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.
npx agentmods add instructions/gtmify/aigtm/claude-mdgit clone --depth 1 https://github.com/GTMify/aigtmWrote 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/gtmify/aigtm/claude-md)<a href="https://agentmods.dev/instructions/gtmify/aigtm/claude-md"><img src="https://agentmods.dev/badge/instructions/gtmify/aigtm/claude-md.svg" alt="Measured on agentmods" 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 | $0.01189 | $0.01189 |
| Opus 5 | $0.00594 | $0.00594 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
aigtm 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 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI GTM Skills for Claude Code
This repo contains 16 ready-to-use AI agent skills for go-to-market and revenue leadership. Skills are installed to ~/.claude/skills/ by the bootstrap script.
First week? Start with five: meeting-prep, prospect-research, deal-strategy, pipeline-health, post-call-summary. They cover the full revenue motion and are the same five the Session 5 demos walk through. Once those feel automatic, the Power Prompting 201 reference covers the compounding moves (chaining, custom Layer 1 patterns, anti-hallucination constraints, JSON output, when not to use a skill).
Available Skills
| Skill | Trigger Phrases |
|---|---|
| meeting-prep | "prep me for my call", "meeting prep", "brief me on [company]" |
| prospect-research | "research [company]", "find decision-makers at [company]" |
| post-call-summary | "summarize my call", "post-call summary", "write follow-up" |
| deal-strategy | "deal strategy for [account]", "MEDDIC assessment" |
| objection-handler | "handle this objection", "stuck deal", "they said [objection]" |
| pipeline-health | "audit my pipeline", "pipeline health check" |
| forecast-narrative | "build my forecast", "forecast narrative" |
| territory-analyzer | "analyze my territory", "rep performance" |
| competitive-intel | "competitive intel on [company]", "monitor competitors" |
| win-loss-analyzer | "analyze our wins and losses", "why did we lose [deal]" |
| qbr-builder | "build a QBR for [client]", "quarterly business review" |
| churn-early-warning | "flag at-risk accounts", "churn risk" |
| board-update | "write a board update", "investor update" |
| hiring-brief | "write a job description for [role]", "hiring brief" |
| weekly-planner | "plan my week", "weekly priorities" |
| inbox-triage | "triage my inbox", "prioritize these emails" |
First-Time Setup: Personal Profile
If ~/.claude/CLAUDE.md does not exist, you MUST run the onboarding flow below before doing anything else. Do not skip this. Do not summarize the skills. Do not answer other questions first. The skills work significantly better when Claude has context about who the user is.
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 First seen · 110 lines · 1,189 tokens per session scan A cabddf94f95a
aigtm CLAUDE.md is an instructions file published in the GitHub repository GTMify/aigtm (24 stars, last pushed 26d ago), licensed MIT. It adds 1,189 tokens to every session, about $0.0059 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.
Other instructions, from other repositories
zime-gtm-skills AGENTS.md
Instructions for zime-ai/zime-gtm-skills, covering agents.md, repository overview, repository structure, frontmatter contract and validate.
outreachmagic AGENTS.md
Instructions for outreachmagic/outreachmagic, covering agent guide — outreachmagic/outreachmagic monorepo, layout, if you add skills/ /scripts/.py, public readme (outreachmagic skill) and if you change pricing / billing limits.
headless-gtm AGENTS.md
Instructions for Zevenue/headless-gtm, covering headless gtm - agent notes, where things are and operating rules.
gtm-brain-builder CLAUDE.md
Instructions for Andytoizer/gtm-brain-builder, covering agent instructions, public packaging rules and validation.
salesably-marketplace CLAUDE.md
Instructions for Salesably/salesably-marketplace, covering claude.md, repository overview, architecture, key concepts and working with skills.
your-tam-is-fake GEMINI.md
Gemini CLI instructions for adaline-ankit/your-tam-is-fake, covering your-tam-is-fake, run six phases, in order, every time, non-negotiables, deep mode, in brief and frameworks worth knowing.