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 skills add benyki/gtm-engine --skill engine-outreachgit clone --depth 1 https://github.com/benyki/gtm-engineWrote 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/skills/benyki/gtm-engine/engine-outreach)<a href="https://agentmods.dev/skills/benyki/gtm-engine/engine-outreach"><img src="https://agentmods.dev/badge/skills/benyki/gtm-engine/engine-outreach/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/skills/benyki/gtm-engine/engine-outreach"><img src="https://agentmods.dev/badge/skills/benyki/gtm-engine/engine-outreach.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 | $0.00119 | $0.06745 |
| Opus 5.5 | $0.00048 | $0.02698 |
| Sonnet 5.5 | $0.00024 | $0.01349 |
| Haiku 4.5 | $0.00012 | $0.00675 |
Grade B, and why
engine-outreach scanned grade B 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 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
user, and never tell them what a plan costs from memory. How it starts
The opening of the file, as written. The whole thing — 447 lines — stays where its author put it; the contents beside it link to each section on GitHub.
engine-outreach
Writes outreach worth reading, one person at a time, and stops at the draft.
This skill runs any engine folder of type outreach. The default folder
is outreach/; paths below (inputs/audience/, crm.csv, templates/,
runs/) are inside that folder, while brand, accounts and keys live in
shared/. Multiple outreach engines are a normal shape — outreach/
for customers and outreach-investors/ for fundraising are two independent
folders with their own CRMs, templates, experiments and metrics — scaffold one
with --merge --engine <name>:outreach, or copy a folder and empty its
runs/, reports/ and crm.csv (history belongs to the original).
It never sends. Not with permission, not "just this once". Drafts land in the user's own mail system and a human clicks send. Everything downstream — the CRM, the A/B verdicts, the report — assumes that boundary holds.
No email template ships with this repo, and that's deliberate. What makes a
cold email work is specific to what the user sells, who they're writing to and
what that industry finds normal — a generic template with placeholders produces
generic email. The first template is written with the user, and
assign_arm.py returns write_template on an empty folder to say so.
How (not just what):
| Step | Reference |
|---|---|
| Where the list comes from, and finding the addresses | references/lead-sourcing.md |
| Researching a person in the browser | references/browser-research.md |
| Writing the first email with the user | references/first-touch.md |
| Cut the slop — every draft, every run | references/anti-slop-writing.md |
| Replies and follow-ups (optional) | references/followups.md |
| Sending domain, volume, deliverability | references/advanced.md |
Paths in this file: shared/… means the gtm home (~/gtm by default, or
$GTM_HOME); templates/, inputs/, runs/ and reports/ mean the engine
folder you're running, wherever it lives. The scripts resolve both through
~/gtm/engines.json, so read them as names rather than literal paths.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 4121ef897ee6
- 2mo ago First seen · 447 lines · 119 tokens per session scan B f5def6cbb5d2
engine-outreach is a skill published in the GitHub repository benyki/gtm-engine (4 stars, last pushed 6d ago), licensed MIT. It adds 119 tokens to every session and 6,745 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
engine-outreach compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| engine-outreachbenyki/gtm-engine | Skill | 4 | 6d ago | MIT | B | 119 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |