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 etrebels/claude-code-growth-os --skill churn-savegit clone --depth 1 https://github.com/etrebels/claude-code-growth-osWrote 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/etrebels/claude-code-growth-os/churn-save)<a href="https://agentmods.dev/skills/etrebels/claude-code-growth-os/churn-save"><img src="https://agentmods.dev/badge/skills/etrebels/claude-code-growth-os/churn-save.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.00677 |
| Opus 5 | $0.00042 | $0.00338 |
| Sonnet 5 | $0.00017 | $0.00135 |
| Haiku 4.5 | $0.00008 | $0.00068 |
Grade A, and why
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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Churn Save
The act-skill on the right side of the bowtie. account-health detects — it scores the account and writes the RETENTION-RISK line; this one acts on it. The split mirrors the left side, where lead-qualify scores and the pursuit skills work the deal. A save is re-earning the outcome the customer bought — not sending a warmer email.
From the at-risk row in ops/customers.md, the RETENTION-RISK line that flagged it, and any recent notes:
- Name the real risk, not the symptom. The cancellation is the lagging indicator; the cause is upstream — usage trending down, the champion gone quiet, a single-threaded account after a reorg, or the value the deal was sold on never landing. Separate the one that's actually moving from the noise.
- Time the motion. The renewal clock starts at day 60, not day 85. If the renewal date is inside 60 days, the save runs now, in parallel with the renewal — don't let the contract surface the risk for you.
- Re-thread if it's single-threaded. If one name carried the account and that name went quiet, the save is a second relationship, not a better message to the first. Name who else to reach, and why they'd care.
- Draft the re-engagement. Lead with their outcome — the metric the deal was bought to move — not "just checking in". One concrete next step, with a date. Offer to debrief any reply with
follow-up. - Route the cause if it's a product gap. If a missing capability is what's blocking value, that's a
RETENTION-RISK/FEATURE-REQUESTfor product — hand it on withproduct-signalso the save and the roadmap move together (handoff H4 indocs/operating-model.md). - Log the play and update the book. Record the play and its outcome; update the account's stage, signal, and next step in
ops/customers.md. If it's lost anyway, log the real reason —/retention-report's churn-by-reason read depends on it.
Don't paper a value miss over with a nicer email; a save the customer can see through costs you the reference too. And don't tag every quiet week as a churn — a book full of false alarms gets ignored.
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.
- 7d ago First seen · 25 lines · 84 tokens per session scan A eb2ff0702448
churn-save is a skill published in the GitHub repository etrebels/claude-code-growth-os (20 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 677 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 2026-08-30.
Other skills, from other repositories
startup-launch-playbook
A step-by-step playbook for early-stage startups going from pre-seed to their first 1000 users. Covers MVP validation, initial traction channels, and founder-led growth tactics. By @WeiYipei — follow on X for more startup growth insights.
four-ps-marketing
Designs and audits marketing strategy using McCarthy and Kotler's Four Ps framework: Product, Price, Place, and Promotion. Evaluates coherence across all four marketing mix elements to identify misalignments that undermine go-to-market effectiveness. Use when launching a new product, diagnosing why conversion rates…
forbotsake
Marketing skills for Claude Code. From zero marketing knowledge to published content. Run /forbotsake to set up all marketing skills, check installation health, or get routed to the right skill. Use when: "forbotsake", "install forbotsake", "marketing skills", "how should I market this", "help me sell this".
forbotsake-cron
Autopilot mode for forbotsake. Installs a cron job that auto-posts reviewed content on schedule using Claude Code + Chrome. Content-calendar.md drives the timing. Subcommands: install, status, uninstall, pause, resume, doctor, run-now. Use when: "auto-post", "schedule posts", "autopilot", "cron", "forbotsake-cron"…
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
ads
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad…