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/coderabbit-inheritance-scanner)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/coderabbit-inheritance-scanner"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/coderabbit-inheritance-scanner/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/wangke19/gemini-ai-helpers/coderabbit-inheritance-scanner"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/coderabbit-inheritance-scanner.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 | $0.00017 | $0.01357 |
| Opus 5 | $0.00009 | $0.00678 |
| Sonnet 5 | $0.00003 | $0.00271 |
| Haiku 4.5 | $0.00002 | $0.00136 |
Grade A, and why
coderabbit-inheritance-scanner 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 9d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
teams:coderabbit-inheritance-scanner
Synopsis
/teams:coderabbit-inheritance-scanner
/teams:coderabbit-inheritance-scanner --dry-run
Description
The teams:coderabbit-inheritance-scanner command scans all repositories in the openshift GitHub organization that contain a .coderabbit.yaml or .coderabbit.yml file and verifies each one has inheritance: true set. This ensures repos with custom CodeRabbit configurations still inherit the org-wide review rules defined in openshift/coderabbit.
The openshift/coderabbit repo itself is excluded from results since it is the source of the global rules.
After scanning, the command offers to open PRs on non-compliant repos to add inheritance: true. PRs are always opened from a personal fork to avoid needing direct push access to upstream repos.
Arguments
--dry-run: Perform all scanning and checks (including searching for existing PRs) but do not actually create forks, push branches, or open PRs. Displays exactly what would be done for each non-compliant repo.
Implementation
Prerequisites
- GitHub CLI (
gh): Must be installed and authenticated with access to theopenshiftorg.
The token must have thegh auth statusworkflowscope to sync forks that contain GitHub Actions workflow files. If missing, warn the user and skip those repos rather than failing.
Steps
-
Search for
.coderabbit.yamlfiles across the openshift org using theteams:coderabbit-inheritance-scanner-searchskill. Use GitHub code search viagh apito find repos efficiently. -
For each repo, fetch the raw file and check for
inheritance: true. Use theteams:coderabbit-inheritance-scanner-checkskill to classify each repo as compliant, non-compliant (missing key), non-compliant (explicitly false), or error. -
For each non-compliant repo, check for an existing open PR whose title contains
"CodeRabbit inheritance"(case-insensitive substring match, since teams sometimes modify the PR title to satisfy merge requirements). Use theteams:coderabbit-inheritance-scanner-existing-prskill. Record the PR URL and how long it has been open.
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.
- 9d ago First seen · 113 lines · 17 tokens per session scan A d03178caeb96
coderabbit-inheritance-scanner is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 1,357 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
gsd:pr-branch
Create a clean PR branch by filtering out .planning/ commits — ready for code review.
commit-push-pr
You are executing the commit-push-pr workflow - the most frequently used inner-loop command.
wtfp:contribute
Guide a bounded WTF-P contribution from branch creation through a reviewable change request.
pr-risk
Calculate a composite PR risk score (size, complexity, test coverage, dependencies, security) before merging or reviewing. Detects large PRs needing splits and generates a context-aware pre-merge checklist. Run before /review-pr or before opening a PR. Usage: /pr-risk [branch or commit range] (default: HEAD1..HEAD).
recreate-pr
Create a copy of an existing PR with review comments summarized as fixes. This allows Gemini (or other reviewers) to re-review the changes.
commit
A focused pipeline: understand the change, hold it to the four quality dimensions, fix the safe stuff, then commit with a clean message. No ceremony — no ticket lookup, no metrics.