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.
git clone --depth 1 https://github.com/openshift-eng/ai-helpersWrote 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/commands/openshift-eng/ai-helpers/setup)<a href="https://agentmods.dev/commands/openshift-eng/ai-helpers/setup"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/setup/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/commands/openshift-eng/ai-helpers/setup"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/setup.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 | $0.00013 | $0.00714 |
| Opus 5.5 | $0.00005 | $0.00286 |
| Sonnet 5.5 | $0.00003 | $0.00143 |
| Haiku 4.5 | $0.00001 | $0.00071 |
Grade A, and why
setup 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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
node-team:setup
Synopsis
/node-team:setup <component> [--ticket OCPNODE-1234] [--pr 456]
Description
Sets up a development environment for a Node team component. Clones the appropriate downstream or upstream repo (based on the component-to-repo mapping), creates a git worktree for the task, and installs the node-team plugin locally in the worktree.
When given a Jira ticket or PR number, names the worktree after it and (for tickets) fetches the issue summary to confirm the right component.
Implementation
- Run the checks from
/node-team:preflightto confirm GitHub and Jira tokens are valid. If any required check fails, stop and show remediation steps before proceeding. - Read the component-to-repo mapping from
shared/components.md.
Match the
<component>argument against the "Day-to-Day Dev Shorthand" table or the full component names (case-insensitive, partial match OK). If ambiguous, ask the user to clarify. - Determine the repo URL. For OpenShift-specific work, use the downstream fork. For upstream contributions, use the upstream repo. If unclear, ask the user.
- Clone the repo if not already present in the current directory:
git clone <repo-url> cd <repo-name> - Create a worktree following the workflow in
SETUP.md:
--ticket OCPNODE-1234: name the worktree after the ticket (wt/ocpnode-1234), fetch issue details from Jira to confirm the component matches--pr 456: fetch the PR and create a worktree for it (pr-456)- Neither: deduce a name from the task context
- Install the node-team plugin in the worktree:
claude plugin install node-team@ai-helpers --scope local - Print the worktree path and a short summary of what was set up.
Return Value
- The path to the created worktree and confirmation of plugin installation
Examples
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.
- 1mo ago First seen · 83 lines · 13 tokens per session scan A 058f6d97cd80
setup is a command published in the GitHub repository openshift-eng/ai-helpers (121 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 714 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other commands, from other repositories
new-wp-plugin
Create a new WordPress plugin from the latest WP Plugin Starter release as a private GitHub repo.
sdk-release
You are an autonomous engineer for the cashfree/agent-skills repository. An issue labelled sdk-release reports that a new version of a Cashfree SDK or REST API has shipped. Your job: research the release from authoritative sources, update the changelog knowledge-base skill (and any integration skill the change…
api-resource-ship
TOTAL AUTONOMY — branch + pipeline + commit + push + PR for an API Platform feature. Refuses dirty tree. Loop REQUESTCHANGES cap 3. Skips secrets.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.