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 skills add gul-labs/craftsman-marketplace --skill craft-infragit clone --depth 1 https://github.com/gul-labs/craftsman-marketplaceWrote 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/skills/gul-labs/craftsman-marketplace/craft-infra)<a href="https://agentmods.dev/skills/gul-labs/craftsman-marketplace/craft-infra"><img src="https://agentmods.dev/badge/skills/gul-labs/craftsman-marketplace/craft-infra/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/skills/gul-labs/craftsman-marketplace/craft-infra"><img src="https://agentmods.dev/badge/skills/gul-labs/craftsman-marketplace/craft-infra.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 | $0.00142 | $0.02783 |
| Opus 5 | $0.00071 | $0.01392 |
| Sonnet 5 | $0.00028 | $0.00557 |
| Haiku 4.5 | $0.00014 | $0.00278 |
Grade A, and why
craft-infra 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 12d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infra Craft
This skill encodes one engineer's standard for shipping and running services reliably, applied the same way across every repo. The method and opinions live here; the project specifics (hosting platform, CI system, IaC tool, env-var schema) live in the target repo's code and config — always discover them, never assume or hardcode.
Operating principle — discover before you build
Different repos already have different pieces in place. Before adding anything, spend a couple of minutes mapping what exists so you extend rather than duplicate or conflict:
package.json/ lockfile → build tooling, runtime adapters (e.g.@vercel/node,flyCLI hints, serverless framework packages).- CI config files (
.github/workflows/,.circleci/,Jenkinsfile,.gitlab-ci.yml) → existing gates, deploy steps, environment secrets. - Env-var schema (
env.ts,config.ts,.env.example,zodschemas) → which vars are required, which are optional, where validation happens. - Health/readiness endpoints (
/health,/ready,/api/healthz) and how they're registered. - IaC files (
terraform/,pulumi/,cdk/,fly.toml,vercel.json,render.yaml) → existing resource definitions to extend rather than replace.
State what you found, then propose the smallest set of additions that closes the gaps.
The infra layers (work in this order)
- Config — all configuration flows through a validated env schema that fails closed on missing
required values. A missing prod var should crash at startup, not surface as a 500 at runtime.
See
references/config.md. - Build & release — builds are reproducible and produce immutable artifacts; the release
process is documented and automated enough that any team member can trigger it. See
references/build-release.md. - CI/CD — gates (lint, typecheck, tests, build) block merge; deploys are automated and
reversible. Manual prod edits are the failure mode, not the workflow. See
references/ci-cd.md. - Runtime health — every service exposes health and readiness probes; graceful shutdown drains
in-flight requests; connection pools are sized and scoped to the runtime model (serverless vs
long-lived). See
references/runtime-health.md. - Scale & resilience — timeouts, retries with backoff, circuit breakers, and capacity limits
that match the actual runtime model. Serverless runtimes do not guarantee shared or durable
in-process state across invocations/instances — warm instances may reuse module-scope state but
this is neither guaranteed nor shared globally and can disappear at any time. Anything that
assumes a long-lived process (in-memory pools, local metrics registries) needs a flag or
replacement. See
references/scale-resilience.md.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 172 lines · 142 tokens per session scan A d293e8a4009a
craft-infra is a skill published in the GitHub repository gul-labs/craftsman-marketplace (1 stars, last pushed today), licensed MIT. It adds 142 tokens to every session and 2,783 once invoked, about $0.0007 per session on Opus 5. 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 skills, from other repositories
deploy
Elixir/Phoenix deployment patterns — Dockerfile, fly.toml, runtime.exs, mix release, rel/ overlays. Use when configuring Fly.io, Docker, CI/CD, health checks, or production migrations.
dockerized-service-release-deployment-workflow
Create a Dockerized-service release contract with clean GitHub Actions builds, main-anchored tags, immutable digest manifests, published-release deployments, production approval, health checks, and exact-digest rollback.
expert-devops
DevOps/infrastructure specialist — CI/CD pipelines, Docker, Kubernetes, cloud config, deploy strategy, monitoring, incident triage, migrations. Use for any task touching build systems, environments, releases, or reliability. Normally invoked by model-router.
ci-cd-pipeline
Use near the end of a project to generate CI and make the app deploy-ready. Produces a polyglot GitHub Actions workflow (lint, typecheck, test, build) and multi-stage Dockerfiles. The finish line is CI-green and container-ready, not an actual deploy.
deploy-planner
Deployment and DevOps agent that generates Dockerfiles, CI/CD configs, and step-by-step deployment guides for free hosting platforms. Triggers on: deploy, launch, hosting, Docker, CI/CD, production, go live, ship it.
devops-engineer
Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates. Handles deployment automation, GitOps configuration, incident response runbooks, and internal developer platform tooling. Use when setting up CI/CD pipelines, containerizing…