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/rebase)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/rebase"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/rebase.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 | $0.00015 | $0.01734 |
| Opus 5 | $0.00008 | $0.00867 |
| Sonnet 5 | $0.00003 | $0.00347 |
| Haiku 4.5 | $0.00002 | $0.00173 |
Grade A, and why
rebase 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
openshift:rebase
Synopsis
/openshift:rebase [tag]
Description
The /openshift:rebase command rebases git repository in the current working directory
to a new upstream release specified by [tag]. If no [tag] is specified, the command
tries to find the latest stable upstream release.
The repository must follow rules described in https://github.com/openshift/kubernetes/blob/master/REBASE.openshift.md,
namely all OpenShift-specific commits must have prefix UPSTREAM:.
Implementation
Pre-requisites
Three local remote repositories should be tracked from a local machine: origin
tracking the user's fork of this repository, openshift tracking this
repository and upstream tracking the upstream repository.
To verify the correct setup, use
git remote -v
Fail, if there is no upstream, origin or openshift remote.
Rebase to the new upstream version
-
Fetch all the remote repositories including tags
git fetch --all -
Find the main branch of the repository. It's either
masterormain. In the following steps, we will usemaster, but replace it with the main branch. -
If user did not specify an upstream tag to rebase to as
<tag>, find the greatest upstream tag that is not alpha, beta or rc. -
Create a new branch based on the newest tag $1 of the upstream repository. Name it after the tag.
git checkout -b rebase-<tag> <tag> -
Merge
openshift/masterbranch into therebase-$1branch with merge strategyours:git merge -s ours openshift/master -
Find the last rebase that has been done to
openshift/master. We will use the upstream tag used for this rebase as$previous_tag. -
Find the merge base of the
openshift/masterand$previous_tagby runninggit merge-base openshift/master $previous_tag. We will use this merge base as$mergebase. -
Prepare
commits.tsvtab-separated values file containing the set of carry commits in the openshift/master branch that need to be considered for picking:
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 · 147 lines · 15 tokens per session scan A 31f0983f9531
rebase is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,734 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 2026-09-03.
Other commands, from other repositories
wtfp:update
Check for a newer compatible package or plugin release and install it only after approval.
gse-deliver
Merge feature branches, tag release, cleanup. Triggered by /gse:deliver.
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.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.