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/zevenue/headless-gtm/agents-mdgit clone --depth 1 https://github.com/Zevenue/headless-gtmWrote 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/zevenue/headless-gtm/agents-md)<a href="https://agentmods.dev/instructions/zevenue/headless-gtm/agents-md"><img src="https://agentmods.dev/badge/instructions/zevenue/headless-gtm/agents-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 5.1 | $0.00483 | $0.00483 |
| Opus 5 | $0.00242 | $0.00242 |
| Sonnet 5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
headless-gtm AGENTS.md scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- API keys come from the environment or a `.env` file (`cp .env.example .env`). The Python scripts load `.env` themselves; **curl does not** - when calling a vendor API directly, load it in the same command (`set -a; [ - What it actually says
Headless GTM - agent notes
This repo is an outbound GTM pipeline packaged as agent skills (the SKILL.md standard). It works in Claude Code and Codex.
Where things are
- Skills live in
skills/- one folder per skill, each with aSKILL.mdspec..claude/skillsand.agents/skillsare symlinks to it, so both Claude Code and Codex discover the skills when run from this repo. - The chain skills are numbered
00-06by layer: router, discovery + qualification, extraction, signals, judgment, email resolution.headless-gtm-shared/CONVENTIONS.mddefines the record contract every chain skill reads and writes (records.jsonl, additive fields, run folders, resume). - The writing skills (
email-writer,creative-variable,prospect-posts,gtm-context) sit downstream of the chain.
Operating rules
- For any multi-step ask (a full list build, a campaign, "what would this cost"), start with
00-gtm-router- it plans the chain and prices it before anything runs. - Never spend API credits without presenting the estimate and getting a go-ahead. Every chain skill documents its own spend gate; respect them.
- API keys come from the environment or a
.envfile (cp .env.example .env). The Python scripts load.envthemselves; curl does not - when calling a vendor API directly, load it in the same command (set -a; [ -f .env ] && . ./.env; set +a), or you'll send an empty auth header and get a misleading provider error. Every key is optional - skip layers whose key is missing and say so, never crash and never hardcode a key. - Output goes to
./runs/<run-id>/in the working directory, never inside a skill folder. Run-ids are prefixed with the producing step (2026-07-27-01-prospeo-saas-us) because every step of a chain shares that oneruns/root. Pass records between steps by explicit path. - Each skill's
SKILL.mdis the authoritative spec for inputs, outputs, and cost rules. Read it before running the skill.
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.
- 5d ago First seen · 18 lines · 483 tokens per session scan A 98d1020835db
headless-gtm AGENTS.md is an instructions file published in the GitHub repository Zevenue/headless-gtm (26 stars, last pushed 1mo ago), licensed MIT. It adds 483 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
GTMOS CLAUDE.md
Claude Code instructions for shyftai/GTMOS, covering gtm:os, on startup, key references (load as needed) and rules.
cdtm-gtm-engine CLAUDE.md
Claude Code instructions for gtmadviser/cdtm-gtm-engine, covering claude.md — gtm engine starter (cdtm workshop edition), tools you'll use (bring your own keys), two skills you know how to run, what we're building and default channel: linkedin-first + email.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.