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 AIDevGTM/gtm-cofounder --skill 18-growth-loopsgit clone --depth 1 https://github.com/AIDevGTM/gtm-cofounderWrote 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/aidevgtm/gtm-cofounder/18-growth-loops)<a href="https://agentmods.dev/skills/aidevgtm/gtm-cofounder/18-growth-loops"><img src="https://agentmods.dev/badge/skills/aidevgtm/gtm-cofounder/18-growth-loops/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.
<a href="https://agentmods.dev/skills/aidevgtm/gtm-cofounder/18-growth-loops"><img src="https://agentmods.dev/badge/skills/aidevgtm/gtm-cofounder/18-growth-loops.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00080 | $0.01961 |
| Opus 5.5 | $0.00032 | $0.00784 |
| Sonnet 5.5 | $0.00016 | $0.00392 |
| Haiku 4.5 | $0.00008 | $0.00196 |
Grade A, and why
growth-loops 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 19d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Growth loops (the next 5,000 without you)
You got your first 50 users by hand: DMs, favors, one good launch. That was the right way to get them, and it was never supposed to scale. A growth loop is what comes next: one user's ordinary use of the product exposes it to the next user, and that user repeats it. Not a one-time referral; a continuous cycle.
Use this when: growth flatlines every time you stop posting, you can trace every user to a founder DM or a launch day, or you're about to add a third channel when the users you already have produce zero new ones.
The core idea
A channel is linear: effort in, users out, stop pushing and it stops. A loop feeds output back into input: usage creates an artifact, a public trace, or an invitation that a new developer finds, and that developer's usage restarts the cycle. Channels deplete; loops compound.
The rule that keeps it non-slimy: every loop must do the user a service, not just you. A branded report the user is proud to send is a loop; a watermark they resent is spam with extra steps. If the loop degrades the experience, it is not a loop, it is a leak in your trust.
The gate: a loop amplifies whatever you feed it. If week-2 retention is broken, a loop compounds churn, not growth. Before this skill: first value in under an hour (time-to-first-value), first 50 real users in hand (first-50-users), and cohorts that come back (know-if-its-working, Frankl's net developer retention). If any of those fail, that failure is your Now move, not this.
The dev-tool loop catalog
Six loops that actually work for developer tools. You need one, running at full strength.
- Showcase loop. The product's output is shareable and carries your name with it: a CodePen link, an exported report with the logo intact, a "Generated by X" footer on docs. crowd.dev's exported community health reports carried the branding; recipients asked how the report was made, and that question was the signup.
- Badge loop. A status signal developers want in their README: "build passing" (Travis CI, CircleCI), coverage percent (Codecov). Every visitor to every repo that uses you sees a micro-advertisement, and the badge earns its place by signaling quality, not by begging.
- Workflow loop. The tool acts inside a shared workflow where non-users see it working. Snyk auto-opens pull requests with vulnerability fixes; every collaborator reviews that PR, discovers the tool, and signs up. A bot comment on a fixed issue, a summary email a dev forwards to the team: same mechanics.
- Team loop. One developer adopts, and the tool lands in a shared repo, a CI pipeline, or a lockfile every collaborator now touches. Then it walks out the door when a dev changes jobs and installs it on day one. The qualifying question: does the tool become more useful when more people use it together? If yes, build the invite into onboarding, not into a popup.
- Public-content loop. Usage produces content strangers find: user-created projects and collections browsable in public (StackBlitz, Postman's public workspaces), community answers that stay indexed instead of dying in a ticket, and the tutorials their questions teach you to write (
founder-led-contentis this loop's fuel). - Marketplace loop. Live where developers already shop: a VS Code extension, a Jenkins plugin, a framework's starter gallery, GitHub's own surfaces (trending, "used by", dependents). Every new user of their platform can now discover yours.
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.
- 19d ago Changed · +1 lines 5c8df528d361
- 2mo ago First seen · 82 lines · 80 tokens per session scan A 7da036044ca5
growth-loops is a skill published in the GitHub repository AIDevGTM/gtm-cofounder (333 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 1,961 once invoked, about $0.0003 per session on Opus 5.5. 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
git-phase-restore
Autonomous Git-based project phase restoration. Uses Git history (commits, tags, branches, diffs, semantic messages) to identify and restore any development phase automatically. Trigger for: "restore to when X worked", "go back to before Y broke", "show project phases", "undo the last feature", "roll back to [phase]"…
github-actions-trigger
Trigger GitHub Actions workflows from Claude Code. Auto-run tests, deploy, or validate when skills like run-pre-commit-checks complete.
e2b-sandboxes
E2B open-source cloud sandboxes for executing AI-generated code securely. USE FOR: run code in sandbox, e2b, code interpreter, execute AI code, secure code execution, isolated environment, AI coding agent execution, run untrusted code, cloud sandbox, code execution API, python sandbox cloud, AI agent code runner, safe…
screenshot-automation
Automatically captures, crops, and beautifies screenshots from URLs for your portfolio or docs.
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.