feature-development

A guided workflow for adding a new HyperShift HostedCluster Platform (HCP) feature with specialist coding agents. It covers the design, control plane, and data plane parts of the change.

In plain words
What is it for?
Use it to design API, command-line, and controller changes, then implement and test the control plane and data plane for a new HCP feature.
Why use it?
It divides a large platform change into connected stages, so implementation work can follow an agreed design and include tests.

Skill for Claude CodeCodex

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/openshift/hypershift/feature-development
Any agent
npx skills add openshift/hypershift --skill feature-development
Clone the repo
git clone --depth 1 https://github.com/openshift/hypershift

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 465 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00015 $0.00465
Opus 5 $0.00008 $0.00233
Sonnet 5 $0.00003 $0.00093
Haiku 4.5 $0.00002 $0.00047

Measured 2d ago against content hash 2e4d1b80a80e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-development 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.

.claude/skills/feature-development/SKILL.md · 39 lines

What it actually says

Implement support for a new HCP feature using specialized agents with explicit Task tool invocations:

[Extended thinking: This workflow orchestrates multiple specialized agents to implement a new HCP feature from design to deployment. Each agent receives context from previous agents to ensure coherent implementation.]

Use the Task tool to delegate to specialized agents in sequence:

  1. HCP architect design

    • Use Task tool with subagent_type="hcp-architect-sme"
    • Prompt: "Design the API and main abstractions for supporting a new platform feature: $ARGUMENTS. Include API changes, cli changes and controller changes"
    • Save the API design and main abstractions for next agents
  2. Control Plane Implementation

    • Use Task tool with subagent_type="control-plane-sme"
    • Prompt: "Implement the control plane changes needed to support the new feature: $ARGUMENTS. Use the hints from hcp-architect-sme [include output from step 1]"
    • Include unit, integration, and e2e tests
  3. Data plane Implementation

    • Use Task tool with subagent_type="data-plane-sme"
    • Prompt: "Implement the data plane changes needed to support the new feature: $ARGUMENTS"
    • Include unit, integration, and e2e tests
  4. Cloud provider integration

    • Use Task tool with subagent_type="cloud-provider-sme"
    • Prompt: "Review the control plane and data plane changes and implement any further changes needed to support the new feature and ensure it has proper cloud integration: $ARGUMENTS. Add support to create a new HostedCluster in the new platform via CLI"
    • Include unit, integration, and e2e tests
  5. HCP architect review

  • Use Task tool with subagent_type="hcp-architect-sme"
  • Prompt: "Review the changes implemented by the other agents for supporting a new feature: $ARGUMENTS. [Use the output from steps 2,3 and 4]. Report feedback and suggest changes"

Aggregate results from all agents and present a unified implementation plan.

Feature description: $ARGUMENTS

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. 2d ago First seen · 39 lines · 15 tokens per session scan A 2e4d1b80a80e

Subscribe to this mod's changes

feature-development is a skill published in the GitHub repository openshift/hypershift (538 stars, last pushed 2d ago), licensed Apache-2.0. It adds 15 tokens to every session and 465 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens