Borrowing it
Nothing to install: this file belongs to LaGrowthMachine/gtm-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/LaGrowthMachine/gtm-system/main/CLAUDE.mdgit clone --depth 1 https://github.com/LaGrowthMachine/gtm-systemWrote 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/instructions/lagrowthmachine/gtm-system/claude-md)<a href="https://agentmods.dev/instructions/lagrowthmachine/gtm-system/claude-md"><img src="https://agentmods.dev/badge/instructions/lagrowthmachine/gtm-system/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.
<a href="https://agentmods.dev/instructions/lagrowthmachine/gtm-system/claude-md"><img src="https://agentmods.dev/badge/instructions/lagrowthmachine/gtm-system/claude-md.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 | $0.02395 | $0.02395 |
| Opus 5.5 | $0.00958 | $0.00958 |
| Sonnet 5.5 | $0.00479 | $0.00479 |
| Haiku 4.5 | $0.00239 | $0.00239 |
Grade A, and why
gtm-system 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 1mo 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LGM GTM Skills — Claude setup
You are looking at the GTM System repo maintained by La Growth Machine. It bundles a library of public Claude skills (sourcing, list building, campaigns, copywriting, analytics, reply handling) and an MCP server that lets Claude act directly inside the user's LGM workspace.
First-time setup
Check if the LGM MCP is already configured by running claude mcp list (look for a line starting with LaGrowthMachine:). The installer registers the MCP via claude mcp add --scope user --transport http, which stores the config in ~/.claude.json at user scope (available in every project). If the claude CLI isn't available, ask the user whether they've already run sh install.sh.
If it is NOT configured, proactively tell the user:
"I can see this is the LGM GTM Skills repo. Would you like me to install the LGM MCP and skills? It takes ~1 minute — I'll run
sh install.shfor you. On first use, a browser tab opens to sign in to La Growth Machine (OAuth) — new accounts can be created from that tab. No API key to copy, nothing to paste."
If they say yes, run sh install.sh and confirm when done.
If it IS configured, present the onboarding to the user:
- Confirm MCP is connected and list the available MCP tools grouped by category (Audiences, Campaigns, Inbox, Send, Workspace, LinkedIn, BigQuery).
- List the available GTM Skills grouped by category.
- Show the suggested first-steps table.
- Ask: "What would you like to do?"
What LGM gives you
Once the MCP is connected and skills are installed, two layers work together.
Layer 1 — LGM MCP (Claude acts inside La Growth Machine)
The MCP gives Claude direct access to the user's LGM workspace. No copy-paste, no tab switching. Tools are exposed under the namespace mcp__LaGrowthMachine__*.
Audiences & leads
list_audiences— list every audience with id, name and lead count; the way to resolve an audience id by name (e.g. right aftercreate_audience_from_linkedin_url, which returns no id)get_audience— fetch an existing audience by ID (details, size, import status)get_audience_leads— list all leads in an audience, full record (paginated withskip, 100 max per page)create_audience_from_linkedin_url— create or populate an audience (by name) from a LinkedIn / Sales Navigator search URL, a post's engagers, or an event's attendees; needs anidentityIdfromlist_identities; asynccreate_lead— create or update (upsert) a lead and attach it to an audienceenrich_lead— find a lead's pro email and/or refresh LinkedIn fields; spends credits, confirm-gatedget_enrich_result— poll an enrichment request started byenrich_leadget_credits— credit balance (total,perishable); check before enriching
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.
- 1mo ago Changed · +2 lines · +93 tokens per session f674ac2db6fe
- 1mo ago Changed · +13 lines · +510 tokens per session 1b2c1c0534e0
- 2mo ago First seen · 133 lines · 1,792 tokens per session scan A e3d3e385f1bd
gtm-system CLAUDE.md is an instructions file published in the GitHub repository LaGrowthMachine/gtm-system (45 stars, last pushed 23d ago), licensed MIT. It adds 2,395 tokens to every session, about $0.0096 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.