deploy

deploy is a command for Claude Code from dinhnguyenngoc/spec-driven-claude-code. It costs 10 tokens per session (7,270 once invoked), scanned A, original, MIT.

A staging-release command that builds the application, runs it in containers, checks its health, and deploys it to a staging environment. Staging is a test copy of the application, not the live production site.

In plain words
What is it for?
Use it to build Docker images, start the staging application, run deployment checks, and leave a tested release ready for human review.
Why use it?
It provides a controlled way to verify a release and recover if deployment fails. Production promotion remains a separate manual decision after people test the staging version.

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/dinhnguyenngoc/spec-driven-claude-code/deploy
Clone the repo
git clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-claude-code

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,270 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 $0.00010 $0.07270
Opus 5 $0.00005 $0.03635
Sonnet 5 $0.00002 $0.01454
Haiku 4.5 $0.00001 $0.00727

Measured 3d ago against content hash 8527bc983197, 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 3d 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.

curl -f http://localhost:${API_PORT}/health && echo "✓ Health OK"
.claude/commands/deploy.md · 557 lines

How it starts

The opening of the file, as written. The whole thing — 557 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/deploy — Release & Deployment (STAGING)

"Ship with confidence."

Purpose

Execute deployment to the STAGING environment (Docker Desktop / staging server): build images, run containers, verify health, rollback if needed.

Workspace Mode: if the session root declares Mode: workspace → resolve the target repo per CLAUDE.md §Workspace Mode before anything else; every path, probe, and gate below is relative to the target repo, and the workspace disk-check applies at the gate.

The kit's boundary (by design): /deploy is the last automated step — it pushes the artifact to staging with Status = STAGED, NOT production. After STAGED: the human test team checks it manually on staging (using reports/VERIFY_MATRIX.md as the test script) → decides go/no-go → promoting to production is a MANUAL step outside the kit, carried out per DEPLOY_RUNBOOK §8 Promote production. The kit never needs (and should never have) production credentials — least privilege. If you want to automate further later → add a separate /promote command, do not extend this one.

Note: Dockerfile and docker compose are created in /infra. This command executes deployment.

Stack Profile note: the sqlcmd/DB and dotnet ef commands below use the default profile (C#/.NET + SQL Server). Read Project Profile first: Oracle → sqlplus · MySQL → mysql · PostgreSQL → psql · MongoDB → mongosh (per rules/overrides/database-*.md); Core = Node.js → the migration steps map to the declared tool (prisma migrate deploy / migrate-mongo up) instead of dotnet ef. Core = PHPphp artisan migrate --force (--force because the deploy environment is non-interactive; add --isolated when several app instances start concurrently, so only one runs the migration), and php artisan config:cache / route:cache are part of the release step — see rules/overrides/framework-php-laravel.md §H for the config:cache caveat that makes env() return null outside config/.

Read the full file on GitHub · 557 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. 3d ago First seen · 557 lines · 10 tokens per session scan A 8527bc983197

Subscribe to this mod's changes

deploy is a command published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 4d ago), licensed MIT. It adds 10 tokens to every session and 7,270 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 2026-08-30.