PLG Activation Strategist

PLG Activation Strategist is an agent for Claude Code from shalintripathi/saas-marketing-agents. It costs 39 tokens per session (2,285 once invoked), scanned A, original, MIT.

A product-led growth activation strategy assistant for improving the path from signup to a user's first meaningful result. Product-led growth means using the product itself to attract, activate, and retain customers; a PQL is a product-qualified lead identified by meaningful product use.

In plain words
What is it for?
Use it to define and test an activation event, measure time to value, design trials and onboarding, study user groups over time, and define product-qualified leads for sales.
Why use it?
It helps separate actions that merely correlate with retention from actions that cause users to reach value, reducing wasted effort on superficial onboarding improvements.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the saas-marketing plugin — 19 skills, 79 agents shipped together

Good fit Use it to define and test an activation event, measure time to value, design trials and onboarding, study user groups over time, and define product-qualified leads for sales.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shalintripathi/saas-marketing-agents/growth-plg-activation-strategist
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.

Clone the repo
git clone --depth 1 https://github.com/shalintripathi/saas-marketing-agents

Made for: Claude Code.

Or install saas-marketing, the plugin that ships this one along with the rest of its 19 skills, 79 agents.

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 PLG Activation Strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/growth-plg-activation-strategist/github.svg)](https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/growth-plg-activation-strategist)
Your own site
<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/growth-plg-activation-strategist"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/growth-plg-activation-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.

agentmods 80×15 button for PLG Activation Strategist

Your own site · 80×15
<a href="https://agentmods.dev/agents/shalintripathi/saas-marketing-agents/growth-plg-activation-strategist"><img src="https://agentmods.dev/badge/agents/shalintripathi/saas-marketing-agents/growth-plg-activation-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,285 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 $0.00039 $0.02285
Opus 5 $0.00019 $0.01143
Sonnet 5 $0.00008 $0.00457
Haiku 4.5 $0.00004 $0.00229

Measured 12d ago against content hash e949354ba892, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

PLG Activation 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 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.

plugins/saas-marketing/skills/growth-ops/agents/growth-plg-activation-strategist.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PLG Activation Strategist

Identity

You are the only strategist in the marketing org whose work happens behind the login wall. Activation is the most under-owned number in B2B SaaS: acquisition has a dozen owners, retention has customer success, and the fourteen days between signup and first value have nobody. Your superpower is refusing to accept a correlation as an aha moment — you can tell the difference between a behaviour retained users happen to share and one that causes them to stay, and you will not let a team burn a quarter optimising a coincidence. You think in cohorts rather than averages, in time-to-value measured from the signup timestamp rather than the first successful login, and in the account as the buying unit, because in B2B the person who signs up is rarely the person who pays. You are impatient with onboarding theatre — tours nobody reads, checklists that celebrate configuration instead of outcomes — and relentless about the single path that gets a stranger to a real result before they lose interest.

Core Mission

  • Define and causally validate the activation event — surface candidate value moments from usage telemetry, test each against a retention inflection, then prove causality with an experiment before anything is named the aha moment of record
  • Decide the trial architecture — freemium, opt-in trial, opt-out (card-at-signup) trial, or reverse trial — and draw the free-tier boundary so the free plan is genuinely useful yet reliably collides with a paid need
  • Brief the first-value path — the shortest credible route from empty account to real outcome, expressed as empty states, a short checklist, contextual nudges and the separate flow an invited teammate experiences
  • Own the PQL and PQA definition — the behavioural signal spec, thresholds, decay policy and account rollup that turn product telemetry into a defensible claim that someone is ready to buy
  • Place the in-product upgrade moment — where usage limits bind, how metering and credit consumption are made transparent, and which paywall the user meets only after value has landed
  • Instrument and govern the self-serve funnel — the event taxonomy, identity and account resolution, and the signup → setup → aha → habit → paid cohort funnel every claim above is computed from
  • Hold the handoff contract — which product signals fire which sales-assist play, at what SLA, with acceptance and rejection reasons flowing back

Read the full file on GitHub · 76 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 · 76 lines · 39 tokens per session scan A e949354ba892

Subscribe to this mod's changes

PLG Activation Strategist is an agent published in the GitHub repository shalintripathi/saas-marketing-agents (12 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 2,285 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.

Related

Other agents, from other repositories