Borrowing it
Nothing to install: this file belongs to Caspian-Sun/claude-code-workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Caspian-Sun/claude-code-workflow/main/.claude/commands/deploy.mdgit clone --depth 1 https://github.com/Caspian-Sun/claude-code-workflowWrote 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/commands/caspian-sun/claude-code-workflow/deploy)<a href="https://agentmods.dev/commands/caspian-sun/claude-code-workflow/deploy"><img src="https://agentmods.dev/badge/commands/caspian-sun/claude-code-workflow/deploy/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/commands/caspian-sun/claude-code-workflow/deploy"><img src="https://agentmods.dev/badge/commands/caspian-sun/claude-code-workflow/deploy.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 | $0.00000 | $0.04281 |
| Opus 5.5 | $0.00000 | $0.01712 |
| Sonnet 5.5 | $0.00000 | $0.00856 |
| Haiku 4.5 | $0.00000 | $0.00428 |
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 2mo 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.
→ Health check (curl access URL, expect HTTP 200) How it starts
The opening of the file, as written. The whole thing — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are now acting as a DevOps Engineer. Responsible for multi-platform builds, deployments, validations, and notifications.
Applicable Scenarios
- Development environment — local build + local preview
- Staging environment — CI/CD build + deploy to staging
- Production environment — CI/CD build + approval + deploy + canary release (optional)
- Multi-platform release — Web / iOS / Android / HarmonyOS simultaneously or separately
Input
| Input | Example | Behavior |
|---|---|---|
| No arguments | /deploy |
Interactive platform and environment selection |
| Platform | /deploy web |
Specify platform, interactive env selection |
| Platform + env | /deploy web --env staging |
Specify platform and environment |
| Multiple platforms | /deploy web,ios,android |
Deploy multiple platforms simultaneously |
| All platforms | /deploy all --env production |
Deploy all platforms to production |
| Canary | /deploy web --env production --canary 10% |
Canary release with 10% traffic |
| CI/CD type | /deploy web --ci github |
Specify CI/CD platform |
Platform × Environment Matrix
| Platform | dev (local) | staging (test) | production | Final Output |
|---|---|---|---|---|
| Web | pnpm build → local preview |
CI → server/CDN | CI → server/CDN + optional canary | 🌐 Access URL |
| iOS | Xcode build (simulator) | CI → TestFlight | CI → App Store Connect | 📱 TestFlight/store link |
| Android | Gradle build (debug APK) | CI → Pgyer/fir/file server | CI → Google Play | 📱 APK download link/store link |
| HarmonyOS | DevEco build (simulator) | CI → file server | CI → AppGallery Connect | 📱 HAP download link/store link |
Core goal: After a user runs
/deploy, the end result is a directly accessible/downloadable URL — not just "CI triggered".
Execution Flow
Step 1: Pre-checks (fail = stop immediately)
Execute in order; any failure causes an error and terminates:
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.
- 2mo ago First seen · 491 lines · 0 tokens per session scan A 51b8fc23ec1a
deploy is a command published in the GitHub repository Caspian-Sun/claude-code-workflow (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,281 tokens. 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 commands, from other repositories
vibe-agents
Step 4 of the vibe-coding workflow: generate AGENTS.md + tool configs so the AI builder stays on track.
spark-prairie-fire
A command that applies the Spark Prairie Fire method to choose a starting point and a small first step for a new task. It produces an assessment, a three-step plan, and a check against spreading the work too widely.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
upgrade
Keep dependencies current and the GitHub security tab clean — CVE fixes through pnpm overrides, red Dependabot PRs taken over, routine bumps landed, CodeQL alerts triaged. Autonomous by default, one PR per lane, asks nothing.
review
Review proposed ADRs for lifecycle progression — accept implemented decisions, deprecate stale ones, archive trivial ones.
from-spec
Extract Architecture Decision Records from a completed spec.