technical-product-gtm AGENTS.md

technical-product-gtm AGENTS.md is an instructions file for Codex, OpenCode from beingsmit/technical-product-gtm. It costs 527 tokens per session, scanned A, original, MIT.

A collection of 11 go-to-market skills for B2B software companies, covering positioning, pricing, launches, partnerships, developer adoption, and growth.

In plain words
What is it for?
It is for shaping product messages, pricing models, sales and partner programs, developer communities, product-led growth, and market launches. B2B means a company sells to other businesses, and GTM means the plan for bringing a product to market.
Why use it?
It helps founders and operators choose a focused method for common commercial decisions instead of treating every product-marketing problem the same way.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: positional $N argument; mentions AGENTS.md.

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 instructions/beingsmit/technical-product-gtm/agents-md
Clone the repo
git clone --depth 1 https://github.com/beingsmit/technical-product-gtm

Made for: Codex, OpenCode.

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 technical-product-gtm AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/beingsmit/technical-product-gtm/agents-md.svg)](https://agentmods.dev/instructions/beingsmit/technical-product-gtm/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/beingsmit/technical-product-gtm/agents-md"><img src="https://agentmods.dev/badge/instructions/beingsmit/technical-product-gtm/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 527 This file is loaded in full into every session.
When invoked 527 The same file — it is already loaded in full.
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 5.1 $0.00527 $0.00527
Opus 5 $0.00264 $0.00264
Sonnet 5 $0.00105 $0.00105
Haiku 4.5 $0.00053 $0.00053

Measured 6d ago against content hash dd2d96f9005f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

technical-product-gtm AGENTS.md 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 6d 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.

AGENTS.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

What This Is

11 go-to-market skills for B2B SaaS companies — built for founders of AI and technical products, GTM leaders, and operators from Seed through Series D. Each skill is a self-contained SKILL.md in the skills/ directory.

How to Use These Skills

Skills are loaded based on what the user is working on. Here's when to load each one:

Positioning & pricing questions — user is struggling with messaging, competitive differentiation, or pricing architecture:

  • positioning-strategy → messaging sounds like competitors, category creation, repositioning
  • technical-product-pricing → usage-based vs seat-based debates, freemium gates, price increases
  • ai-gtm → selling AI products, "will this replace my team?" objections, AI pricing models

Building GTM motions — user is setting up or scaling go-to-market channels:

  • partnership-architecture → partner programs, channel strategy, certification wedges, build-vs-partner
  • developer-ecosystem → developer adoption, open vs curated marketplaces, student programs
  • product-led-growth → self-serve funnels, PLG vs sales-led decisions, growth experimentation
  • 0-to-1-launch → new market entry, first 50 customers, partner-led launches

Enterprise execution — user is in active deals or post-sale:

  • enterprise-account-planning → stuck deals, MEDDICC qualification, procurement navigation, mutual action plans
  • enterprise-onboarding → champion went quiet, adoption stalled, implementation planning

Running the company — user needs operating rhythm or board prep:

  • operating-cadence → meeting structures, metric dashboards, quarterly planning, decision rights
  • board-and-investor-communication → board decks, investor updates, missed quarter narratives

What Makes These Skills Different

Each skill contains specific decision thresholds (not principles), real stories where things went wrong before they went right, and the counter-intuitive patterns most operators learn too late. When applying a framework, use the specific numbers and criteria in the skill — they're earned, not theoretical.

Read the full file on GitHub · 37 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. 6d ago First seen · 37 lines · 527 tokens per session scan A dd2d96f9005f

Subscribe to this mod's changes

technical-product-gtm AGENTS.md is an instructions file published in the GitHub repository beingsmit/technical-product-gtm (42 stars, last pushed 5mo ago), licensed MIT. It adds 527 tokens to every session, about $0.0026 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 2026-08-30.