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 skills/benyki/gtm-engine/engine-setupnpx skills add benyki/gtm-engine --skill engine-setupgit clone --depth 1 https://github.com/benyki/gtm-engineWhat 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 | $0.00130 | $0.05998 |
| Opus 5 | $0.00065 | $0.02999 |
| Sonnet 5 | $0.00026 | $0.01200 |
| Haiku 4.5 | $0.00013 | $0.00600 |
Grade A, and why
engine-setup 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 2d 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.
**If they already ran the one-command installer** (`curl -fsSL 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-setup
Gets someone from nothing to a working home.
Run it once per project. It is also re-runnable, and doctor.py is there as an
optional health check when something looks wrong — never a step to clear before
work can start.
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.
Read the onboarding script first
docs/onboarding.md in the repo is the script for
the conversation: what to warn about, what to offer, which question to ask and
in what order. Read it before you touch their disk. This file is the mechanics.
What you're building
Three separate things, and keeping them separate is the point:
- The clone (
~/.gtm-engine): the engines' logic. One per machine, updated bygit pull. Nothing personal in it, nothing to gitignore in anyone's project. - The home (
~/gtm): their brand, accounts, keys, assets, insights, andengines.json. One per person. Never touched by an update. - The engines: one self-contained folder per channel. These can live anywhere, and where they go is the one real question of setup.
~/.gtm-engine/ the clone (read-only, git pull)
~/gtm/ the home
├── AGENTS.md CLAUDE.md
├── engines.json the registry: every engine and where it lives
├── shared/ brand, channels, .env, assets, insights
├── published/
└── engines/ engines kept in one place, named
engine-<type>-<project>/
~/.agents/skills/ the skills themselves (step 4)
~/Desktop/ two symlinks, so neither is buried (step 5)
├── gtm -> ~/gtm
└── skills -> ~/.agents/skills
Where the engines live
The default is ~/gtm/engines/, and you ask before using it. Not a
required-choices screen: one question, with the answer already suggested.
What ships with it
7 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.
- 2d ago First seen · 447 lines · 130 tokens per session scan A edf03a64f2d0
engine-setup is a skill published in the GitHub repository benyki/gtm-engine (5 stars, last pushed 29d ago), licensed MIT. It adds 130 tokens to every session and 5,998 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…