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/wangke19/gemini-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/wangke19/gemini-ai-helpers/two-node-origin-pr-helper)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/two-node-origin-pr-helper"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/two-node-origin-pr-helper.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.01143 |
| Opus 5 | $0.00017 | $0.00571 |
| Sonnet 5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
two-node-origin-pr-helper 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 4d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
/origin:two-node-origin-pr-helper — Review Two Node (Fencing/Arbiter) tests in openshift/origin.
Synopsis
/origin:two-node-origin-pr-helper [--url PR_URL] [<pr>] [--depth quick|full]
Description
The /origin:two-node-origin-pr-helper command is an expert review tool for PRs that add or modify Two Node (Fencing or Arbiter) tests under test/extended/two_node/ in openshift/origin.
It:
- Discovers changed Two Node test files from the current branch.
- Analyzes Ginkgo Describe / Context / It blocks, suite tags, and [Serial] markers.
- Reviews test logic, structure, cleanup, and determinism.
- Suggests reuse of existing Origin and Kubernetes helpers instead of ad-hoc code.
- Recommends suite + [Serial] tagging and CI coverage.
- Generates ready-to-paste PR description text for the Origin PR.
- Suggests CI lane characteristics for openshift/release (without generating full PR text).
Use this command when creating or reviewing Origin PRs that touch the Two Node test suite and you want a focused, reproducible review of test design, helper usage, and CI integration.
This is a specialized Origin review helper focused on Two Node tests and is intended as a building block toward a future generic Origin review command.
Implementation
The command should behave as follows.
1. Argument handling
Parse arguments from the invocation:
-
--url:
- Optional full PR URL (example: https://github.com/openshift/origin/pull/30510)
- When provided, this takes precedence over any local git information.
-
(optional positional):
- Optional PR number (example: 30510)
-
--depth:
- quick: short, high-level summary
- full: detailed four-section output (default)
Default behavior:
- If --url is provided, use that PR.
- Else if is provided, use that PR in the current repo.
- Else infer the PR from the current git repository remote and branch name.
- Fail with a clear error message if the PR cannot be determined.
2. Automatically discover relevant 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.
- 4d ago First seen · 175 lines · 34 tokens per session scan A d4ab8609e434
two-node-origin-pr-helper is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,143 once invoked, about $0.0002 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 2026-09-03.
Other commands, from other repositories
final-review
Command "final-review" from adriannoes/awesome-agentic-ai, covering final review - comprehensive pr review & testing, step 0: determine review pass, step 1: create or update the pr, step 2: launch three review agents in parallel and agent 1: codebase consistency reviewer.
test
Write tests before implementation using Red-Green-Refactor.
bmad-review-verification-gap
Deprecated — forwards to bmad-review.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.