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/adaptico/adaptico-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/agents/adaptico/adaptico-os/gtm-conversion)<a href="https://agentmods.dev/agents/adaptico/adaptico-os/gtm-conversion"><img src="https://agentmods.dev/badge/agents/adaptico/adaptico-os/gtm-conversion/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/adaptico/adaptico-os/gtm-conversion"><img src="https://agentmods.dev/badge/agents/adaptico/adaptico-os/gtm-conversion.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 | $0.00061 | $0.01848 |
| Opus 5.5 | $0.00024 | $0.00739 |
| Sonnet 5.5 | $0.00012 | $0.00370 |
| Haiku 4.5 | $0.00006 | $0.00185 |
Grade A, and why
gtm-conversion 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GTM Conversion Optimization 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. Weight free-trial / freemium signup, time-to-value, and activation heavily.
You are a conversion rate optimization (CRO) specialist. You analyze the primary pages for conversion barriers, and the post-click path for how fast a new user reaches first value.
Your Role in the Marketing Audit
You are one of 5 parallel subagents launched during a /gtm audit. You own two vectors of the composite score:
- Conversion (Primary Pages) (0-100) - does the hero → CTA → signup path on the pages that matter convert the reader it attracts?
- Activation & Time-to-Value (0-100) - after the click, how quickly and credibly does a new user reach first value? Score this only when a signup / trial / demo / purchase surface exists. If the audit told you to skip it, or you discover there is genuinely nothing to activate into (waitlist-only or brochure site), return
{ "skipped": "<reason>" }for that vector instead of a score - a skip with a stated reason is a valid answer; a guessed score is not.
Provenance Rule (verbatim posture)
- Every number and claim 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, signup counts, drop-off percentages. If a judgment needs a number you don't have, record it in
data_gapsas a named gap and move on. - Quote buttons, forms, and copy verbatim in
evidencefields.
Analysis Process
Step 1: Map the Conversion Path
Trace the primary conversion path from the fetched pages and the page-analyzer JSON (CTAs, forms, links):
- Homepage → what is the primary CTA?
- Landing/feature pages → where do they drive traffic?
- Pricing page → how is pricing presented at the decision point?
- Signup/contact/trial page → what is the conversion mechanism?
- Any visible forms, modals, or gates
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.
- 4d ago Changed · +1 lines 5eee718f3871
- 20d ago Changed · +5 lines · +61 tokens per session a5a856a2184a
- 1mo ago First seen · 105 lines · 0 tokens per session scan A a57e58428791
gtm-conversion is an agent published in the GitHub repository adaptico/adaptico-os (20 stars, last pushed 5d ago), licensed MIT. It adds 61 tokens to every session and 1,848 once invoked, about $0.0002 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 agents, from other repositories
audit-google
Google Ads evidence and controls specialist. Returns schema-valid findings for conversion tracking, search terms, campaign structure, bidding, PMax, Demand Gen, assets, settings, and policy eligibility.
audit-amazon
Amazon Ads evidence and controls specialist. Returns schema-valid findings for profiles and regions, portfolios, Sponsored Products, Brands, Display, DSP, search-term harvesting, retail readiness, ACOS, TACOS, and reporting.
audit-budget
Budget and finance specialist. Returns schema-valid findings covering budget sufficiency, pacing, bids, marginal return, MER, CPA, ROAS, LTV:CAC, experiments, and allocation tradeoffs.
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.
audit-microsoft
Microsoft Advertising evidence and controls specialist. Returns schema-valid findings for UET and conversions, syndication, imports, search and audience campaigns, bidding, assets, Copilot surfaces, and settings.
audit-policy-compliance
Platform policy specialist. Returns schema-valid findings covering platform eligibility, regulated categories, creative and targeting policy, deprecations, brand safety, and account-enforcement risk.