renewal-churn-save

renewal-churn-save is a skill for Claude Code from Doris-Labs/sales-skills. It costs 62 tokens per session (1,725 once invoked), scanned A, original, MIT.

A guide for saving a customer relationship when a contract renewal is at risk, by examining usage, sentiment, stakeholders, and the results delivered since purchase.

In plain words
What is it for?
Use it to assess renewal risk, summarize return on investment, re-engage decision-makers, create a customer save plan, and assign owners and dates.
Why use it?
It turns warning signs such as declining use, a lost internal advocate, or negative feedback into a concrete plan to address the root problem and prove value.

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 assess renewal risk, summarize return on investment, re-engage decision-makers, create a customer save plan, and assign owners and dates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/doris-labs/sales-skills/renewal-churn-save
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 renewal-churn-save
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 renewal-churn-save

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/renewal-churn-save"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/renewal-churn-save.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,725 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 $0.00062 $0.01725
Opus 5 $0.00031 $0.00863
Sonnet 5 $0.00012 $0.00345
Haiku 4.5 $0.00006 $0.00172

Measured 12d ago against content hash 6f9ba10dd77d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

renewal-churn-save 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 12d 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/renewal-churn-save/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Renewal & Churn Save

Purpose

Catch a renewal that's slipping before it's lost. Read the risk signals, build a value-realization recap that proves ROI delivered since purchase, and run a save play that re-engages the economic buyer, fixes the root issue, and re-anchors the relationship on outcomes — then ship a save plan with an owner and dates.

Inputs

  • The account and its renewal date (and current ARR / contract terms)
  • Usage / health signals since last renewal (logins, seats active, feature adoption)
  • Who the champion and economic buyer are, and whether either has changed
  • Recent sentiment: support tickets, escalations, tone on calls/emails
  • What the customer originally bought this to fix (the purchase thesis)

Method

1. Score the renewal risk

Run every signal against this checklist. Two or more red flags = at-risk; treat the renewal as active opportunity work, not an admin renewal.

Signal Red flag looks like
Usage trend Logins/active seats declining month-over-month; key feature never adopted
Champion Champion left, changed roles, or went quiet; no internal advocate left
Sentiment Negative tone on calls, frustrated tickets, NPS/CSAT drop
Responsiveness Emails/calls unanswered; meetings rescheduled or skipped
Support Open escalations, repeat tickets on the same issue, unresolved SLA breach
Economic buyer No exec engagement in 90+ days; budget owner unknown or changed

Classify: Green (renew on autopilot), Yellow (one signal — pre-empt), Red (two+ signals — full save play).

2. Build the value-realization recap

You cannot save a renewal without proving the customer got what they paid for. Assemble:

  • The purchase thesis — what problem they bought this to solve, in their words.
  • What's been delivered — concrete outcomes since go-live: time saved, deals influenced, tickets deflected, revenue touched. Quantify everything you can.
  • Adoption proof — who uses it, how often, which workflows it now runs.
  • The gap — honestly name where value has NOT landed yet, and why (this earns trust and sets up the fix).

Read the full file on GitHub · 146 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. 12d ago First seen · 146 lines · 62 tokens per session scan A 6f9ba10dd77d

Subscribe to this mod's changes

renewal-churn-save is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 1,725 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.