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 commands/caspian-sun/claude-code-workflow/buildgit clone --depth 1 https://github.com/Caspian-Sun/claude-code-workflowWhat 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 | $0.00000 | $0.01812 |
| Opus 5 | $0.00000 | $0.00906 |
| Sonnet 5 | $0.00000 | $0.00362 |
| Haiku 4.5 | $0.00000 | $0.00181 |
Grade A, and why
build scanned grade A with 0 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 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are now acting as a Build Engineer. Responsible for multi-platform builds, artifact validation, and local preview.
Core Scope
/build does exactly three things: Build → Validate → Local-ready. No uploading, deploying, or notifications.
Once artifacts are confirmed good, use /deploy to push them to a server or platform.
Input
| Input | Example | Behavior |
|---|---|---|
| No arguments | /build |
Interactive platform selection |
| Platform | /build web |
Build Web |
| Multiple platforms | /build web,android |
Multi-platform build |
| All platforms | /build all |
Build all platforms |
| Specific env | /build web --env staging |
Build with staging config (different env vars / API URLs) |
| Skip preview | /build web --no-preview |
Build only, do not start local preview |
| Clean rebuild | /build web --clean |
Clean previous artifacts, then rebuild |
Execution Flow
Step 1: Pre-checks
- Dependency check —
node_modulesexists and is non-empty; otherwise promptpnpm install - Type check (Web) —
workspace/src/types/api.tsexists; otherwise promptpnpm gen:api - Environment config — read
--envargument to determine build env vars (default: dev)
Step 2: Build
Execute per platform:
| Platform | Build Command | Artifact Path | Artifact Type |
|---|---|---|---|
| Web | pnpm build |
workspace/dist/ |
Static files (HTML/JS/CSS) |
| Android | cd android && ./gradlew assembleDebug (dev) / assembleRelease (staging/prod) |
android/app/build/outputs/apk/ |
.apk |
| iOS | cd ios && xcodebuild build (simulator) / archive (device) |
ios/build/ |
.app (simulator) / .ipa (device) |
| HarmonyOS | cd harmony && hvigorw assembleHap |
harmony/build/ |
.hap |
Stream build logs in real time; on failure, output complete error info and stop.
Step 3: Artifact Validation
Automatically validate after build completes:
Web:
dist/index.htmlexists- At least 1
.jsand 1.cssfile present - Total artifact size is reasonable (not 0, not above warning threshold)
- Output file count and total size
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 · 205 lines · 0 tokens per session scan A 33d900eb4662
build is a command published in the GitHub repository Caspian-Sun/claude-code-workflow (10 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,812 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
generate-rules
Generate development rules and standards into RULES.md.
a11y-audit
Web accessibility (WCAG 2.1) audit command. axe-core-based checks via PageSpeed Insights.
kotlin-build
Fix Kotlin/Gradle build errors, compiler warnings, and dependency issues incrementally. Invokes the kotlin-build-resolver agent for minimal, surgical fixes.
gradle-build
Fix Gradle build errors for Android and KMP projects.
vibe-agents
Step 4 of the vibe-coding workflow: generate AGENTS.md + tool configs so the AI builder stays on track.
sync-linear
Sync current work with Linear ticket status.