deploy

A command for shipping application code to a live environment such as containers, virtual machines, edge functions, Kubernetes, or mobile stores. It has execute, check, and onboarding modes driven by a deployment configuration file.

In plain words
What is it for?
Use it to create deployment configuration, inspect the current deployment setup, or deploy an application to its production environment. It can detect platform clues such as Docker, Vercel, Fly, Kubernetes, and Azure files.
Why use it?
It separates deploying running software from releasing packages to registries such as npm or PyPI. Check mode can detect deployment drift without deploying, while onboarding helps define the required deployment details.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/terrene-foundation/metis/deploy
Clone the repo
git clone --depth 1 https://github.com/terrene-foundation/metis

Made for: Claude Code.

Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,949 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.01949
Opus 5 $0.00012 $0.00975
Sonnet 5 $0.00005 $0.00390
Haiku 4.5 $0.00002 $0.00195

Measured 2d ago against content hash 0759d4b25139, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy 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.

LIVE_HTML=$(curl -fsSL -H "Cache-Control: no-cache" -H "Pragma: no-cache" "$LIVE_URL")
.claude/commands/deploy.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/deploy - Application Deployment

For applications that ship code to running environments (containers, edge functions, VMs, k8s, mobile stores). Driven by deploy/deployment-config.md.

NOT to be confused with /release/release publishes packages to artifact registries (PyPI, crates.io, npm). /deploy ships running code. If your repo's deploy/deployment-config.md declares type: sdk, this command redirects to /release.

Mode Detection

/deploy            → Execute mode
/deploy --check    → Check mode (drift detection only, no deploy)
/deploy --onboard  → Onboard mode (create deployment-config.md)

If deploy/deployment-config.md does NOT exist → Onboard Mode

Run the application deployment onboarding process. See skills/10-deployment-git/application-deployment.md.

  1. Detect platform — read repo for clues: Dockerfile, vercel.json, fly.toml, app.yaml, kubernetes/, azure-pipelines.yml, containerapps/, Procfile, native binaries
  2. Ask the human — what platform, what deploy command, what counts as "production code", how to query current deployed state, staging required?
  3. Research current best practices — web search for platform-specific deploy patterns (Container Apps revisions, Fly machines, Cloud Run revisions, etc.). Do NOT rely on encoded knowledge — cloud platform CLIs change frequently.
  4. Create deploy/deployment-config.md — see schema in skills/10-deployment-git/application-deployment.md
  5. STOP — present to human for review

If deploy/deployment-config.md declares type: sdk → Redirect

This repo is an SDK. Run /release instead — it handles version bumping, PyPI/registry publishing, and artifact validation.

If deploy/deployment-config.md declares type: application → Execute Mode

Read the config and execute. Print the 10-step DEPLOY CHECKLIST at the start of the response and check off boxes as each step passes. Do NOT report deploy as complete until every box is checked. The full checklist text and per-step guidance lives in rules/deploy-hygiene.md Rule 8 and skills/10-deployment-git/application-deployment.md. If any step fails, say "DEPLOY FAILED AT STEP N: " — NOT "build succeeded, will redeploy soon".

Read the full file on GitHub · 136 lines

Changes

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.

  1. 2d ago First seen · 136 lines · 23 tokens per session scan A 0759d4b25139

Subscribe to this mod's changes

deploy is a command published in the GitHub repository terrene-foundation/metis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 1,949 once invoked, about $0.0001 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.