platform-ci

platform-ci is a skill for Claude Code from alimobrem/openshift-platform-skills. It costs 87 tokens per session (1,165 once invoked), scanned A, original, MIT.

An OpenShift skill for building container images with Shipwright and creating CI/CD pipelines with Tekton. It works with the YAML resource types used to define builds, pipelines, tasks, and triggers.

In plain words
What is it for?
Use it to generate, review, debug, or explain Shipwright builds and Tekton pipelines, including their tasks, runs, event listeners, and triggers.
Why use it?
It helps avoid invalid resource types, API versions, field names, and YAML examples when configuring OpenShift builds or pipelines.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the platform-skills plugin — 4 skills shipped together

Good fit Use it to generate, review, debug, or explain Shipwright builds and Tekton pipelines, including their tasks, runs, event listeners, and triggers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alimobrem/openshift-platform-skills/platform-ci
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.

Any agent
npx skills add alimobrem/openshift-platform-skills --skill platform-ci
Clone the repo
git clone --depth 1 https://github.com/alimobrem/openshift-platform-skills

Made for: Claude Code.

Or install platform-skills, the plugin that ships this one along with the rest of its 4 skills.

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-ci

README.md
[![agentmods](https://agentmods.dev/badge/skills/alimobrem/openshift-platform-skills/platform-ci/github.svg)](https://agentmods.dev/skills/alimobrem/openshift-platform-skills/platform-ci)
Your own site
<a href="https://agentmods.dev/skills/alimobrem/openshift-platform-skills/platform-ci"><img src="https://agentmods.dev/badge/skills/alimobrem/openshift-platform-skills/platform-ci/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.

agentmods 80×15 button for platform-ci

Your own site · 80×15
<a href="https://agentmods.dev/skills/alimobrem/openshift-platform-skills/platform-ci"><img src="https://agentmods.dev/badge/skills/alimobrem/openshift-platform-skills/platform-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,165 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00087 $0.01165
Opus 5 $0.00044 $0.00583
Sonnet 5 $0.00017 $0.00233
Haiku 4.5 $0.00009 $0.00117

Measured 10d ago against content hash b1018659458a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

platform-ci 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 10d 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.

skills/platform-ci/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenShift CI/CD — Builds & Pipelines

Skill for container image builds (Shipwright) and CI/CD pipelines (Tekton) on OpenShift.

Rules

  1. Always use correct apiVersion and kind. Every CRD example must use the real apiVersion from the CRD table below. Never invent CRDs or apiVersions.
  2. Load references on-demand. Only read reference files when the user's question requires detailed field-level knowledge. Do not preload all references.
  3. Validate YAML before presenting. Every YAML example must be syntactically valid and use real field names from the CRD schemas.
  4. Prefer canonical patterns. Use patterns from reference docs as starting points. Adapt to the user's specifics rather than inventing from scratch.

How This Skill Works

User asks about Reference Topic
Builds, images, Buildah, BuildConfig, Shipwright, BuildRun references/shipwright.md Build
Pipelines, Tasks, Triggers, CI, OpenShift Pipelines, PipelineRun references/tekton.md Pipeline

Load the matching reference file before answering. Max 1 reference file per request.

CRD Reference Table

Kind apiVersion Project
Build shipwright.io/v1beta1 Shipwright
BuildRun shipwright.io/v1beta1 Shipwright
BuildStrategy shipwright.io/v1beta1 Shipwright
ClusterBuildStrategy shipwright.io/v1beta1 Shipwright
Pipeline tekton.dev/v1 Tekton Pipelines
PipelineRun tekton.dev/v1 Tekton Pipelines
Task tekton.dev/v1 Tekton Pipelines
TaskRun tekton.dev/v1 Tekton Pipelines
EventListener triggers.tekton.dev/v1beta1 Tekton Triggers
TriggerBinding triggers.tekton.dev/v1beta1 Tekton Triggers
TriggerTemplate triggers.tekton.dev/v1beta1 Tekton Triggers

Safety Model

Every write operation follows a 3-step protocol: Generate, Preview, Confirm.

Read-only operations (status checks, log inspection) do NOT require confirmation.

Read the full file on GitHub · 99 lines

Files

What ships with it

3 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.

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. 10d ago First seen · 99 lines · 87 tokens per session scan A b1018659458a

Subscribe to this mod's changes

platform-ci is a skill published in the GitHub repository alimobrem/openshift-platform-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,165 once invoked, about $0.0004 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.