Claude Code for GTM Engineers: The Five-File Setup A developer published a five-layer configuration for running Anthropic's Claude Code as a go-to-market workbench, covering project-scoped MCP servers in .mcp.json, ICP and rules in CLAUDE.md, repeatable jobs as skills, permission rules that gate sending or spending actions, and headless execution via claude -p or scheduled GitHub Actions. The setup is committed to a single repository so an entire team shares identical tooling, and the author notes Claude Code requires a Pro, Max, Team, Enterprise or Console account. The writeup cautions that CLAUDE.md is treated as context rather than enforced configuration, so rules that matter should be backed by permission settings. The short answer. For go-to-market work, set up Claude Code in five layers: add your data and sending tools as project-scoped MCP servers in .mcp.json, put your ICP and rules in CLAUDE.md, package repeat jobs as skills, use permission rules so anything that sends or spends asks first, and run jobs headless with claude -p or a scheduled GitHub Action. Commit it all to one repo and the whole team gets the same setup. As a workbench for go-to-market jobs: build a list, enrich it, check it, research the accounts, draft outreach, and repeat the jobs that work. Claude Code, Anthropic's agent for the terminal, does each job from a sentence. What makes it reliable is the setup around it, and that setup is plain files in a repository your team can share. | Layer | File | What it does | |---|---|---| | Tools | .mcp.json | The data, sending and CRM servers Claude can call | | Context | CLAUDE.md | Your ICP, offer and rules, read at the start of every session | | Methods | .claude/skills/ | Repeatable jobs, one SKILL.md each | | Guardrails | .claude/settings.json | Which tools run freely and which ask first | | Schedule | claude -p, GitHub Actions | The same jobs, run without you | Locations from Anthropic's Claude Code docs, checked 12 October 2026. Claude Code needs a Pro, Max, Team, Enterprise or Console account; Anthropic's setup page says the free plan doesn't include it Anthropic https://code.claude.com/docs/en/setup . Add each tool as a remote MCP Model Context Protocol server. Anthropic's docs call HTTP servers "the recommended option for connecting to remote MCP servers", and the project scope writes them to .mcp.json so you can "Check .mcp.json into version control so everyone on your team gets the same MCP tools" Anthropic https://code.claude.com/docs/en/mcp . Terminal claude mcp add --transport http --scope project layrcake https://mcp.layrcake.dev/mcp .mcp.json { "mcpServers": { "layrcake": { "type": "http", "url": "https://mcp.layrcake.dev/mcp" } } } Then run /mcp and authenticate; servers that use OAuth open a browser to sign in. We connect Layrcake for the data and outreach loop search, emails, verification, research, signals, campaigns, replies . Add your CRM's own server alongside it; Anthropic's docs use HubSpot's as an example. The MCP servers roundup https://layrcake.dev/guides/best-mcp-servers-for-sales covers the other options by job. Keep the list short. Every server adds tools for Claude to choose between, and overlapping tools make its choices worse. CLAUDE.md is read at the start of every session, so it is where your go-to-market context lives: what you sell, who you sell to, who to never contact, how you write. A project's ./CLAUDE.md is shared with the team; ~/.claude/CLAUDE.md holds your personal preferences Anthropic https://code.claude.com/docs/en/memory . One caution from the same page: Claude treats CLAUDE.md "as context, not enforced configuration". Write your rules there, and enforce the ones that matter with permissions step 4 . Our template is below and in the download button under Share. CLAUDE.md · template Go-to-market context Claude reads this file at the start of every session. Keep it short and true. Replace everything in brackets . What we sell One or two sentences: the product, who it's for, and the result a customer gets. Proof we can cite: one customer result with a number, and where it's published . Who we sell to ICP - Companies: industry , country or region , headcount range , any must-have, e.g. "has a sales team" or "uses Salesforce" . - People: titles , and who to skip titles that look close but aren't buyers . - Never contact: existing customers, partners, competitors, or a list file in this repo . How we prospect - Find people with the data tools, never from memory. Never guess an email address. - Verify every email before it goes on a list. Drop invalid and unknown. Keep catch-all only in small numbers and say how many. - Research before writing: one dated fact per company, with its source link. No fact, no personalised opener. - Every request has a credit budget. Check each call's cost before making it and stop before the budget runs out. Default budget: 100 credits. - Report what each step cost, using the charge each tool returns. How we write - First email under 120 words. One problem, one result, one yes/no question. No meeting link in email 1. - Follow-ups in the same thread, under 60 words. - Sign as name , role . - Banned: exclamation marks, "hope this finds you well", "quick question", invented facts. What needs a human - Never launch a campaign, buy sending capacity or send a reply without the user's explicit yes in this session. - Stop at a draft and show: the list, the openers with sources, the emails, and the total credits. When you run the same job twice, make it a skill. A skill is a SKILL.md file in .claude/skills/