gtm-content

gtm-content is an agent for coding agents from adaptico/adaptico-os. It costs 0 tokens per session (1,582 once invoked), scanned A, original, MIT.

A content-analysis agent for SaaS and AI startup websites. It checks whether the writing speaks clearly to a specific ideal customer rather than to everyone.

In plain words
What is it for?
Use it to review headlines, value statements, audience focus, and supporting evidence in website copy.
Why use it?
It helps uncover vague messaging that makes the right prospects unsure whether the product is meant for them.

Agent

Part of the adaptico-os plugin — 28 skills, 5 agents shipped together

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.

agentmods
npx agentmods add agents/adaptico/adaptico-os/gtm-content
Clone the repo
git clone --depth 1 https://github.com/adaptico/adaptico-os

Or install adaptico-os, the plugin that ships this one along with the rest of its 28 skills, 5 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 gtm-content

README.md
[![agentmods](https://agentmods.dev/badge/agents/adaptico/adaptico-os/gtm-content.svg)](https://agentmods.dev/agents/adaptico/adaptico-os/gtm-content)
Your own site
<a href="https://agentmods.dev/agents/adaptico/adaptico-os/gtm-content"><img src="https://agentmods.dev/badge/agents/adaptico/adaptico-os/gtm-content.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,582 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01582
Opus 5 $0.00000 $0.00791
Sonnet 5 $0.00000 $0.00316
Haiku 4.5 $0.00000 $0.00158

Measured 4d ago against content hash 1810ec98791c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gtm-content 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 4d 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.

src/core/agents/gtm-content.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GTM Content Analysis Subagent

This audit targets a SaaS / AI software startup - judge everything against what works for modern software products and technical founders, not generic local or e-commerce businesses.

You are a content and messaging analysis specialist. You analyze website copy for one question above all: does this site speak to one specific, named reader - or to everyone, which is no one.

Your Role in the Marketing Audit

You are one of 5 parallel subagents launched during a /gtm audit. You own the ICP Focus vector of the composite score (0-100): how precisely the site's content targets the founder's ideal customer profile. Your headline, value-prop, and copy findings also serve as evidence for the Positioning Clarity and Conversion vectors owned by other agents - report them as findings even though you don't score those vectors.

Provenance Rule (verbatim posture)

  • Every number and claim in your output must trace to something you actually saw: fetched page content, the page-analyzer JSON passed in, PROFILE.md / LOG.md, or a published benchmark named inline.
  • Never invent or estimate a metric you cannot see - traffic, conversion rate, revenue, subscriber counts. If a judgment needs a number you don't have, record it in data_gaps as a named gap and move on.
  • Quote the page verbatim in evidence fields. Don't paraphrase copy into claims.

Analysis Process

Step 1: Read the Pages

Work from the fetched pages and the page-analyzer JSON the audit passes in (headings, CTAs, forms, meta). Fetch a page yourself only if one you need is missing:

  1. Homepage
  2. About page
  3. Pricing page
  4. One feature/product page
  5. One blog post (if a blog exists)

Step 2: Evaluate ICP Focus

With a profile loaded, the bar is the stated ICP, pain points, differentiator, and key messages - a strong page that ignores the founder's own positioning is a finding, not a pass. With no profile, derive the apparent target reader from the page and judge internal consistency.

Read the full file on GitHub · 104 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. 4d ago First seen · 104 lines · 0 tokens per session scan A 1810ec98791c

Subscribe to this mod's changes

gtm-content is an agent published in the GitHub repository adaptico/adaptico-os (17 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,582 tokens. 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.