ROSA Command Authoring

Instructions for adding or changing commands in the ROSA command-line tool, which uses Cobra to define command-line commands and flags. They keep command wiring small and place the main behavior in the appropriate package.

In plain words
What is it for?
Use them when adding commands, changing flags or help, moving logic between folders, or refactoring command execution. They also cover formatting, tests, documentation checks, and related structure-test updates.
Why use it?
Command changes can break help text, flags, structure tests, or established execution patterns. These instructions point to the nearby code and checks that should be followed.

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/rosa/rosa-command-authoring
Any agent
npx skills add openshift/rosa --skill rosa-command-authoring
Clone the repo
git clone --depth 1 https://github.com/openshift/rosa

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 352 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 $0.00029 $0.00352
Opus 5 $0.00015 $0.00176
Sonnet 5 $0.00006 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured 2d ago against content hash 07fe676751e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ROSA Command Authoring 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/rosa-command-authoring/SKILL.md · 34 lines

What it actually says

ROSA Command Authoring

Use this skill when:

  • Adding a new rosa command or subcommand
  • Changing flags or command help
  • Moving logic between cmd/ and pkg/
  • Refactoring command execution flow

Workflow

  1. Read AGENTS.md and guidelines/command-guidelines.md, then inspect the nearest similar command implementation.
  2. Keep Cobra command files thin and move non-Cobra logic into pkg/.
  3. Follow the entrypoint and exit pattern already established in the nearest similar command area.
  4. Many ROSA commands use Run: run; do not switch a command area between Run and RunE, or add/remove direct os.Exit() calls, unless the surrounding pattern already does so and the change keeps behavior consistent.
  5. Reuse output, reporter, and interactive patterns already used by the surrounding command area.
  6. If the command tree changes, update cmd/rosa/structure_test/command_structure.yml.
  7. If supported flags change, update the matching cmd/rosa/structure_test/command_args/**/command_args.yml.
  8. When command help or docs change, check whether make generate-docs is part of the required verification.

Verification

  • make fmt
  • relevant package tests or make test
  • make rosa
  • make generate-docs when command docs or help output changed

Follow CONTRIBUTING.md for the exact contributor workflow and hook expectations.

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 · 34 lines · 29 tokens per session scan A 07fe676751e3

Subscribe to this mod's changes

ROSA Command Authoring is a skill published in the GitHub repository openshift/rosa (103 stars, last pushed 2d ago), licensed Apache-2.0. It adds 29 tokens to every session and 352 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.