crm-hygiene

crm-hygiene is a skill for Claude Code from jaredlangleycc/nightshift-os. It costs 135 tokens per session (4,027 once invoked), scanned A, original, MIT.

A review of customer and deal records in a CRM, the system used to track contacts, sales opportunities, and their progress. It works with a HubSpot, Google Sheet, or Notion-based CRM according to the configured setup.

In plain words
What is it for?
Use it to audit contacts and deals, find opportunities that have not moved, identify duplicates, check required fields, or review whether won deals have supporting payment records.
Why use it?
It reveals stale deals, duplicate contacts, missing information, and records whose status is not supported by related data, so the user can correct them.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; positional $N argument.

Part of the nightshift-os plugin — 43 skills shipped together

Good fit Use it to audit contacts and deals, find opportunities that have not moved, identify duplicates, check required fields, or review whether won deals have supporting payment records.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jaredlangleycc/nightshift-os/crm-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 jaredlangleycc/nightshift-os --skill crm-hygiene
Clone the repo
git clone --depth 1 https://github.com/jaredlangleycc/nightshift-os

Made for: Claude Code.

Or install nightshift-os, the plugin that ships this one along with the rest of its 43 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 crm-hygiene

README.md
[![agentmods](https://agentmods.dev/badge/skills/jaredlangleycc/nightshift-os/crm-hygiene/github.svg)](https://agentmods.dev/skills/jaredlangleycc/nightshift-os/crm-hygiene)
Your own site
<a href="https://agentmods.dev/skills/jaredlangleycc/nightshift-os/crm-hygiene"><img src="https://agentmods.dev/badge/skills/jaredlangleycc/nightshift-os/crm-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 crm-hygiene

Your own site · 80×15
<a href="https://agentmods.dev/skills/jaredlangleycc/nightshift-os/crm-hygiene"><img src="https://agentmods.dev/badge/skills/jaredlangleycc/nightshift-os/crm-hygiene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,027 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00135 $0.04027
Opus 5 $0.00068 $0.02014
Sonnet 5 $0.00027 $0.00805
Haiku 4.5 $0.00014 $0.00403

Measured 9d ago against content hash 6c1e961da067, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

crm-hygiene scanned grade A with 1 finding 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 9d 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.

Strips warnings and disclaimerslowAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

A CRM with 50 dirty records is not a crisis. It is one Friday of work. Triage and move. Do not lecture.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/ops/crm-hygiene/SKILL.md · 413 lines

How it starts

The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRM Hygiene

The CRM cleanup skill. Finds the rot. The user fixes it.

Solopreneurs do not lose deals to bad selling. They lose deals to bad CRM hygiene: the prospect who slipped into "stage 3" five weeks ago and never moved, the duplicate contact created on a second form-fill, the deal marked won with no payment row to back it up. Crm-hygiene is the audit that makes the rot visible.

When this skill triggers

  • /crm-hygiene
  • "Clean up my CRM"
  • "Audit my contacts"
  • "Find stale deals"
  • "Dedupe my contacts"
  • "Deals review"
  • "Fix my CRM"
  • "Find deals with missing fields"
  • Inside /ship-it-friday as a monthly check (first Friday of each month)
  • Inside weekly-brief as a light stale-deal flag (under 60 seconds, stale-deal count only)

Adapting to the user's CRM

Read CLAUDE.md > Stack > CRM. Adapt the data source based on what the user has.

Priority 1: HubSpot

If the user has crm: HubSpot in stack and the HubSpot MCP is connected, use:

  • search_objects for contacts and deals with property filters
  • get_properties to confirm custom fields exist before querying
  • Query both pipelines if configured (e.g., organic + accelerator)

Priority 2: Google Sheet

If the user has crm: Google Sheet in stack, read the sheet via the configured method (Google Sheets MCP if connected, or instruct the user to export to CSV).

Expected columns (from examples/crm-sheet-template.csv):

contact_id, name, email, company, role, source, first_touch_at, last_touch_at,
stage, owner, next_action, next_action_date, deal_value, notes

Priority 3: Notion

If the user has crm: Notion in stack and the Notion MCP is connected, query the database.

Priority 4: Manual

If no CRM is connected or accessible, ask: "Drop your top 20 active prospects and current stages. I'll run the hygiene on what you share."

Do not fabricate CRM data.

The seven hygiene checks

Run all seven by default. Each produces a row in the hygiene report. The user picks which to fix.

Read the full file on GitHub · 413 lines

Files

What ships with it

4 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.

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. 9d ago First seen · 413 lines · 0 tokens per session scan A 6c1e961da067

Subscribe to this mod's changes

crm-hygiene is a skill published in the GitHub repository jaredlangleycc/nightshift-os (3 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 4,027 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (strips warnings and disclaimers). 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

Brand Guidelines Generator

Create and maintain brand style guides for consistent visual identity.

claude-office-skills/skills · 14 tokens

web-vid

Turn a web app or marketing site into a recreated (not screen-recorded) Remotion promo video — pixel-faithful to the site's own design system, choreographed clicks/scrolls/zooms, rendered to MP4. Use when the user asks for a product demo video, a promo/teaser for LinkedIn or social, an "walkthrough video" of their…

naidx0/web-vid · 145 tokens

pitchdocs

Generate marketing-quality repository documentation from codebase analysis. Scans 10 signal categories, extracts features with file-level evidence, and produces README, CHANGELOG, ROADMAP, and 15+ more docs. Zero runtime dependencies. For AI context file management, see ContextDocs.

littlebearapps/pitchdocs · 58 tokens

demo-video-factory

Generate a custom 26s product-demo video from any SaaS URL — brand-matched scenes, a recreated product-UI "wow" scene, real screenshots, and a soundtrack. Use whenever the user wants a demo, promo, launch, or marketing video for a website or product.

jonny-1812/demo-video-factory · 63 tokens

brand

Brand context management for marketing sessions with continuity across conversations.

itsbariscan/claude-code-marketing · 12 tokens

liking-factor-engineer

Analyze and engineer liking to increase rapport, persuasion, and compliance in marketing, sales, and communication contexts. Use this skill when the user wants to improve how much an audience likes them, their brand, or their message — including writing sales copy, designing onboarding flows, crafting brand voice…

bookforge-ai/bookforge-skills · 175 tokens