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 retention-feedbackgit 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/retention-feedback)<a href="https://agentmods.dev/skills/etrebels/claude-code-growth-os/retention-feedback"><img src="https://agentmods.dev/badge/skills/etrebels/claude-code-growth-os/retention-feedback.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00086 | $0.00704 |
| Opus 5 | $0.00043 | $0.00352 |
| Sonnet 5 | $0.00017 | $0.00141 |
| Haiku 4.5 | $0.00009 | $0.00070 |
Grade A, and why
retention-feedback 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retention Feedback
The loop that keeps the post-sale half of the motion connected to product — the half the funnel forgets. Sales→marketing is the loop everyone can see; this is its mirror on the right side of the bowtie. Field intelligence from onboarding, adoption, and renewal flows back to product and CS on a cadence, instead of dying in a QBR. This is the four-function version of the alignment thesis in docs/why-align.md — made concrete as a tagged line in the same shared log the marketing-feedback skill writes to.
From a source — an onboarding note, a usage review, a support thread, a renewal call, a deal update:
- Scan for the four signal types:
- Adoption friction — where customers stall between signing and getting value (the workflow they never turned on, the setup step that blocks them).
- Churn risk — the real leading indicator: usage trending down, a champion gone quiet, a single-threaded account after a reorg.
- Expansion blocker / signal — a missing feature that's holding back a renewal or a second department; or, the opposite, a customer asking for more unprompted.
- Renewal-loss reason — the real one, logged, not remembered (people misdiagnose why accounts leave as often as why deals are lost).
- Log each as a tagged line in
ops/feedback-log.md— the same single home marketing's tags use — so product and CS can act without a meeting:RETENTION-RISK: [account] — [the adoption/churn/blocker signal] → [product or CS action]EXPANSION-SIGNAL:when a healthy account is ready to grow (hand to sales with the CS context attached).
- Route, don't dump. A feature request that blocks adoption goes to the roadmap, not the backlog void. A churn signal triggers the renewal motion early — day 60, not day 85. Don't tag every quiet week as a risk; tag it when usage, the champion, or the value story is actually slipping.
The tag is the hand-off. One file — the same one marketing reads — now carries both loops, so a post-sale signal can't quietly die any more than a field objection can. Product's job is to clear the RETENTION-RISK lines that are really roadmap; CS's job is to keep them honest and act on the renewal clock.
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 · 28 lines · 86 tokens per session scan A b1c176b4bc6a
retention-feedback is a skill published in the GitHub repository etrebels/claude-code-growth-os (20 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 704 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…