whether deals are placed in the right forecast category and whether their close dates are credible.

In plain words
What is it for?
Use it to sort deals into Commit, Best Case, or Pipeline, flag risks, and produce a cleaned forecast roll-up.
Why use it?
It exposes unsupported optimism, slipping deals, and inconsistent categories before a forecast or pipeline review.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sales-skills plugin — 30 skills shipped together

Good fit Use it to sort deals into Commit, Best Case, or Pipeline, flag risks, and produce a cleaned forecast roll-up.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/doris-labs/sales-skills/forecast-hygiene
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 Doris-Labs/sales-skills --skill forecast-hygiene
Clone the repo
git clone --depth 1 https://github.com/Doris-Labs/sales-skills

Made for: Claude Code.

Or install sales-skills, the plugin that ships this one along with the rest of its 30 skills.

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-hygiene

README.md
[![agentmods](https://agentmods.dev/badge/skills/doris-labs/sales-skills/forecast-hygiene/github.svg)](https://agentmods.dev/skills/doris-labs/sales-skills/forecast-hygiene)
Your own site
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/forecast-hygiene"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/forecast-hygiene/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-hygiene

Your own site · 80×15
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/forecast-hygiene"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/forecast-hygiene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,626 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 $0.00060 $0.01626
Opus 5 $0.00030 $0.00813
Sonnet 5 $0.00012 $0.00325
Haiku 4.5 $0.00006 $0.00163

Measured 11d ago against content hash 901f1445c39a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

forecast-hygiene 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/forecast-hygiene/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forecast Hygiene

Purpose

Turn a messy pipeline into a forecast you can defend: every deal in the right category for the right reason, close dates that survive scrutiny, slipping and sandbagged deals surfaced, and a cleaned roll-up your manager won't pick apart.

Inputs

  • The current pipeline (CRM export, list, or your recollection): deal, amount, stage, close date, forecast category, owner.
  • The forecast period you're committing to (this month / this quarter).
  • Per-deal context: last activity, next step, and what's actually been agreed.

Method

  1. Apply forecast category discipline. Every open deal lands in exactly one bucket, defined by a hard bar — not by gut feel:

    • Commit — you would bet your number on it. Mutually agreed close plan, buyer has confirmed timing, budget is real, and the only remaining steps are ones you control or are already scheduled. If it slips, you owe an explanation.
    • Best case — credible path to close this period, but a dependency you don't control is open (legal, procurement, a stakeholder not yet bought in, a step not yet scheduled). Upside, not your number.
    • Pipeline — qualified and progressing, but won't close this period or the path isn't proven. Not in the forecast.
    • Omitted/closed — no realistic path; stop carrying it.
  2. Run the evidence test on every Commit. A deal is only Commit if you can name, for each, the artifact that proves it:

    • Confirmed close date — buyer said it, ideally in writing, tied to a business event.
    • Economic buyer engaged — not just a champion relaying messages.
    • Defined buying process with no unknown steps to signature.
    • Paper/procurement path known and started, or known not to apply.
    • No unresolved objection or competitor that could reset the cycle. If any answer is "I think" or "should be," it's Best case, not Commit.
  3. Close-date sanity checks. Reject any close date that is:

    • In the past, or default end-of-month/end-of-quarter with no buyer confirmation.
    • Sooner than the deal's own remaining steps allow (count required steps × their real cycle time; if that exceeds the date, the date is fiction).
    • Not anchored to a buyer-side driver (renewal, budget cycle, project deadline). Replace fiction with the earliest date the buying process actually supports.

Read the full file on GitHub · 128 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 · 128 lines · 60 tokens per session scan A 901f1445c39a

Subscribe to this mod's changes

forecast-hygiene is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 60 tokens to every session and 1,626 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.