platform-build

platform-build is a skill for Claude Code, Codex from telus-labs/stagecraft. It costs 36 tokens per session (747 once invoked), scanned A, original, MIT.

A build-stage guide for platform developers setting up infrastructure and deployment support for a new feature.

In plain words
What is it for?
It helps create or update Docker Compose services, environment examples, web-server configuration, package scripts, shared tool settings, and stage-gate documentation.
Why use it?
It provides a defined process for coordinating application services, local development, health checks, secrets, and continuous integration setup.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/telus-labs/stagecraft/platform-build
Any agent
npx skills add telus-labs/stagecraft --skill platform-build
Clone the repo
git clone --depth 1 https://github.com/telus-labs/stagecraft

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for platform-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/telus-labs/stagecraft/platform-build.svg)](https://agentmods.dev/skills/telus-labs/stagecraft/platform-build)
Your own site
<a href="https://agentmods.dev/skills/telus-labs/stagecraft/platform-build"><img src="https://agentmods.dev/badge/skills/telus-labs/stagecraft/platform-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 747 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 5.1 $0.00036 $0.00747
Opus 5 $0.00018 $0.00374
Sonnet 5 $0.00007 $0.00149
Haiku 4.5 $0.00004 $0.00075

Measured 5d ago against content hash d6bea2971c68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

platform-build 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 5d 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 -i http://localhost/api/health`
skills/platform-build/SKILL.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Platform Build Task (Stage 4)

Use this skill when you are the Platform Developer executing the Stage 4 build stage — setting up infra, CI, and the deploy rails for a new feature.

Procedure

  1. Read pipeline/design-spec.md — set up infra, CI, and root toolchain config to support what's being built.

  2. Append an ## Assumptions block to pipeline/context.md for non-obvious infra choices (ports, volumes, healthcheck targets) per coding-principles §1. Write the Plan preamble at the top of pipeline/pr-platform.md per §4.

  3. Write or update docker-compose.yml in the project root:

    • Define a service for each component in the design spec
    • Add a healthcheck: to every HTTP service so docker compose up --wait works
    • Use .env for all secrets and environment-specific values — never hardcode
    • Mount source directories as volumes for local dev hot-reload where appropriate
  4. Write or update any supporting infra/toolchain config (.env.example, nginx config, package.json scripts, lockfiles, ESLint/TypeScript config, Docker/compose files, etc.). Root package-manager scripts and shared toolchain config are platform-owned unless the design spec or a Principal ruling assigns them elsewhere. If npm run lint is missing, add the script and any minimal config needed for Stage 4a to run it mechanically. Keep source-code changes inside src/infra/; cross-boundary edits need a CONCERN: line first (coding-principles §3).

  5. Finish pipeline/pr-platform.md. Include ## Out of Scope — Noticed. Also:

    • ## Verify — required before writing a PASS gate. One bullet per infrastructure criterion you claim to have satisfied, in this exact shape:

      ## Verify
      
      - **AC-7**: docker-compose brings the stack up cleanly
        - `docker compose up --wait`
        - → `Network created`, `Container api healthy`, `Container db healthy`,
          exit 0 after 14s
      - **AC-8**: nginx forwards /api to backend on port 3000
        - `curl -i http://localhost/api/health`
        - → `HTTP/1.1 200 OK`, body `{"status":"ok"}`, no nginx 502
      

Read the full file on GitHub · 57 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. 5d ago First seen · 57 lines · 36 tokens per session scan A d6bea2971c68

Subscribe to this mod's changes

platform-build is a skill published in the GitHub repository telus-labs/stagecraft (6 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 747 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

dokploy-deploy

This skill should be used when user asks to "deploy with Dokploy", "use Dokploy Cloud", "manage self-hosted Dokploy", "deploy Docker Compose on Dokploy", "manage Dokploy databases", "configure Dokploy domains", or "look up Dokploy CLI commands".

fcakyon/claude-codex-settings · 63 tokens

kubernetes

Kubernetes operations expert for kubectl, pods, deployments, and debugging.

RightNow-AI/openfang · 17 tokens

gcp-essentials

Use when running a small product on core Google Cloud via the gcloud CLI: a project, Cloud Run deploys, a locked-down Cloud Storage bucket, managed Cloud SQL, and least-privilege IAM wiring them together. NOT AWS (that is aws-essentials), NOT the CI pipeline that ships the image (that is deployment), NOT Postgres…

ericrisco/rsc-harness · 91 tokens

huawei-cce

Use when creating or managing CCE Kubernetes clusters. Covers cluster creation, node pools, SWR registry, autoscaling. Triggers: CCE, Kubernetes, K8s, cluster, node pool, container, SWR. NOT for: serverless functions (use huawei-functiongraph), serverless containers (use huawei-cce for CCI redirect).

huaweicloud/huaweicloud-devkit · 78 tokens

kubernetes

Diagnose and fix Kubernetes pods, services, networking, storage, and rollout failures with kubectl. Safety-first, read-only by default.

vladkesler/initrunner · 31 tokens

ring:creating-helm-charts

Creating Helm charts to Lerian conventions via ring:helm: standardized chart structure, full env-var coverage from .env.example, security defaults (runAsNonRoot, readOnlyRootFilesystem), ClusterIP-only services, and health probes; validates helm lint and template render. Use when creating, modifying, or reviewing a…

LerianStudio/ring · 92 tokens