Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Abilityai/abilities/plugin install trinityWrote 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/abilityai/abilities/deploy-new-instance)<a href="https://agentmods.dev/skills/abilityai/abilities/deploy-new-instance"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/deploy-new-instance/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/abilityai/abilities/deploy-new-instance"><img src="https://agentmods.dev/badge/skills/abilityai/abilities/deploy-new-instance.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 | $0.00027 | $0.09090 |
| Opus 5.5 | $0.00011 | $0.03636 |
| Sonnet 5.5 | $0.00005 | $0.01818 |
| Haiku 4.5 | $0.00003 | $0.00909 |
Grade F, and why
deploy-new-instance scanned grade F with 5 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 10d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
### STEP B3b (Existing Install): Verify + Collect Credentials Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
rules): on a public VPS run sudo ./scripts/deploy/docker-firewall.sh Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
Then run **STEP B2** for `SSH_HOST` (the Droplet IP) and `SSH_KEY` only — skip the SSH-user question. The installer attached every SSH key already on the DigitalOcean account; if the account had none, SSH will fail — tel Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
"docker --version 2>/dev/null || (curl -fsSL https://get.docker.com | sh && sudo usermod -aG docker \$USER)" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bash <(curl -fsSL https://raw.githubusercontent.com/abilityai/trinity/v0.9.5/scripts/deploy/trinity-do-create.sh) How it starts
The opening of the file, as written. The whole thing — 667 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy Trinity
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.deploy-new-instance vX.Y — recent: <summary>. Then proceed.
Set up a Trinity instance and create a complete operations agent to manage it.
What you'll get:
- A running Trinity instance (if fresh install) — your own self-hosted operating system for the AI-native company
- A fully configured ops agent cloned from trinity-ops-public
- 13 built-in skills:
/status,/restart,/update,/logs,/agents,/cleanup,/diagnose,/rebuild-agent,/rollback,/telemetry,/provision,/migrate-to-postgres,/sync-ops-knowledge
STEP 1: Deployment Mode
Use AskUserQuestion:
- Question: "How will you run Trinity?"
- Header: "Trinity Deployment"
- Options:
- DigitalOcean, guided installer — Trinity's own one-command installer: a new Droplet behind HTTPS in about ten minutes (~$48/month, billed by DigitalOcean)
- Self-hosted, remote server — VPS, GCP, AWS, or any SSH-accessible machine
- Self-hosted, local Docker — Docker running on this machine
PATH A: DigitalOcean (guided installer)
Trinity ships its own installer for this (scripts/deploy/trinity-do-create.sh, v0.9.5+): it creates a stock Ubuntu Droplet (s-4vcpu-8gb, about $48/month until the Droplet is deleted), installs Trinity from prebuilt images on first boot, and serves it over HTTPS with a real certificate for the IP address. There is no managed Trinity hosting — this is the least-infrastructure path.
The installer asks for the admin password and a Claude subscription token in the user's own terminal. Never run it from this session and never ask for either secret here — the script is built to keep them off the screen and out of shell history.
Display:
## DigitalOcean Install
Run these in your own terminal (on Windows: inside WSL):
1. Install DigitalOcean's CLI (doctl) and authorise it: doctl auth init
2. Create a Claude subscription token: claude setup-token
(an sk-ant-oat01-… value — the installer refuses sk-ant-api03- API keys;
add an API key later under Settings → Integrations if you prefer one)
3. Pick an admin password: 12+ characters with upper/lowercase, a digit and a symbol.
4. Run the installer — it installs the release it was fetched from:
bash <(curl -fsSL https://raw.githubusercontent.com/abilityai/trinity/v0.9.5/scripts/deploy/trinity-do-create.sh)
(newer release? swap the tag — https://github.com/abilityai/trinity/releases)
It asks for the password, the token, a region and a Droplet name, shows the cost,
and asks before creating anything. About six minutes end to end.
5. When it prints "Trinity is ready", open https://<droplet-ip> and sign in as admin.
First-run setup opens — "Secure this instance" is the step worth doing now.
Full guide: https://docs.ability.ai/getting-started/deploying/digitalocean
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.
- 10d ago Changed · +1 lines 83db53142113
- 29d ago Changed · +37 lines 56259e1747ec
- 1mo ago Changed 65229bf5f69f
- 1mo ago First seen · 629 lines · 27 tokens per session scan F c1c2ad849298
deploy-new-instance is a skill published in the GitHub repository Abilityai/abilities (12 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 9,090 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it F with 5 findings (harvests environment variables, asks for root, reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.
Other skills, from other repositories
openshell-cli
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, profile management, policy iteration, settings, service exposure, BYOC workflows, and attached-provider inference. Covers basic through advanced multi-step workflows. Trigger…
azd-deployment
Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…
compute-env-setup
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
atmos-helmfile
Helmfile orchestration: sync/apply/destroy/diff, Kubernetes deployments, declarative Helm plugins, varfile generation, EKS integration, source management.