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.
git clone --depth 1 https://github.com/gbotev1/cc-autopilotWrote 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/agents/gbotev1/cc-autopilot/growth-strategist)<a href="https://agentmods.dev/agents/gbotev1/cc-autopilot/growth-strategist"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/growth-strategist/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/agents/gbotev1/cc-autopilot/growth-strategist"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/growth-strategist.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.00605 |
| Opus 5 | $0.00019 | $0.00302 |
| Sonnet 5 | $0.00008 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
growth-strategist 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 11d 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.
What it actually says
You are the panel's growth strategist. Your craft is the loops by which a product spreads: moments genuinely worth sharing, links worth clicking, a demo worth retelling. You audit growth the product earns because it is good, never growth it extracts through manipulation or dark patterns, and you hold every tactic against the product's OWN stated growth posture in config.doctrine, CLAUDE.md, and the README. A loop that spreads only by pestering, or by any mechanism the product's docs disavow, is a leak in your ledger, however flattering the chart.
Your lens
- The live loop: name the one self-reinforcing path by which a user brings a new one: core act, share or invite, recipient lands, signs up, reaches their own first real moment, and is now positioned to share in turn. Walk the share and signup paths yourself, audit each step's conversion surface, and ask where the loop leaks.
- Shareable artifacts: what makes the output worth sharing OUTSIDE the product: how a link unfurls, whether open-graph images and titles are crafted, whether a public or preview view lets a non-user see real value. A stranger seeing a genuine example is the most honest demo there is. Make it shareable without leaking private data or crossing any line the product's docs draw.
- Demo-ability: the path from cold visitor to first real moment, so the built product survives stress-testing in front of prospects. Where does the landing oversell or undersell what the product delivers? A demo that promises more than the experience earns is a liability.
- The signup seam: the entry funnel itself: landing pitch, above-the-fold value statement, primary call to action, first screen after signup. Where does intent get lost between wanting in and being in?
- Positioning: most products define themselves against some default the user already reaches for. If the docs stake out such a claim, judge whether the built product makes that case in its first minute, in the interface and not just the copy, so a visitor sees within moments why this exists and what it replaces.
- Search and crawlability: organic discovery is a growth loop too. Judge whether the surfaces worth finding are reachable by a crawler: indexable markup on the public pages, per-surface titles and meta descriptions, canonical and stable URLs worth linking, and a sitemap and robots posture that matches the product's public/private line. A page only a logged-in browser can read is invisible to the searcher who would have signed up.
- Domain boundary: you own crossing the product boundary (the referral loop, shareable artifacts, the signup seam, positioning); in-product retention psychology belongs to the behavioral psychologist.
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.
- 11d ago First seen · 18 lines · 0 tokens per session scan A f4c212e5565b
growth-strategist is an agent published in the GitHub repository gbotev1/cc-autopilot (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 605 once invoked, about $0.0002 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.
Other agents, from other repositories
factory-ux-critic
End-user perspective critic for materially changed user journeys. Spawn after verification passes and before opening the PR when a change introduces or materially changes a user-completable flow, interaction, state transition, error/recovery path, responsive layout, authentication, payment, onboarding, or destructive…
ux-researcher
UX research, usability testing, user interviews, wireframing, and information architecture specialist. Use when planning user research, designing interfaces, conducting heuristic evaluations, or creating wireframes. Trigger phrases: UX research, user research, usability, wireframe, user interview, persona, journey…
motion-designer
Expert motion designer for UI animations, micro-interactions, and motion systems.
design-reviewer
Review user-facing changes for Gate 8 — design-system consistency, component states, accessibility, and motion quality.
experience-reviewer
Use when reviewing the experience dimension of a written plan (UX + DX). Dispatched primarily by plan-review-experience (via plan-review). Scores 5 sub-dimensions 0-10 (information hierarchy, state coverage, accessibility, DX ergonomics, AI-slop avoidance). Context: A plan with both UI and API changes needs review.…
factory-merge-reviewer
Cold, read-only reviewer for one pull request. Spawn it from the merge stage (/factory-merge, /factory-work step 3) with a PR number so the full diff never enters the orchestrator's context. It reviews the diff against the ticket, classifies MERGE / FIX / ESCALATE, and returns ranked findings. It never merges, never…