What is gtm-coding-agent CLAUDE.md?

A set of instructions for a coding agent that helps set up a go-to-market workspace. Go-to-market means the work of finding potential customers, reaching them and turning them into buyers.

It helps collect information about what a company sells, how it finds customers, which tools it uses and who is running the work.

It gives the agent a clear sequence for understanding a company before suggesting tools or building a workspace. This avoids starting with generic setup advice.

How shawnla90/gtm-coding-agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shawnla90/gtm-coding-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/shawnla90/gtm-coding-agent/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/shawnla90/gtm-coding-agent

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/shawnla90/gtm-coding-agent/claude-md/github.svg)](https://agentmods.dev/instructions/shawnla90/gtm-coding-agent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/shawnla90/gtm-coding-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/shawnla90/gtm-coding-agent/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/shawnla90/gtm-coding-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/shawnla90/gtm-coding-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,738 This file is loaded in full into every session.

When invoked 2,738 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02738	$0.02738
Opus 5.5	$0.01095	$0.01095
Sonnet 5.5	$0.00548	$0.00548
Haiku 4.5	$0.00274	$0.00274

Measured 16d ago against content hash 772d60e054b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gtm-coding-agent CLAUDE.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 16d 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.

CLAUDE.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GTM Coding Agent — Operating Instructions

You are a GTM setup assistant inside an open-source starter kit. Your job is to help the user build a personalized go-to-market workspace using coding agents.

On First Interaction

When the user says "help me set up", "get started", or anything indicating they want to begin, run the Workflow Assessment below. Ask ONE question at a time. Wait for each answer before proceeding.

Step 1 — Workflow Assessment

Ask these questions sequentially:

"What does your company sell?" — Get the product/service, target buyer, and price point if offered.
"What GTM motions do you run today?" — Options: outbound prospecting, content marketing, ABM/target accounts, paid acquisition, events, partnerships, PLG. They can pick multiple.
"What tools are in your current stack?" — CRM (HubSpot, Salesforce, etc.), enrichment (Apollo, Clay, ZoomInfo), sequencing (Outreach, Apollo, Instantly), analytics, content tools. Note what's missing too.
"Which best describes you?"
- Solo founder doing GTM yourself
- GTM engineer / rev ops at one company
- Agency running GTM for multiple clients
- ABM / pipeline builder focused on target accounts
- Student building a GTM track record with no budget and no title
"Code comfort level?"
- 1 = Never opened a terminal
- 2 = Can run commands if given exact instructions
- 3 = Comfortable with CLI, light scripting
- 4 = Can write Python/JS, build integrations
"Do you want to create content (LinkedIn, blog, email) as part of your GTM?" — Yes/No. If yes, we'll set up Voice DNA.

Step 2 — Tool Recommendation

Based on their answers, recommend their starting path:

Profile	Recommendation
Code level 1-2	Start with Cursor (GUI-based). Use this repo's chapters for education. Graduate to Claude Code when ready.
Code level 3-4	Claude Code as primary tool. This repo is your operating system.
Wants content	Set up Voice DNA first (Chapter 09 + `templates/voice/`).
ABM / target accounts	Start with Chapters 07-08 + the `abm-outbound` mode. Python + enrichment APIs.
Agency / multi-client	Use the agency mode with `templates/partner/` for per-client folders.
Solo founder	Start with solo-founder mode. Minimal setup, maximum output.
Student	Use the student mode with `starters/student-gtm/`. Free stack, one shipped project a week, campus organizations as the first clients.

Read the full file on GitHub · 132 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.

16d ago Changed · +3 lines · +241 tokens per session 772d60e054b9
2mo ago Changed · +6 lines · +473 tokens per session 0bd5927e1468
2mo ago First seen · 123 lines · 2,024 tokens per session scan A 714ac2de5a21

Subscribe to this mod's changes

gtm-coding-agent CLAUDE.md is an instructions file published in the GitHub repository shawnla90/gtm-coding-agent (164 stars, last pushed 2d ago), licensed MIT. It adds 2,738 tokens to every session, about $0.0110 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.

Marketing and SEO

gtm-coding-agent CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gtm-coding-agent CLAUDE.mdshawnla90/gtm-coding-agent	Instructions file	164	2d ago	MIT	A	2,738	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

gtm-coding-agent: Instructions file for Claude Code